逻辑回归和人工神经网络模型在滑坡灾害空间预测中的应用

Application of logistic regression and artificial neural networks in spatial assessment of landslide hazards

摘要: 以三峡坝区到巴东段为研究区,选择坡度、坡向、软弱夹层、水系影响范围和土地利用状况等9项评价指标,分别采用逻辑回归和人工神经网络(ANN)模型,在ArcGIS平台上进行滑坡灾害危险性预测。此外,应用受试者工作特征曲线(receiver operating characteristic curve,ROC曲线)分析方法对两种模型的预测结果进行对比,分析结果表明滑坡危险性预测区划图和实际的滑坡发育情况基本吻合,逻辑回归模型和ANN模型的ROC曲线下面积AUC值分别为0.806和0.799,两种模型的预测结果可以相互验证,且逻辑回归模型的预测精度相对较高。

Abstract: The main purpose of this study is to analyze and compare the results of spatial assessment of landslide hazards by means of logistic regression analysis,back-propagation artificial neural network(ANN) through the use of geographic information system(GIS) techniques.A region from the Three Gorges Dam to the Badong Town,which suffered from deformation for many years,was selected as the application site of this study.Firstly,nine evaluation factors were selected,including topographic slope,topograp...