Description: <DIV STYLE="text-align:Left;"><DIV><DIV><P><SPAN>Species distribution modelling using a random forest (RF) machine learning approach was used to predict the probability of occurrence and biomass of sponges, sea pens, large and small gorgonians and Vazella pourtalesi in the Maritimes Region. A suite of 66 environmental predictor variables from different data sources were used. Models utilized catch records from the DFO multispecies trawl and scallop stock assessment surveys and in situ benthic imagery observations. Most presence-absence models had good predictive capacity with cross-validated Area Under the Receiver Operating Characteristic Curve (AUC) values ranging from 0.760 to 0.949. These models were used in a Canadian Science Advisory Secretariat (CSAS) process to delineate significant areas of cold-water corals and sponges in the Maritimes Region.</SPAN></P><P><SPAN /></P></DIV></DIV></DIV>
Service Item Id: c91be5e730844fc1b0e82d684b134952
Copyright Text: Fisheries and Oceans Canada, Bedford Institute of Oceanography, P.O. Box 1006, Dartmouth, NS, Canada B2Y 4A2
Description: <DIV STYLE="text-align:Left;"><DIV><DIV><P><SPAN>Species distribution modelling using a random forest (RF) machine learning approach was used to predict the probability of occurrence and biomass of sponges, sea pens, large and small gorgonians and Vazella pourtalesi in the Maritimes Region. A suite of 66 environmental predictor variables from different data sources were used. Models utilized catch records from the DFO multispecies trawl and scallop stock assessment surveys and in situ benthic imagery observations. Most presence-absence models had good predictive capacity with cross-validated Area Under the Receiver Operating Characteristic Curve (AUC) values ranging from 0.760 to 0.949. These models were used in a Canadian Science Advisory Secretariat (CSAS) process to delineate significant areas of cold-water corals and sponges in the Maritimes Region</SPAN><SPAN>.</SPAN></P></DIV></DIV></DIV>
Copyright Text: Fisheries and Oceans Canada, Bedford Institute of Oceanography, P.O. Box 1006, Dartmouth, NS, Canada B2Y 4A2
Description: <DIV STYLE="text-align:Left;"><DIV><DIV><P><SPAN>Species distribution modelling using a random forest (RF) machine learning approach was used to predict the probability of occurrence and biomass of sponges, sea pens, large and small gorgonians and Vazella pourtalesi in the Maritimes Region. A suite of 66 environmental predictor variables from different data sources were used. Models utilized catch records from the DFO multispecies trawl and scallop stock assessment surveys and in situ benthic imagery observations. Most presence-absence models had good predictive capacity with cross-validated Area Under the Receiver Operating Characteristic Curve (AUC) values ranging from 0.760 to 0.949. These models were used in a Canadian Science Advisory Secretariat (CSAS) process to delineate significant areas of cold-water corals and sponges in the Maritimes Region.</SPAN></P><P><SPAN /></P></DIV></DIV></DIV>
Service Item Id: c91be5e730844fc1b0e82d684b134952
Copyright Text: Fisheries and Oceans Canada, Bedford Institute of Oceanography, P.O. Box 1006, Dartmouth, NS, Canada B2Y 4A2
Description: <DIV STYLE="text-align:Left;"><P><SPAN>Species distribution modelling using a random forest (RF) machine learning approach was used to predict the probability of occurrence and biomass of sponges, sea pens, large and small gorgonians and Vazella pourtalesi in the Maritimes Region. A suite of 66 environmental predictor variables from different data sources were used. Models utilized catch records from the DFO multispecies trawl and scallop stock assessment surveys and in situ benthic imagery observations. Most presence-absence models had good predictive capacity with cross-validated Area Under the Receiver Operating Characteristic Curve (AUC) values ranging from 0.760 to 0.949. These models were used in a Canadian Science Advisory Secretariat (CSAS) process to delineate significant areas of cold-water corals and sponges in the Maritimes Region.</SPAN></P><P><SPAN /></P></DIV>
Service Item Id: c91be5e730844fc1b0e82d684b134952
