Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/c125ff8d8d65413f96d0835687e08c3f
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/700901db62674be2b03755bc0e338023
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/d0d4756e1b2e4e3aa1a33b6d618d6eb3
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/e9e1fa14b770466ea1820943badec7af
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/eb3553c0dc274b1e9cf9ebe2bdd15a14
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/ea5f9e75c4ed44cf93a0583d0e2c1894
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/9520913a538b4a75a733db38ab77c84f
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/8dfe15c09aab4194a2f9ba8859c0d78a
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/e32ff523bbcb40839a33e8440c5d39d2
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/25a53cb251cc413aab379e9b5672ae07
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/f3986e559bd84d83b7bd9f0948c92de6
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/b0e79e4f34f3419a9c7c9f2a515ceb85
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/daef4008c8cb4a3f9ee1c62e2e7acd7f
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/10a7b99ee9bb47558ebb3ede5fad9009
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/42fe93ed7f304ff2bb3c62e27957f3c4
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/32fbd19d2d5849d7893710a165615960
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/953c13846bdc46fda6ecdf42e6f2a856
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/233d72bfd7034a1eafbd5db6e8c720d0
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/5bd69336082d41a88f6b39dedb8fb938
Description: <p>Marine Protected Areas (MPAs) are a cornerstone for the conservation of marine ecosystems. To be effective, these areas must be strategically located. To support the planning and establishment of MPAs and inform marine spatial planning, we identified areas that may support aggregations of foraging seabirds (“hotspots”) in the California Current System, a highly productive, large marine ecosystem on the west coast of North America. We developed habitat-association models for 16 species using information from at-sea observations collected over an 11-year period (1997-2008), bathymetric data, and remotely sensed oceanographic data. The surveys were conducted by several agencies and monitoring programs and extended from north of Vancouver Island to the US/Mexico border and seaward 600 km from the coast. We developed single-species predictive models using a machine-learning algorithm, bagged decision trees. Bathymetric variables were often important predictive variables, whereas oceanographic variables derived from remotely sensed data were generally less important. Model predictions were applied to the entire California Current for 4 months (February, May, July, October) as a proxy for seasons in each of 11 years. Single-species predictions were then combined to identify potential “hotspots” of seabird aggregation, using three criteria: (1) overall abundance among species, (2) importance of specific areas (“core areas”) to individual species, and (3) predicted persistence of hotspots across years. Potential hotspots often aligned with currently protected areas (e.g., National Marine Sanctuaries), but we also identified potential hotspots in Northern California/Southern Oregon (from Cape Mendocino to Heceta Bank) and Southern California (adjacent to the Channel Islands) that are not currently included in protected areas. Prioritization and identification of multi-species hotspots will depend on which group of species is of highest management priority. Modeling hotspots at a broad spatial scale can contribute to MPA planning, particularly if complemented by fine-scale information for focal areas. Because fishery extraction and changes in climate and oceanographic conditions have major impacts on coastal marine ecosystems, it is also important to consider how future climate change may affect the vulnerability of areas that are currently under protection.</p>
This dataset was uploaded to Data Basin and is available with additional information at: /datasets/44b7e042ef514b12b7cda75c7424acd4
Description: Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are Generalized Additive Models (GAMs) and Boosted Regression Trees (BRTs), but comparative studies have rarely been conducted; most rely on presence-only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals km-2) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness-of-fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991-2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.
Service Item Id: 3ae57892c8bc4c268565cbf878cf0fb3
Copyright Text: Becker, E.A., J.V. Carretta, K.A. Forney, J. Barlow, S. Brodie, R. Hoopes, M.G. Jacox, S.M. Maxwell, J.V. Redfern, N.B. Sisson, H. Welch, E.L. Hazen. 2020. Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees. Ecology and Evolution, 10, 5759-5784.
