Machine learning is currently one of the research hotspots in the field of landslide prediction.To clarify and evaluate the differences in characteristics and prediction effects of different machine learning models,Co...Machine learning is currently one of the research hotspots in the field of landslide prediction.To clarify and evaluate the differences in characteristics and prediction effects of different machine learning models,Conghua District,which is the most prone to landslide disasters in Guangzhou,was selected for landslide susceptibility evaluation.The evaluation factors were selected by using correlation analysis and variance expansion factor method.Applying four machine learning methods namely Logistic Regression(LR),Random Forest(RF),Support Vector Machines(SVM),and Extreme Gradient Boosting(XGB),landslide models were constructed.Comparative analysis and evaluation of the model were conducted through statistical indices and receiver operating characteristic(ROC)curves.The results showed that LR,RF,SVM,and XGB models have good predictive performance for landslide susceptibility,with the area under curve(AUC)values of 0.752,0.965,0.996,and 0.998,respectively.XGB model had the highest predictive ability,followed by RF model,SVM model,and LR model.The frequency ratio(FR)accuracy of LR,RF,SVM,and XGB models was 0.775,0.842,0.759,and 0.822,respectively.RF and XGB models were superior to LR and SVM models,indicating that the integrated algorithm has better predictive ability than a single classification algorithm in regional landslide classification problems.展开更多
This study investigated water samples collected from the surface water and groundwater in Wuhan City,Hubei Province,China in different stages of the outbreak of the coronavirus disease 2019(hereinafter referred to as ...This study investigated water samples collected from the surface water and groundwater in Wuhan City,Hubei Province,China in different stages of the outbreak of the coronavirus disease 2019(hereinafter referred to as COVID-19)in the city,aiming to determine the distribution characteristics of antiviral drugs in the city’s waters.The results are as follows.The main hydrochemical type of surface water and groundwater in Wuhan was Ca-HCO3.The major chemical components in the groundwater had higher concentrations and spatial variability than those in the surface water.Two antiviral drugs and two glucocorticoids were detected in the surface water,groundwater,and sewage during the COVID-19 outbreak.Among them,chloroquine phosphate and cortisone had higher detection rates of 32.26%and 25.80%,respectively in all samples.The concentrations of residual drugs in East Lake were higher than those in other waters.The main drug detected in the waters in the later stage of the COVID-19 outbreak in Wuhan was chloroquine phosphate,whose detection rates in the surface water and the groundwater were 53.85%and 28.57%,respectively.Moreover,the detection rate and concentration of chloroquine phosphate were higher in East Lake than in Huangjia Lake.The groundwater containing chloroquine phosphate was mainly distributed along the river areas where the groundwater was highly vulnerable.The residual drugs in the surface water and the groundwater had lower concentrations in the late stage of the COVID-19 outbreak than in the middle of the outbreak,and they have not yet caused any negative impacts on the ecological environment.展开更多
基金supported by the projects of the China Geological Survey(DD20221729,DD20190291)Zhuhai Urban Geological Survey(including informatization)(MZCD–2201–008).
文摘Machine learning is currently one of the research hotspots in the field of landslide prediction.To clarify and evaluate the differences in characteristics and prediction effects of different machine learning models,Conghua District,which is the most prone to landslide disasters in Guangzhou,was selected for landslide susceptibility evaluation.The evaluation factors were selected by using correlation analysis and variance expansion factor method.Applying four machine learning methods namely Logistic Regression(LR),Random Forest(RF),Support Vector Machines(SVM),and Extreme Gradient Boosting(XGB),landslide models were constructed.Comparative analysis and evaluation of the model were conducted through statistical indices and receiver operating characteristic(ROC)curves.The results showed that LR,RF,SVM,and XGB models have good predictive performance for landslide susceptibility,with the area under curve(AUC)values of 0.752,0.965,0.996,and 0.998,respectively.XGB model had the highest predictive ability,followed by RF model,SVM model,and LR model.The frequency ratio(FR)accuracy of LR,RF,SVM,and XGB models was 0.775,0.842,0.759,and 0.822,respectively.RF and XGB models were superior to LR and SVM models,indicating that the integrated algorithm has better predictive ability than a single classification algorithm in regional landslide classification problems.
基金This research was jointly by the China Geological Survey Project Multi-Factor Urban Geological Survey of Wuhan(DD20190282)Survey and Evaluation of Riverside Urban Geological Safety in Wuhan(DD20221734).
文摘This study investigated water samples collected from the surface water and groundwater in Wuhan City,Hubei Province,China in different stages of the outbreak of the coronavirus disease 2019(hereinafter referred to as COVID-19)in the city,aiming to determine the distribution characteristics of antiviral drugs in the city’s waters.The results are as follows.The main hydrochemical type of surface water and groundwater in Wuhan was Ca-HCO3.The major chemical components in the groundwater had higher concentrations and spatial variability than those in the surface water.Two antiviral drugs and two glucocorticoids were detected in the surface water,groundwater,and sewage during the COVID-19 outbreak.Among them,chloroquine phosphate and cortisone had higher detection rates of 32.26%and 25.80%,respectively in all samples.The concentrations of residual drugs in East Lake were higher than those in other waters.The main drug detected in the waters in the later stage of the COVID-19 outbreak in Wuhan was chloroquine phosphate,whose detection rates in the surface water and the groundwater were 53.85%and 28.57%,respectively.Moreover,the detection rate and concentration of chloroquine phosphate were higher in East Lake than in Huangjia Lake.The groundwater containing chloroquine phosphate was mainly distributed along the river areas where the groundwater was highly vulnerable.The residual drugs in the surface water and the groundwater had lower concentrations in the late stage of the COVID-19 outbreak than in the middle of the outbreak,and they have not yet caused any negative impacts on the ecological environment.
