Landslide susceptibility mapping using random forest, boosted regression tree, classification and regression tree, and general linear models and comparison of their performance at Wadi Tayyah Basin, Asir Region, Saudi Arabia
Landslide susceptibility mapping using random forest, boosted regression tree, classification and regression tree, and general linear models and comparison of their performance at Wadi Tayyah Basin, Asir Region, Saudi Arabia
复制标题
DOI：
10.1007/s10346-015-0614-1
复制
发表时间：
2015
期刊：
影响因子：
6.7
通讯作者：
A. Youssef;H. Pourghasemi;Zohre Sadat Pourtaghi;Mohamed M. Al-Katheeri
中科院分区：
文献类型：
--
作者：
A. Youssef;H. Pourghasemi;Zohre Sadat Pourtaghi;Mohamed M. Al-Katheeri
本研究的目的是利用不同的数据挖掘模型生成滑坡易感性图。采用随机森林（RF）、增强回归树（BRT）、分类与回归树（CART）和一般线性（GLM）四种建模技术，对沙特阿拉伯阿西尔地区瓦迪塔耶盆地的滑坡易感性作图结果进行了比较。通过对不同数据类型的解释，包括高分辨率卫星图像、地形图、历史记录和广泛的实地调查，确定并绘制了滑坡位置。利用ArcGIS 10.2软件绘制了125个滑坡位置图，并将其分为两组；培训（70%）和验证（25%）。编制了11层滑坡调节因子，包括坡向、海拔、离断层距离、岩性、平面曲率、剖面曲率、降雨量、离溪流距离、离道路距离、坡度角和土地利用。利用上述32种模型（RF、BRT、CART和广义加性（GAM））计算了滑坡调节因子与滑坡盘存图之间的关系。将模型的结果与模型训练中未使用的滑坡位置进行了比较。使用受试者工作特征（ROC），包括曲线下面积（AUC）来评估模型的准确性。计算成功率（训练数据）和预测率（验证数据）曲线。结果表明，RF、BRT、CART和GLM模型的成功率AUC分别为0.783（78.3%）、0.958（95.8%）、0.816（81.6%）和0.821（82.1%）。RF、BRT、CART和GLM模型的预测率分别为0.812（81.2%）、0.856（85.6%）、0.862（86.2%）和0.769（76.9%）。随后，将滑坡易感性图划分为低、中、高、极高易感性4个等级。结果表明，RF、BRT、CART和GLM模型在滑坡敏感性制图中具有合理的精度。成果图将有助于今后总体规划的发展活动，例如选择新的城市地区和基础设施活动，以及环境保护。
The purpose of the current study is to produce landslide susceptibility maps using different data mining models. Four modeling techniques, namely random forest (RF), boosted regression tree (BRT), classification and regression tree (CART), and general linear (GLM) are used, and their results are compared for landslides susceptibility mapping at the Wadi Tayyah Basin, Asir Region, Saudi Arabia. Landslide locations were identified and mapped from the interpretation of different data types, including high-resolution satellite images, topographic maps, historical records, and extensive field surveys. In total, 125 landslide locations were mapped using ArcGIS 10.2, and the locations were divided into two groups; training (70 %) and validating (25 %), respectively. Eleven layers of landslide-conditioning factors were prepared, including slope aspect, altitude, distance from faults, lithology, plan curvature, profile curvature, rainfall, distance from streams, distance from roads, slope angle, and land use. The relationships between the landslide-conditioning factors and the landslide inventory map were calculated using the mentioned 32 models (RF, BRT, CART, and generalized additive (GAM)). The models’ results were compared with landslide locations, which were not used during the models’ training. The receiver operating characteristics (ROC), including the area under the curve (AUC), was used to assess the accuracy of the models. The success (training data) and prediction (validation data) rate curves were calculated. The results showed that the AUC for success rates are 0.783 (78.3 %), 0.958 (95.8 %), 0.816 (81.6 %), and 0.821 (82.1 %) for RF, BRT, CART, and GLM models, respectively. The prediction rates are 0.812 (81.2 %), 0.856 (85.6 %), 0.862 (86.2 %), and 0.769 (76.9 %) for RF, BRT, CART, and GLM models, respectively. Subsequently, landslide susceptibility maps were divided into four classes, including low, moderate, high, and very high susceptibility. The results revealed that the RF, BRT, CART, and GLM models produced reasonable accuracy in landslide susceptibility mapping. The outcome maps would be useful for general planned development activities in the future, such as choosing new urban areas and infrastructural activities, as well as for environmental protection.