For Blue_whale_winter_spring:
Hazen, E. L., Palacios, D. M., Forney, K. A., Howell, E. A., Becker, E., Hoover, A. L., … Bailey, H. (2017). WhaleWatch: A dynamic management tool for predicting blue whale density in the California Current. Journal of Applied Ecology, 54(5), 1415–1428. https://doi.org/10.1111/1365‐2664.12820
For Humpback_whale_winter_spring and Fin_whale_winter_spring:
U.S. Department of the Navy. (2019). U.S. Navy Marine Species Density Database Phase III for the Northwest Training and Testing Study Area. NAVFAC Pacific Technical Report. Naval Facilities Engineering Command Pacific, Pearl Harbor, HI. 262 pp.
Description: Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are Generalized Additive Models (GAMs) and Boosted Regression Trees (BRTs), but comparative studies have rarely been conducted; most rely on presence-only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals km-2) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness-of-fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991-2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.
Service Item Id: 3ae57892c8bc4c268565cbf878cf0fb3
Copyright Text: Becker, E.A., J.V. Carretta, K.A. Forney, J. Barlow, S. Brodie, R. Hoopes, M.G. Jacox, S.M. Maxwell, J.V. Redfern, N.B. Sisson, H. Welch, E.L. Hazen. 2020. Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees. Ecology and Evolution, 10, 5759-5784.
For Blue_whale_winter_spring:
Hazen, E. L., Palacios, D. M., Forney, K. A., Howell, E. A., Becker, E., Hoover, A. L., … Bailey, H. (2017). WhaleWatch: A dynamic management tool for predicting blue whale density in the California Current. Journal of Applied Ecology, 54(5), 1415–1428. https://doi.org/10.1111/1365‐2664.12820
For Humpback_whale_winter_spring and Fin_whale_winter_spring:
U.S. Department of the Navy. (2019). U.S. Navy Marine Species Density Database Phase III for the Northwest Training and Testing Study Area. NAVFAC Pacific Technical Report. Naval Facilities Engineering Command Pacific, Pearl Harbor, HI. 262 pp.
Description: Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are Generalized Additive Models (GAMs) and Boosted Regression Trees (BRTs), but comparative studies have rarely been conducted; most rely on presence-only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals km-2) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness-of-fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991-2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.
Service Item Id: 3ae57892c8bc4c268565cbf878cf0fb3
Copyright Text: Becker, E.A., J.V. Carretta, K.A. Forney, J. Barlow, S. Brodie, R. Hoopes, M.G. Jacox, S.M. Maxwell, J.V. Redfern, N.B. Sisson, H. Welch, E.L. Hazen. 2020. Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees. Ecology and Evolution, 10, 5759-5784.
For Blue_whale_winter_spring:
Hazen, E. L., Palacios, D. M., Forney, K. A., Howell, E. A., Becker, E., Hoover, A. L., … Bailey, H. (2017). WhaleWatch: A dynamic management tool for predicting blue whale density in the California Current. Journal of Applied Ecology, 54(5), 1415–1428. https://doi.org/10.1111/1365‐2664.12820
For Humpback_whale_winter_spring and Fin_whale_winter_spring:
U.S. Department of the Navy. (2019). U.S. Navy Marine Species Density Database Phase III for the Northwest Training and Testing Study Area. NAVFAC Pacific Technical Report. Naval Facilities Engineering Command Pacific, Pearl Harbor, HI. 262 pp.
Description: Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are Generalized Additive Models (GAMs) and Boosted Regression Trees (BRTs), but comparative studies have rarely been conducted; most rely on presence-only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals km-2) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness-of-fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991-2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.
Service Item Id: 3ae57892c8bc4c268565cbf878cf0fb3
Copyright Text: Becker, E.A., J.V. Carretta, K.A. Forney, J. Barlow, S. Brodie, R. Hoopes, M.G. Jacox, S.M. Maxwell, J.V. Redfern, N.B. Sisson, H. Welch, E.L. Hazen. 2020. Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees. Ecology and Evolution, 10, 5759-5784.