Copyright Text: Fisheries and Oceans Canada, Bedford Institute of Oceanography, P.O. Box 1006, Dartmouth, NS, Canada B2Y 4A2
Name: Éponges des Maritimes Zone extrapolée Modèle 1
Display Field:
Type: Raster Layer
Geometry Type: null
Description: <DIV STYLE="text-align:Left;"><DIV><DIV><P><SPAN>The spatial extent of the Maritimes Region reaches far beyond the Scotian Shelf and Slope, down to ~5100 m depth. Our data observations are limited to depths above ~2900 m. Extrapolation of model predictions to areas outside of the range of data observations where the environmental conditions could be different than those used to train the model, may produce unreliable predictions in those areas. For each random forest model, we highlight those areas within the study extent where model predictions are considered extrapolated.</SPAN></P><P><SPAN /></P><P><SPAN /></P><P><SPAN /></P></DIV></DIV></DIV>
Service Item Id: c91be5e730844fc1b0e82d684b134952
Copyright Text: Fisheries and Oceans Canada, Bedford Institute of Oceanography, P.O. Box 1006, Dartmouth, NS, Canada B2Y 4A2
Name: Modèle de probabilité de présence des éponges des Maritimes 1
Display Field:
Type: Raster Layer
Geometry Type: null
Description: <DIV STYLE="text-align:Left;"><DIV><DIV><P><SPAN>Species distribution modelling using a random forest (RF) machine learning approach was used to predict the probability of occurrence and biomass of sponges, sea pens, large and small gorgonians and Vazella pourtalesi in the Maritimes Region. A suite of 66 environmental predictor variables from different data sources were used. Species occurrence was predicted using all presence and absence data (unbalanced model), and a balanced species prevalence model (i.e. an equal number of presences and absences). Also, for such taxonomic groups whose distribution was felt was not fully sampled by the multispecies stock assessment surveys, or when the number of trawl records for a group was insufficient for producing accurate predictions of distribution, additional random forest models were run using trawl survey data augmented with data from other sources: 1) in situ benthic imagery observations from scientific surveys, 2) DFO scallop stock assessment surveys, and 3) commercial records from the Fisheries Observer Program (FOP). The model unbalanced presence and absence catch data from DFO multispecies trawl surveys and in addition with other sources was chosen for the sea pens, small and large gorgonian corals and Vazella pourtalesi as the better prediction surface and the model produced from the balanced data was chosen for sponges.</SPAN></P><P><SPAN>Three measures of accuracy were used to assess model performance: sensitivity, specificity, and AUC, or Area Under the Receiver Operating Curve. The accuracy measures for the random forest model using an</SPAN><SPAN /><SPAN>equal number of presence and absences sponge data (balanced species prevalence model)and scallop stock assessment surveys were AUC= 0.760, sensitivity= 0.691and specificity=0.702; indicating fair model performance.</SPAN></P></DIV></DIV></DIV>
Service Item Id: c91be5e730844fc1b0e82d684b134952
Copyright Text: Fisheries and Oceans Canada, Bedford Institute of Oceanography, P.O. Box 1006, Dartmouth, NS, Canada B2Y 4A2
Name: Petits gorgoniens des Maritimes Zone extrapolée Modèle 3
Display Field:
Type: Raster Layer
Geometry Type: null
Description: <DIV STYLE="text-align:Left;"><DIV><DIV><P><SPAN>The spatial extent of the Maritimes Region reaches far beyond the Scotian Shelf and Slope, down to ~5100 m depth. Our data observations are limited to depths above ~2900 m. Extrapolation of model predictions to areas outside of the range of data observations where the environmental conditions could be different than those used to train the model, may produce unreliable predictions in those areas. For each random forest model, we highlight those areas within the study extent where model predictions are considered extrapolated.</SPAN></P></DIV></DIV></DIV>
Service Item Id: c91be5e730844fc1b0e82d684b134952
Copyright Text: Fisheries and Oceans Canada, Bedford Institute of Oceanography, P.O. Box 1006, Dartmouth, NS, Canada B2Y 4A2
Name: Modèle de probabilité de présence des petits gorgoniens des Maritimes 3
