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.

Response of glacier area variation to climate change in the Kaidu-Kongque river basin,Southern Tianshan Mountains during the last 20 years

Glaciers are crucial water resources for arid inland rivers in Northwest China.In recent decades,glaciers are largely experiencing shrinkage under the climate-warming scenario,thereby exerting tremendous influences on regional water resources.The primary role of understudying watershed scale glacier changes under changing climatic conditions is to ensure sustainable utilization of regional water resources,to prevent and mitigate glacier-related disasters.This study maps the current(2020)distribution of glacier boundaries across the Kaidu-Kongque river basin,south slope of Tianshan Mountains,and monitors the spatial evolution of glaciers over five time periods from 2000-2020 through thresholded band ratios approach,using 25 Landsat images at 30 m resolution.In addition,this study attempts to understand the role of climate characteristics for variable response of glacier area.The results show that the total area of glaciers was 398.21 km^(2)in 2020.The glaciers retreated by about 1.17 km^(2)/a(0.26%/a)from 2000 to 2020.The glaciers were reducing at a significantly rapid rate between 2000 and 2005,a slow rate from 2005 to 2015,and an accelerated rate during 2015-2020.The meteorological data shows slight increasing trends of mean annual temperature(0.02℃/a)and annual precipitation(2.07 mm/a).The correlation analysis demonstrates that the role of temperature presents more significant correlation with glacier recession than precipitation.There is a temporal hysteresis in the response of glacier change to climate change.Increasing trend of temperature in summer proves to be the driving force behind the Kaidu-Kongque basin glacier recession during the recent 20 years.

基于激光点云技术的山区工程测绘信息提取方法

激光点云技术是一种利用激光扫描系统快速获取大量空间数据点的高效技术,已广泛应用于地形测绘、城市规划、林业管理等领域.通过发射激光束并测量其反射回来的光的时间,该技术能生成代表物体表面的精细三维坐标点云.在复杂的山区地形,传统测绘方法由于地形限制和成本问题面临诸多挑战,而激光点云技术因其高效率和高精度的特点,成为解决这一问题的理想选择.

内蒙古大青山山前第四纪冲洪积扇填图实践与思考

第四纪地质调查和填图对解决当前人类生存发展面临的生态环境问题具有重要意义,但“填什么,如何填”等相关问题尚处于探索示范阶段。基于在内蒙古大青山山前地区开展的特殊地质地貌区填图工作,查明了大青山山前冲洪积扇的分布特征、期次及影响因素,总结了以冲洪积扇为代表的第四系覆盖区的调查与填图方法。首先,应针对地质地貌的特殊性,初步梳理区域内主要的第四纪地质与环境问题,选取针对性的沉积相模式进行沉积相划分;其次,综合前人资料成果和遥感解译结果编制设计地质图,依靠露头剖面、槽型钻揭露开展野外调查和验证,划分基本填图单元;然后,利用光释光、^(14)C等测年技术,确定填图单元时代,查明区内冲洪积扇发育的时间和期次;最后,选取“时代+成因+沉积相”结合不同岩性花纹的组合表达方式,增强工作区内典型剖面和钻孔的显示度,丰富图面内容和形式。

边远山区小面积大比例尺地形图施测技术探讨

在工程测量的应用方面,经常会遇到很多特殊任务。比如各种观测站选址测绘,往往选在边远山区,虽然面积很小,但难度很大。本文以抚松兴隆火山观测站、安图白河火山观测站站址1:500比例尺地形图的施测为例,探讨了边远山区小面积1:500比例尺地形图施测技术问题。

山区公路沿线地震滑坡易发性区划研究

基于地理信息系统(GIS)技术,建立逻辑回归评价模型,对汶川县和芦山县公路周边8km范围的地震滑坡开展易发性区划研究。在研究过程中,首先,从地震诱发滑坡灾害的触发机理出发,参考现场工程地质勘察资料及现有的研究成果,选取包括高程、坡度、坡位、坡向、曲率、微地貌、岩性、距断层距离、距水系距离、归一化植被指数(NDVI)、地震峰值加速度(PGA)、距离道路距离、年平均降雨量在内的13个地震诱发滑坡的影响因子;然后,以汶川县地理空间数据库为基础,通过10组样本在R软件中的训练,建立逻辑回归评价模型;最后,应用上述建立的模型,在ARCGIS平台下将汶川县公路沿线地震滑坡的易发性划分为极低、低、中、高、极高5个级别。为了进一步检验所建立评价模型的稳定性,将上述模型仿真到芦山县公路沿线,形成芦山县公路沿线地震滑坡易发性区划图。通过2个研究区域的ROC曲线,可以得到AUC值分别为0.912和0.783。研究结果表明:预测结果与实际地震滑坡分布吻合度较高,建立的评价模型稳定性较好,可以推广用于地形、地质环境相似山区公路沿线地震滑坡易发性区划评价。