For Blue_whale_winter_spring:
Hazen, E. L., Palacios, D. M., Forney, K. A., Howell, E. A., Becker, E., Hoover, A. L., … Bailey, H. (2017). WhaleWatch: A dynamic management tool for predicting blue whale density in the California Current. Journal of Applied Ecology, 54(5), 1415–1428. https://doi.org/10.1111/1365‐2664.12820
For Humpback_whale_winter_spring and Fin_whale_winter_spring:
U.S. Department of the Navy. (2019). U.S. Navy Marine Species Density Database Phase III for the Northwest Training and Testing Study Area. NAVFAC Pacific Technical Report. Naval Facilities Engineering Command Pacific, Pearl Harbor, HI. 262 pp.
Description: Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are Generalized Additive Models (GAMs) and Boosted Regression Trees (BRTs), but comparative studies have rarely been conducted; most rely on presence-only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals km-2) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness-of-fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991-2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.
Service Item Id: 3ae57892c8bc4c268565cbf878cf0fb3
Copyright Text: Becker, E.A., J.V. Carretta, K.A. Forney, J. Barlow, S. Brodie, R. Hoopes, M.G. Jacox, S.M. Maxwell, J.V. Redfern, N.B. Sisson, H. Welch, E.L. Hazen. 2020. Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees. Ecology and Evolution, 10, 5759-5784.
For Blue_whale_winter_spring:
Hazen, E. L., Palacios, D. M., Forney, K. A., Howell, E. A., Becker, E., Hoover, A. L., … Bailey, H. (2017). WhaleWatch: A dynamic management tool for predicting blue whale density in the California Current. Journal of Applied Ecology, 54(5), 1415–1428. https://doi.org/10.1111/1365‐2664.12820
For Humpback_whale_winter_spring and Fin_whale_winter_spring:
U.S. Department of the Navy. (2019). U.S. Navy Marine Species Density Database Phase III for the Northwest Training and Testing Study Area. NAVFAC Pacific Technical Report. Naval Facilities Engineering Command Pacific, Pearl Harbor, HI. 262 pp.
Description: Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are Generalized Additive Models (GAMs) and Boosted Regression Trees (BRTs), but comparative studies have rarely been conducted; most rely on presence-only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals km-2) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness-of-fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991-2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.
Service Item Id: 3ae57892c8bc4c268565cbf878cf0fb3
Copyright Text: Becker, E.A., J.V. Carretta, K.A. Forney, J. Barlow, S. Brodie, R. Hoopes, M.G. Jacox, S.M. Maxwell, J.V. Redfern, N.B. Sisson, H. Welch, E.L. Hazen. 2020. Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees. Ecology and Evolution, 10, 5759-5784.
For Blue_whale_winter_spring:
Hazen, E. L., Palacios, D. M., Forney, K. A., Howell, E. A., Becker, E., Hoover, A. L., … Bailey, H. (2017). WhaleWatch: A dynamic management tool for predicting blue whale density in the California Current. Journal of Applied Ecology, 54(5), 1415–1428. https://doi.org/10.1111/1365‐2664.12820
For Humpback_whale_winter_spring and Fin_whale_winter_spring:
U.S. Department of the Navy. (2019). U.S. Navy Marine Species Density Database Phase III for the Northwest Training and Testing Study Area. NAVFAC Pacific Technical Report. Naval Facilities Engineering Command Pacific, Pearl Harbor, HI. 262 pp.
Description: Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are Generalized Additive Models (GAMs) and Boosted Regression Trees (BRTs), but comparative studies have rarely been conducted; most rely on presence-only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals km-2) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness-of-fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991-2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.
Service Item Id: 3ae57892c8bc4c268565cbf878cf0fb3
Copyright Text: Becker, E.A., J.V. Carretta, K.A. Forney, J. Barlow, S. Brodie, R. Hoopes, M.G. Jacox, S.M. Maxwell, J.V. Redfern, N.B. Sisson, H. Welch, E.L. Hazen. 2020. Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees. Ecology and Evolution, 10, 5759-5784.