Display Field:
Type: Raster Layer
Geometry Type: null
Description: <DIV STYLE="text-align:Left;"><DIV><DIV><P><SPAN>Species distribution modelling using a random forest (RF) machine learning approach was used to predict the probability of occurrence and biomass of sponges, sea pens, large and small gorgonians and Vazella pourtalesi in the Maritimes Region. A suite of 66 environmental predictor variables from different data sources were used. Species occurrence was predicted using all presence and absence data (unbalanced model), and a balanced species prevalence model (i.e. an equal number of presences and absences). Also, for such taxonomic groups whose distribution was felt was not fully sampled by the multispecies stock assessment surveys, or when the number of trawl records for a group was insufficient for producing accurate predictions of distribution, additional random forest models were run using trawl survey data augmented with data from other sources: 1) in situ benthic imagery observations from scientific surveys, 2) DFO scallop stock assessment surveys, and 3) commercial records from the Fisheries Observer Program (FOP). The model unbalanced presence and absence catch data from DFO multispecies trawl surveys and in addition with other sources was chosen for the sea pens, small and large gorgonian corals and Vazella pourtalesi as the better prediction surface and the model produced from the balanced data was chosen for sponges.</SPAN></P><P STYLE="margin:0 0 0 0;"><SPAN>Three measures of accuracy were used to assess model performance: sensitivity, specificity, and AUC, or Area Under the Receiver Operating Curve. The accuracy measures for the random forest model using all small gorgonian presence and absence data, in situ benthic imagery observations and a threshold equal to species prevalence (0.06)were AUC= 0.949, sensitivity= 0.876and specificity=0.916; indicating excellent model performance.</SPAN></P><P><SPAN /></P><P><SPAN /></P></DIV></DIV></DIV>
Service Item Id: c91be5e730844fc1b0e82d684b134952
Copyright Text: Fisheries and Oceans Canada, Bedford Institute of Oceanography, P.O. Box 1006, Dartmouth, NS, Canada B2Y 4A2
Name: Pennatulacea des Maritimes Zone extrapolée Modèle 3
Display Field:
Type: Raster Layer
Geometry Type: null
Description: <DIV STYLE="text-align:Left;"><DIV><DIV><P><SPAN>The spatial extent of the Maritimes Region reaches far beyond the Scotian Shelf and Slope, down to ~5100 m depth. Our data observations are limited to depths above ~2900 m. Extrapolation of model predictions to areas outside of the range of data observations where the environmental conditions could be different than those used to train the model, may produce unreliable predictions in those areas. For each random forest model, we highlight those areas within the study extent where model predictions are considered extrapolated.</SPAN></P></DIV></DIV></DIV>
Service Item Id: c91be5e730844fc1b0e82d684b134952
Copyright Text: Fisheries and Oceans Canada, Bedford Institute of Oceanography, P.O. Box 1006, Dartmouth, NS, Canada B2Y 4A2
Name: Modèle de probabilité de présence de la Pennatulacea Maritimes 3
Display Field:
Type: Raster Layer
Geometry Type: null
Description: <DIV STYLE="text-align:Left;"><DIV><DIV><P><SPAN>Species distribution modelling using a random forest (RF) machine learning approach was used to predict the probability of occurrence and biomass of sponges, sea pens, large and small gorgonians and Vazella pourtalesi in the Maritimes Region. A suite of 66 environmental predictor variables from different data sources were used. Species occurrence was predicted using all presence and absence data (unbalanced model), and a balanced species prevalence model (i.e. an equal number of presences and absences). Also, for such taxonomic groups whose distribution was felt was not fully sampled by the multispecies stock assessment surveys, or when the number of trawl records for a group was insufficient for producing accurate predictions of distribution, additional random forest models were run using trawl survey data augmented with data from other sources: 1) in situ benthic imagery observations from scientific surveys, 2) DFO scallop stock assessment surveys, and 3) commercial records from the Fisheries Observer Program (FOP). The model unbalanced presence and absence catch data from DFO multispecies trawl surveys and in addition with other sources was chosen for the sea pens, small and large gorgonian corals and Vazella pourtalesi as the better prediction surface and the model produced from the balanced data was chosen for sponges.