GIS-based logistic regression method for landslide susceptibility mapping in regional scale *
GIS-based logistic regression method for landslide susceptibility mapping in regional scale *
复制标题
DOI：
10.1631/jzus.2006.a2007
复制
发表时间：
2006-12
期刊：
影响因子：
--
通讯作者：
Zhu Lei;Huang Jingfeng
中科院分区：
文献类型：
--
作者：
Zhu Lei;Huang Jingfeng
滑坡易感性图是描绘未来边坡破坏易感性空间分布的研究领域之一。本文对以往滑坡敏感性图的制作方法进行了综述，并将其分为三大类。逻辑线性回归方法通过交叉表方法进一步阐述，交叉表方法用于分析分类或二元响应变量与来自样本的一个或多个连续或分类或二元解释变量之间的关系。它是一个客观的分配系数作为权重的各种因素考虑，而专家意见的启发式方法有很大的差异。与确定性方法不同，它非常适用于区域尺度。在这项研究中，双重逻辑回归应用于研究区。首先对整个研究区域进行分析。Logistic回归方程表明，海拔、道路、河流和居民点距离是该地区滑坡发生的主要因素。第一张滑坡易发性图的预测精度为80%。沿着及居民区几乎全部处于滑坡高易发区。一些非滑坡区被错误地划分为高、中滑坡易发区。为了改善这一现状，在滑坡高易发区利用滑坡单元和非滑坡单元进行了二次Logistic回归分析。在第二次逻辑回归分析中，只有工程和地质条件在这些地区是重要的，并进入新的逻辑回归方程，表明只有工程和地质条件不稳定的地区在大规模工程活动中容易发生滑坡。考虑到这两个逻辑回归的结果产生一个新的滑坡易感性图。双Logistic回归分析提高了非滑坡预测精度。在Logistic回归参数计算中，利用滑坡密度将名义变量转化为数值变量，避免了虚拟变量过多的问题。
Landslide susceptibility map is one of the study fields portraying the spatial distribution of future slope failure susceptibility. This paper deals with past methods for producing landslide susceptibility map and divides these methods into 3 types. The logistic linear regression approach is further elaborated on by crosstabs methods, which is used to analyze the relationship between the categorical or binary response variable and one or more continuous or categorical or binary explanatory variables derived from samples. It is an objective assignment of coefficients serving as weights of various factors under considerations while expert opinions make great difference in heuristic approaches. Different from deterministic approach, it is very applicable to regional scale. In this study, double logistic regression is applied in the study area. The entire study area is first analyzed. The logistic regression equation showed that elevation, proximity to road, river and residential area are main factors triggering landslide occurrence in this area. The prediction accuracy of the first landslide susceptibility map was showed to be 80%. Along the road and residential area, almost all areas are in high landslide susceptibility zone. Some non-landslide areas are incorrectly divided into high and medium landslide susceptibility zone. In order to improve the status, a second logistic regression was done in high landslide susceptibility zone using landslide cells and non-landslide sample cells in this area. In the second logistic regression analysis, only engineering and geological conditions are important in these areas and are entered in the new logistic regression equation indicating that only areas with unstable engineering and geological conditions are prone to landslide during large scale engineering activity. Taking these two logistic regression results into account yields a new landslide susceptibility map. Double logistic regression analysis improved the non-landslide prediction accuracy. During calculation of parameters for logistic regression, landslide density is used to transform nominal variable to numeric variable and this avoids the creation of an excessively high number of dummy variables.