For Blue_whale_winter_spring:
Hazen, E. L., Palacios, D. M., Forney, K. A., Howell, E. A., Becker, E., Hoover, A. L., … Bailey, H. (2017). WhaleWatch: A dynamic management tool for predicting blue whale density in the California Current. Journal of Applied Ecology, 54(5), 1415–1428. https://doi.org/10.1111/1365‐2664.12820
For Humpback_whale_winter_spring and Fin_whale_winter_spring:
U.S. Department of the Navy. (2019). U.S. Navy Marine Species Density Database Phase III for the Northwest Training and Testing Study Area. NAVFAC Pacific Technical Report. Naval Facilities Engineering Command Pacific, Pearl Harbor, HI. 262 pp.
Description: Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are Generalized Additive Models (GAMs) and Boosted Regression Trees (BRTs), but comparative studies have rarely been conducted; most rely on presence-only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals km-2) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness-of-fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991-2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.
Service Item Id: 3ae57892c8bc4c268565cbf878cf0fb3
Copyright Text: Becker, E.A., J.V. Carretta, K.A. Forney, J. Barlow, S. Brodie, R. Hoopes, M.G. Jacox, S.M. Maxwell, J.V. Redfern, N.B. Sisson, H. Welch, E.L. Hazen. 2020. Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees. Ecology and Evolution, 10, 5759-5784.
For Blue_whale_winter_spring:
Hazen, E. L., Palacios, D. M., Forney, K. A., Howell, E. A., Becker, E., Hoover, A. L., … Bailey, H. (2017). WhaleWatch: A dynamic management tool for predicting blue whale density in the California Current. Journal of Applied Ecology, 54(5), 1415–1428. https://doi.org/10.1111/1365‐2664.12820
For Humpback_whale_winter_spring and Fin_whale_winter_spring:
U.S. Department of the Navy. (2019). U.S. Navy Marine Species Density Database Phase III for the Northwest Training and Testing Study Area. NAVFAC Pacific Technical Report. Naval Facilities Engineering Command Pacific, Pearl Harbor, HI. 262 pp.
Description: Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are Generalized Additive Models (GAMs) and Boosted Regression Trees (BRTs), but comparative studies have rarely been conducted; most rely on presence-only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals km-2) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness-of-fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991-2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.
Service Item Id: 3ae57892c8bc4c268565cbf878cf0fb3
Copyright Text: Becker, E.A., J.V. Carretta, K.A. Forney, J. Barlow, S. Brodie, R. Hoopes, M.G. Jacox, S.M. Maxwell, J.V. Redfern, N.B. Sisson, H. Welch, E.L. Hazen. 2020. Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees. Ecology and Evolution, 10, 5759-5784.
For Blue_whale_winter_spring:
Hazen, E. L., Palacios, D. M., Forney, K. A., Howell, E. A., Becker, E., Hoover, A. L., … Bailey, H. (2017). WhaleWatch: A dynamic management tool for predicting blue whale density in the California Current. Journal of Applied Ecology, 54(5), 1415–1428. https://doi.org/10.1111/1365‐2664.12820
For Humpback_whale_winter_spring and Fin_whale_winter_spring:
U.S. Department of the Navy. (2019). U.S. Navy Marine Species Density Database Phase III for the Northwest Training and Testing Study Area. NAVFAC Pacific Technical Report. Naval Facilities Engineering Command Pacific, Pearl Harbor, HI. 262 pp.
Description: Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are Generalized Additive Models (GAMs) and Boosted Regression Trees (BRTs), but comparative studies have rarely been conducted; most rely on presence-only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals km-2) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness-of-fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991-2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.