</SPAN></P><P STYLE="margin:0 0 7 0;"><SPAN>Three measures of accuracy were used to assess model performance: sensitivity, specificity, and AUC, or Area Under the Receiver Operating Curve. The accuracy measures for the random forest model using all sea pen presence and absence data, in situ benthic imagery observations and a threshold equal to species prevalence (0.11) were AUC= 0.901, sensitivity= 0.813 and specificity=0.819; indicating excellent model performance.</SPAN></P></DIV></DIV></DIV>
Copyright Text: Fisheries and Oceans Canada, Bedford Institute of Oceanography, P.O. Box 1006, Dartmouth, NS, Canada B2Y 4A2
Name: Grands gorgones maritimes Zone extrapolée Modèle 3
Display Field:
Type: Raster Layer
Geometry Type: null
Description: <DIV STYLE="text-align:Left;"><DIV><DIV><P><SPAN>The spatial extent of the Maritimes Region reaches far beyond the Scotian Shelf and Slope, down to ~5100 m depth. Our data observations are limited to depths above ~2900 m. Extrapolation of model predictions to areas outside of the range of data observations </SPAN><SPAN>where the environmental conditions could be different than those used to train the model, may produce unreliable predictions in those areas</SPAN><SPAN>.</SPAN><SPAN> For each random forest model</SPAN><SPAN>, we highlight those areas within the study extent where model predictions are considered extrapolated.</SPAN></P><P><SPAN /></P></DIV></DIV></DIV>
Service Item Id: c91be5e730844fc1b0e82d684b134952
Copyright Text: Fisheries and Oceans Canada, Bedford Institute of Oceanography, P.O. Box 1006, Dartmouth, NS, Canada B2Y 4A2
Name: Modèle de probabilité de présence des grands gorgoniens des Maritimes 3
Display Field:
Type: Raster Layer
Geometry Type: null
Description: <DIV STYLE="text-align:Left;"><DIV><DIV><P><SPAN>Species distribution modelling using a random forest (RF) machine learning approach was used to predict the probability of occurrence and biomass of sponges, sea pens, large and small gorgonians and Vazella pourtalesi in the Maritimes Region. A suite of 66 environmental predictor variables from different data sources were used. Species occurrence was predicted using all presence and absence data (unbalanced model), and a balanced species prevalence model (i.e. an equal number of presences and absences). Also, for such taxonomic groups whose distribution was felt was not fully sampled by the multispecies stock assessment surveys, or when the number of trawl records for a group was insufficient for producing accurate predictions of distribution, additional random forest models were run using trawl survey data augmented with data from other sources: 1) in situ benthic imagery observations from scientific surveys, 2) DFO scallop stock assessment surveys, and 3) commercial records from the Fisheries Observer Program (FOP). The model unbalanced presence and absence catch data from DFO multispecies trawl surveys and in addition with other sources was chosen for the sea pens, small and large gorgonian corals and Vazella pourtalesi as the better prediction surface and the model produced from the balanced data was chosen for sponges.</SPAN></P><P STYLE="margin:0 0 7 0;"><SPAN>Three measures of accuracy were used to assess model performance: sensitivity, specificity, and AUC, or Area Under the Receiver Operating Curve. The accuracy measures for the random forest model using all large gorgonian presence and absence data, in situ benthic imagery observations and a threshold equal to species prevalence (0.09) were AUC= 0.928, sensitivity= 0.833 and specificity=0.892; indicating excellent model performance.</SPAN></P></DIV></DIV></DIV>
Service Item Id: c91be5e730844fc1b0e82d684b134952
Copyright Text: Fisheries and Oceans Canada, Bedford Institute of Oceanography, P.O. Box 1006, Dartmouth, NS, Canada B2Y 4A2