Landslide susceptibility assessment in Western Henan Province based on a comparison of conventional and ensemble machine learning

Landslide is a serious natural disaster next only to earthquake and flood,which will cause a great threat to people’s lives and property safety.The traditional research of landslide disaster based on experience-driven or statistical model and its assessment results are subjective,difficult to quantify,and no pertinence.As a new research method for landslide susceptibility assessment,machine learning can greatly improve the landslide susceptibility model’s accuracy by constructing statistical models.Taking Western Henan for example,the study selected 16 landslide influencing factors such as topography,geological environment,hydrological conditions,and human activities,and 11 landslide factors with the most significant influence on the landslide were selected by the recursive feature elimination(RFE)method.Five machine learning methods[Support Vector Machines(SVM),Logistic Regression(LR),Random Forest(RF),Extreme Gradient Boosting(XGBoost),and Linear Discriminant Analysis(LDA)]were used to construct the spatial distribution model of landslide susceptibility.The models were evaluated by the receiver operating characteristic curve and statistical index.After analysis and comparison,the XGBoost model(AUC 0.8759)performed the best and was suitable for dealing with regression problems.The model had a high adaptability to landslide data.According to the landslide susceptibility map of the five models,the overall distribution can be observed.The extremely high and high susceptibility areas are distributed in the Funiu Mountain range in the southwest,the Xiaoshan Mountain range in the west,and the Yellow River Basin in the north.These areas have large terrain fluctuations,complicated geological structural environments and frequent human engineering activities.The extremely high and highly prone areas were 12043.3 km^(2)and 3087.45 km^(2),accounting for 47.61%and 12.20%of the total area of the study area,respectively.Our study reflects the distribution of landslide susceptibility in western Henan Province,which provides a scientific basis for regional disaster warning,prediction,and resource protection.The study has important practical significance for subsequent landslide disaster management.

Assessment of water level threshold for groundwater restoration and over-exploitation remediation the Beijing-Tianjin-Hebei Plain

The Beijing-Tianjin-Hebei Plain(BTHP)is the political,economic and cultural center of China,where groundwater is the main source of water supply to support social and economic development.Continuous overdraft of the resources has caused a persistent decline of groundwater level and formed a huge cone of depression at a regional scale.This paper addresses current groundwater situation over the BTHP area.The paper also delineates the groundwater flow field,using groundwater level data,in order to provide an effective method for the restoration of groundwater level and associated water resources management.Based on the analysis of multiple factors,such as groundwater level,soil salinization,ground subsidence,groundwater recharge and storage,urban underground space security,formation of fractures,and seawater intrusion,the threshold for groundwater level restoration is defined,and some measures for groundwater over-exploitation management are accordingly proposed.The study shows that:(i)Since the 1980s to 2020,shallow groundwater level in the western part of the BTHP area has dropped by 25 m to 60m,while the cumulative decline of deep groundwater in the central and eastern regions is in the range of 40–80 m;(ii)The water table of the shallow groundwater within the depression zone over the Western Piedmont Plain should be controlled in the range of 15–30 m below ground level(mbgl),while the depth of groundwater level in large and medium-sized urban areas should be controlled within 20–30 mbgl.The groundwater level in the resource preservation area should be controlled within 10–15 mbgl,and the groundwater level in the area with identified soil salinization in the central and eastern plain should be controlled within 3–10 mbgl.However,for the deep groundwater in the central and eastern plainwater,the main focus of the resources management is to control the land subsidence.The water level in the severe land subsidence area should be controlled within 45–60 mbgl,and in the general subsidence area should be controlled within 30–45 mbgl;(iii)Based on the water level recovery threshold and proposed groundwater overdraft management program,if the balance of abstraction and recharge is reached in 2025,the shallow groundwater abstraction needs to be gradually reduced by about 2×10^(8) m^(3).Meanwhile,the ecological water replenishment of rivers through the South-to-North Water Transfer Project should be increased to 28.58×10^(8) m^(3)/a,and the deep groundwater abstraction needs to be gradually reduced by 2.24×10^(8) m^(3).To reach the target of shallow groundwater level in 2040,surface water replacement is recommended with a rate of 25.77×10^(8) m^(3)/a and the ecological water replenishment of rivers in the South-to-North Water Diversion Project should reach 33.51×10^(8) m^(3)/a.For deep groundwater recovery,it is recommended to replace the deep freshwater extraction with the utilization of shallow salt water by 2.82×10^(8) m^(3),in addition to the amount of 7.86×10^(8) m^(3) by water diversion.The results are of great significance to the remediation of groundwater over-exploitation,the regulation of water resources development and utilization,and ecological protection in Beijing-Tianjin-Hebei plain.