Service Item Id: 3ae57892c8bc4c268565cbf878cf0fb3
Copyright Text: Becker, E.A., J.V. Carretta, K.A. Forney, J. Barlow, S. Brodie, R. Hoopes, M.G. Jacox, S.M. Maxwell, J.V. Redfern, N.B. Sisson, H. Welch, E.L. Hazen. 2020. Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees. Ecology and Evolution, 10, 5759-5784.
For Blue_whale_winter_spring:
Hazen, E. L., Palacios, D. M., Forney, K. A., Howell, E. A., Becker, E., Hoover, A. L., … Bailey, H. (2017). WhaleWatch: A dynamic management tool for predicting blue whale density in the California Current. Journal of Applied Ecology, 54(5), 1415–1428. https://doi.org/10.1111/1365‐2664.12820
For Humpback_whale_winter_spring and Fin_whale_winter_spring:
U.S. Department of the Navy. (2019). U.S. Navy Marine Species Density Database Phase III for the Northwest Training and Testing Study Area. NAVFAC Pacific Technical Report. Naval Facilities Engineering Command Pacific, Pearl Harbor, HI. 262 pp.
Description: Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are Generalized Additive Models (GAMs) and Boosted Regression Trees (BRTs), but comparative studies have rarely been conducted; most rely on presence-only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals km-2) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness-of-fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991-2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.
Service Item Id: 3ae57892c8bc4c268565cbf878cf0fb3
Copyright Text: Becker, E.A., J.V. Carretta, K.A. Forney, J. Barlow, S. Brodie, R. Hoopes, M.G. Jacox, S.M. Maxwell, J.V. Redfern, N.B. Sisson, H. Welch, E.L. Hazen. 2020. Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees. Ecology and Evolution, 10, 5759-5784.
For Blue_whale_winter_spring:
Hazen, E. L., Palacios, D. M., Forney, K. A., Howell, E. A., Becker, E., Hoover, A. L., … Bailey, H. (2017). WhaleWatch: A dynamic management tool for predicting blue whale density in the California Current. Journal of Applied Ecology, 54(5), 1415–1428. https://doi.org/10.1111/1365‐2664.12820
For Humpback_whale_winter_spring and Fin_whale_winter_spring:
U.S. Department of the Navy. (2019). U.S. Navy Marine Species Density Database Phase III for the Northwest Training and Testing Study Area. NAVFAC Pacific Technical Report. Naval Facilities Engineering Command Pacific, Pearl Harbor, HI. 262 pp.
Description: Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are Generalized Additive Models (GAMs) and Boosted Regression Trees (BRTs), but comparative studies have rarely been conducted; most rely on presence-only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals km-2) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness-of-fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991-2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.
Service Item Id: 3ae57892c8bc4c268565cbf878cf0fb3
Copyright Text: Becker, E.A., J.V. Carretta, K.A. Forney, J. Barlow, S. Brodie, R. Hoopes, M.G. Jacox, S.M. Maxwell, J.V. Redfern, N.B. Sisson, H. Welch, E.L. Hazen. 2020. Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees. Ecology and Evolution, 10, 5759-5784.
For Blue_whale_winter_spring:
Hazen, E. L., Palacios, D. M., Forney, K. A., Howell, E. A., Becker, E., Hoover, A. L., … Bailey, H. (2017). WhaleWatch: A dynamic management tool for predicting blue whale density in the California Current. Journal of Applied Ecology, 54(5), 1415–1428. https://doi.org/10.1111/1365‐2664.12820
For Humpback_whale_winter_spring and Fin_whale_winter_spring:
U.S. Department of the Navy. (2019). U.S. Navy Marine Species Density Database Phase III for the Northwest Training and Testing Study Area. NAVFAC Pacific Technical Report. Naval Facilities Engineering Command Pacific, Pearl Harbor, HI. 262 pp.
Description: Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are Generalized Additive Models (GAMs) and Boosted Regression Trees (BRTs), but comparative studies have rarely been conducted; most rely on presence-only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals km-2) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness-of-fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991-2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.
