As a primary sediment source,gully erosion leads to severe land degradation and poses a threat to food and ecological security.Therefore,identification of susceptible areas is critical to the prevention and control of...As a primary sediment source,gully erosion leads to severe land degradation and poses a threat to food and ecological security.Therefore,identification of susceptible areas is critical to the prevention and control of gully erosion.This study aimed to identify areas prone to gully erosion using four machine learning methods with derived topographic attributes.Eight topographic attributes(elevation,slope aspect,slope degree,catchment area,plan curvature,profile curvature,stream power index,and topo-graphic wetness index)were derived as feature variables controlling gully occurrence from digital elevation models with four different pixel sizes(5.0 m,12.5 m,20.0 m,and 30.0 m).A gully inventory map of a small agricultural catchment in Heilongjiang,China,was prepared through a combination of field surveys and satellite imagery.Each topographic attribute dataset was randomly divided into two portions of 70%and 30%for calibrating and validating four machine learning methods,namely random forest(RF),support vector machines(SVM),artificial neural network(ANN),and generalized linear models(GLM).Accuracy(ACC),area under the receiver operating characteristic curve(AUC),root mean square error(RMSE),and mean absolute error(MAE)were calculated to assess the performance of the four machine learning methods in predicting spatial distribution of gully erosion susceptibility(GES).The results suggested that the selected topographic attributes were capable of predicting GES in the study catchment area.A pixel size of 20.0 m was optimal for all four machine learning methods.The RF method described the spatial relationship between the feature variables and gully occurrence with the greatest accuracy,as it returned the highest values of ACC(0.917)and AUC(0.905)at a 20.0 m resolution.The RF was also the least sensitive to resolutions,followed by SVM(ACC=0.781-0.891,AUC=0.724-0.861)and ANN(ACC=0.744-0.808,AUC=0.649-0.847).GLM performed poorly in this study(ACC=0.693-0.757,AUC=0.608-0.703).Based on the spatial distribution of GES determined using the optimal method(RF+pixel size of 20.0 m),16%of the study area has very high level susceptibility classes,whereas areas with high,moderate,and low levels of susceptibility make up approximately 24%,30%,and 31%of the study area,respectively.Our results demonstrate that GES assessment with machine learning methods can successfuly identify areas prone to gully erosion,providing reference information for future soil conservation plans and land management.In addition,pixel size(resolution)is the key consideration when preparing suitable datasets of feature variables for GES assessment.展开更多
基金supported by the National Key R&D Program of China[Grant number 2021YFD1500700]the National Natural Science Foundation of China[Grant number 42007050]Scientific Research Foundation of Liaoning Province[Grant number LSNPT202002].
文摘As a primary sediment source,gully erosion leads to severe land degradation and poses a threat to food and ecological security.Therefore,identification of susceptible areas is critical to the prevention and control of gully erosion.This study aimed to identify areas prone to gully erosion using four machine learning methods with derived topographic attributes.Eight topographic attributes(elevation,slope aspect,slope degree,catchment area,plan curvature,profile curvature,stream power index,and topo-graphic wetness index)were derived as feature variables controlling gully occurrence from digital elevation models with four different pixel sizes(5.0 m,12.5 m,20.0 m,and 30.0 m).A gully inventory map of a small agricultural catchment in Heilongjiang,China,was prepared through a combination of field surveys and satellite imagery.Each topographic attribute dataset was randomly divided into two portions of 70%and 30%for calibrating and validating four machine learning methods,namely random forest(RF),support vector machines(SVM),artificial neural network(ANN),and generalized linear models(GLM).Accuracy(ACC),area under the receiver operating characteristic curve(AUC),root mean square error(RMSE),and mean absolute error(MAE)were calculated to assess the performance of the four machine learning methods in predicting spatial distribution of gully erosion susceptibility(GES).The results suggested that the selected topographic attributes were capable of predicting GES in the study catchment area.A pixel size of 20.0 m was optimal for all four machine learning methods.The RF method described the spatial relationship between the feature variables and gully occurrence with the greatest accuracy,as it returned the highest values of ACC(0.917)and AUC(0.905)at a 20.0 m resolution.The RF was also the least sensitive to resolutions,followed by SVM(ACC=0.781-0.891,AUC=0.724-0.861)and ANN(ACC=0.744-0.808,AUC=0.649-0.847).GLM performed poorly in this study(ACC=0.693-0.757,AUC=0.608-0.703).Based on the spatial distribution of GES determined using the optimal method(RF+pixel size of 20.0 m),16%of the study area has very high level susceptibility classes,whereas areas with high,moderate,and low levels of susceptibility make up approximately 24%,30%,and 31%of the study area,respectively.Our results demonstrate that GES assessment with machine learning methods can successfuly identify areas prone to gully erosion,providing reference information for future soil conservation plans and land management.In addition,pixel size(resolution)is the key consideration when preparing suitable datasets of feature variables for GES assessment.
