Limits...
Using stochastic gradient boosting to infer stopover habitat selection and distribution of Hooded Cranes Grus monacha during spring migration in Lindian, Northeast China.

Cai T, Huettmann F, Guo Y - PLoS ONE (2014)

Bottom Line: Our field work in 2013 using systematic ground-truthing confirmed that this prediction was accurate.Based on this study, we suggest that Lindian plays an important role for migratory birds and that cultivation practices should be adjusted locally.Furthermore, public education programs to promote the concept of the harmonious coexistence of humans and cranes can help successfully protect this species in the long term and eventually lead to its delisting by the IUCN.

View Article: PubMed Central - PubMed

Affiliation: College of Nature Conservation, Beijing Forestry University, Beijing, China.

ABSTRACT
The Hooded Crane (Grus monacha) is a globally vulnerable species, and habitat loss is the primary cause of its decline. To date, little is known regarding the specific habitat needs, and stopover habitat selection in particular, of the Hooded Crane. In this study we used stochastic gradient boosting (TreeNet) to develop three specific habitat selection models for roosting, daytime resting, and feeding site selection. In addition, we used a geographic information system (GIS) combined with TreeNet to develop a species distribution model. We also generated a digital map of the relative occurrence index (ROI) of this species at daytime resting sites in the study area. Our study indicated that the water depth, distance to village, coverage of deciduous leaves, open water area, and density of plants were the major predictors of roosting site selection. For daytime resting site selection, the distance to wetland, distance to farmland, and distance to road were the primary predictors. For feeding site selection, the distance to road, quantity of food, plant coverage, distance to village, plant density, distance to wetland, and distance to river were contributing factors, and the distance to road and quantity of food were the most important predictors. The predictive map showed that there were two consistent multi-year daytime resting sites in our study area. Our field work in 2013 using systematic ground-truthing confirmed that this prediction was accurate. Based on this study, we suggest that Lindian plays an important role for migratory birds and that cultivation practices should be adjusted locally. Furthermore, public education programs to promote the concept of the harmonious coexistence of humans and cranes can help successfully protect this species in the long term and eventually lead to its delisting by the IUCN.

Show MeSH
A prediction model map of Hooded Crane daytime resting sites in the study area.
© Copyright Policy
Related In: Results  -  Collection

License
getmorefigures.php?uid=PMC3935961&req=5

pone-0089913-g007: A prediction model map of Hooded Crane daytime resting sites in the study area.

Mentions: The optimized TreeNet model contained 310 statistical trees and predicted the Hooded Crane occurrence at a daytime resting site (Figure 7). This model also obtained a very high AUC value (learning/testing = 0.99/0.91), indicating a high prediction accuracy for the data and as well as the software. Based on the prediction map, we found that the potential daytime resting sites are distributed within the grasslands. Approximately 45% of the study area was predicted to have an ROI <20%, and 39% of the study area was predicted to have an ROI >60% (Table 3). Cranes were predicted to occur most often (>80%) in the southwest (Zone 1), southeast (Zone 2), and northern (Zone 3) regions of the study area. The map appears somewhat banded because of the road effects, although this is to be interpreted in the context of biological habitat and can be smoothed out in subsequent model runs. Here we provide a robust proof of concept and suggest that the method may be applied to larger areas and other migration hotspots.


Using stochastic gradient boosting to infer stopover habitat selection and distribution of Hooded Cranes Grus monacha during spring migration in Lindian, Northeast China.

Cai T, Huettmann F, Guo Y - PLoS ONE (2014)

A prediction model map of Hooded Crane daytime resting sites in the study area.
© Copyright Policy
Related In: Results  -  Collection

License
Show All Figures
getmorefigures.php?uid=PMC3935961&req=5

pone-0089913-g007: A prediction model map of Hooded Crane daytime resting sites in the study area.
Mentions: The optimized TreeNet model contained 310 statistical trees and predicted the Hooded Crane occurrence at a daytime resting site (Figure 7). This model also obtained a very high AUC value (learning/testing = 0.99/0.91), indicating a high prediction accuracy for the data and as well as the software. Based on the prediction map, we found that the potential daytime resting sites are distributed within the grasslands. Approximately 45% of the study area was predicted to have an ROI <20%, and 39% of the study area was predicted to have an ROI >60% (Table 3). Cranes were predicted to occur most often (>80%) in the southwest (Zone 1), southeast (Zone 2), and northern (Zone 3) regions of the study area. The map appears somewhat banded because of the road effects, although this is to be interpreted in the context of biological habitat and can be smoothed out in subsequent model runs. Here we provide a robust proof of concept and suggest that the method may be applied to larger areas and other migration hotspots.

Bottom Line: Our field work in 2013 using systematic ground-truthing confirmed that this prediction was accurate.Based on this study, we suggest that Lindian plays an important role for migratory birds and that cultivation practices should be adjusted locally.Furthermore, public education programs to promote the concept of the harmonious coexistence of humans and cranes can help successfully protect this species in the long term and eventually lead to its delisting by the IUCN.

View Article: PubMed Central - PubMed

Affiliation: College of Nature Conservation, Beijing Forestry University, Beijing, China.

ABSTRACT
The Hooded Crane (Grus monacha) is a globally vulnerable species, and habitat loss is the primary cause of its decline. To date, little is known regarding the specific habitat needs, and stopover habitat selection in particular, of the Hooded Crane. In this study we used stochastic gradient boosting (TreeNet) to develop three specific habitat selection models for roosting, daytime resting, and feeding site selection. In addition, we used a geographic information system (GIS) combined with TreeNet to develop a species distribution model. We also generated a digital map of the relative occurrence index (ROI) of this species at daytime resting sites in the study area. Our study indicated that the water depth, distance to village, coverage of deciduous leaves, open water area, and density of plants were the major predictors of roosting site selection. For daytime resting site selection, the distance to wetland, distance to farmland, and distance to road were the primary predictors. For feeding site selection, the distance to road, quantity of food, plant coverage, distance to village, plant density, distance to wetland, and distance to river were contributing factors, and the distance to road and quantity of food were the most important predictors. The predictive map showed that there were two consistent multi-year daytime resting sites in our study area. Our field work in 2013 using systematic ground-truthing confirmed that this prediction was accurate. Based on this study, we suggest that Lindian plays an important role for migratory birds and that cultivation practices should be adjusted locally. Furthermore, public education programs to promote the concept of the harmonious coexistence of humans and cranes can help successfully protect this species in the long term and eventually lead to its delisting by the IUCN.

Show MeSH