Service Item Id: 3ae57892c8bc4c268565cbf878cf0fb3
Copyright Text: Becker, E.A., J.V. Carretta, K.A. Forney, J. Barlow, S. Brodie, R. Hoopes, M.G. Jacox, S.M. Maxwell, J.V. Redfern, N.B. Sisson, H. Welch, E.L. Hazen. 2020. Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees. Ecology and Evolution, 10, 5759-5784.
For Blue_whale_winter_spring:
Hazen, E. L., Palacios, D. M., Forney, K. A., Howell, E. A., Becker, E., Hoover, A. L., … Bailey, H. (2017). WhaleWatch: A dynamic management tool for predicting blue whale density in the California Current. Journal of Applied Ecology, 54(5), 1415–1428. https://doi.org/10.1111/1365‐2664.12820
For Humpback_whale_winter_spring and Fin_whale_winter_spring:
U.S. Department of the Navy. (2019). U.S. Navy Marine Species Density Database Phase III for the Northwest Training and Testing Study Area. NAVFAC Pacific Technical Report. Naval Facilities Engineering Command Pacific, Pearl Harbor, HI. 262 pp.
Description: Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are Generalized Additive Models (GAMs) and Boosted Regression Trees (BRTs), but comparative studies have rarely been conducted; most rely on presence-only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals km-2) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness-of-fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991-2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.
Service Item Id: 3ae57892c8bc4c268565cbf878cf0fb3
Copyright Text: Becker, E.A., J.V. Carretta, K.A. Forney, J. Barlow, S. Brodie, R. Hoopes, M.G. Jacox, S.M. Maxwell, J.V. Redfern, N.B. Sisson, H. Welch, E.L. Hazen. 2020. Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees. Ecology and Evolution, 10, 5759-5784.
For Blue_whale_winter_spring:
Hazen, E. L., Palacios, D. M., Forney, K. A., Howell, E. A., Becker, E., Hoover, A. L., … Bailey, H. (2017). WhaleWatch: A dynamic management tool for predicting blue whale density in the California Current. Journal of Applied Ecology, 54(5), 1415–1428. https://doi.org/10.1111/1365‐2664.12820
For Humpback_whale_winter_spring and Fin_whale_winter_spring:
U.S. Department of the Navy. (2019). U.S. Navy Marine Species Density Database Phase III for the Northwest Training and Testing Study Area. NAVFAC Pacific Technical Report. Naval Facilities Engineering Command Pacific, Pearl Harbor, HI. 262 pp.
Description: Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are Generalized Additive Models (GAMs) and Boosted Regression Trees (BRTs), but comparative studies have rarely been conducted; most rely on presence-only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals km-2) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness-of-fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991-2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.
Service Item Id: 3ae57892c8bc4c268565cbf878cf0fb3
Copyright Text: Becker, E.A., J.V. Carretta, K.A. Forney, J. Barlow, S. Brodie, R. Hoopes, M.G. Jacox, S.M. Maxwell, J.V. Redfern, N.B. Sisson, H. Welch, E.L. Hazen. 2020. Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees. Ecology and Evolution, 10, 5759-5784.
For Blue_whale_winter_spring:
Hazen, E. L., Palacios, D. M., Forney, K. A., Howell, E. A., Becker, E., Hoover, A. L., … Bailey, H. (2017). WhaleWatch: A dynamic management tool for predicting blue whale density in the California Current. Journal of Applied Ecology, 54(5), 1415–1428. https://doi.org/10.1111/1365‐2664.12820
For Humpback_whale_winter_spring and Fin_whale_winter_spring:
U.S. Department of the Navy. (2019). U.S. Navy Marine Species Density Database Phase III for the Northwest Training and Testing Study Area. NAVFAC Pacific Technical Report. Naval Facilities Engineering Command Pacific, Pearl Harbor, HI. 262 pp.
Description: Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are Generalized Additive Models (GAMs) and Boosted Regression Trees (BRTs), but comparative studies have rarely been conducted; most rely on presence-only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals km-2) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness-of-fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991-2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.
Service Item Id: 3ae57892c8bc4c268565cbf878cf0fb3
Copyright Text: Becker, E.A., J.V. Carretta, K.A. Forney, J. Barlow, S. Brodie, R. Hoopes, M.G. Jacox, S.M. Maxwell, J.V. Redfern, N.B. Sisson, H. Welch, E.L. Hazen. 2020. Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees. Ecology and Evolution, 10, 5759-5784.
For Blue_whale_winter_spring:
Hazen, E. L., Palacios, D. M., Forney, K. A., Howell, E. A., Becker, E., Hoover, A. L., … Bailey, H. (2017). WhaleWatch: A dynamic management tool for predicting blue whale density in the California Current. Journal of Applied Ecology, 54(5), 1415–1428. https://doi.org/10.1111/1365‐2664.12820
For Humpback_whale_winter_spring and Fin_whale_winter_spring:
U.S. Department of the Navy. (2019). U.S. Navy Marine Species Density Database Phase III for the Northwest Training and Testing Study Area. NAVFAC Pacific Technical Report. Naval Facilities Engineering Command Pacific, Pearl Harbor, HI. 262 pp.
Description: Species distribution models (SDMs) are important management tools for highly mobile marine species because they provide spatially and temporally explicit information on animal distribution. Two prevalent modeling frameworks used to develop SDMs for marine species are Generalized Additive Models (GAMs) and Boosted Regression Trees (BRTs), but comparative studies have rarely been conducted; most rely on presence-only data; and few have explored how features such as species distribution characteristics affect model performance. Since the majority of marine species BRTs have been used to predict habitat suitability, we first compared BRTs to GAMs that used presence/absence as the response variable. We then compared results from these habitat suitability models to GAMs that predict species density (animals km-2) because density models built with a subset of the data used here have previously received extensive validation. We compared both the explanatory power (i.e., model goodness-of-fit) and predictive power (i.e., performance on a novel dataset) of the GAMs and BRTs for a taxonomically diverse suite of cetacean species using a robust set of systematic survey data (1991-2014) within the California Current Ecosystem. Both BRTs and GAMs were successful at describing overall distribution patterns throughout the study area for the majority of species considered, but when predicting on novel data, the density GAMs exhibited substantially greater predictive power than both the presence/absence GAMs and BRTs, likely due to both the different response variables and fitting algorithms. Our results provide an improved understanding of some of the strengths and limitations of models developed using these two methods. These results can be used by modelers developing SDMs and resource managers tasked with the spatial management of marine species to determine the best modeling technique for their question of interest.
Service Item Id: 3ae57892c8bc4c268565cbf878cf0fb3
Copyright Text: Becker, E.A., J.V. Carretta, K.A. Forney, J. Barlow, S. Brodie, R. Hoopes, M.G. Jacox, S.M. Maxwell, J.V. Redfern, N.B. Sisson, H. Welch, E.L. Hazen. 2020. Performance evaluation of cetacean species distribution models developed using generalized additive models and boosted regression trees. Ecology and Evolution, 10, 5759-5784.
For Blue_whale_winter_spring:
Hazen, E. L., Palacios, D. M., Forney, K. A., Howell, E. A., Becker, E., Hoover, A. L., … Bailey, H. (2017). WhaleWatch: A dynamic management tool for predicting blue whale density in the California Current. Journal of Applied Ecology, 54(5), 1415–1428. https://doi.org/10.1111/1365‐2664.12820
For Humpback_whale_winter_spring and Fin_whale_winter_spring:
U.S. Department of the Navy. (2019). U.S. Navy Marine Species Density Database Phase III for the Northwest Training and Testing Study Area. NAVFAC Pacific Technical Report. Naval Facilities Engineering Command Pacific, Pearl Harbor, HI. 262 pp.