Evaluation of geological hazard susceptibility based on certainty factors coupling logistic regression

doi:10.13474/j.cnki.11-2246.2022.0335

Abstract

Abstract: In order to study the susceptibility of geological disasters in the Northwest region, where natural disasters frequently occur, we consider ten factors, such as elevation and slope aspect, and use the coefficient of certainty (CF) model and the coupled logistic regression (CF-LR) model to evaluate the susceptibility of geological hazards in Chenggu county. The results show that the disaster ratios of the CF model and the CF-LR model are increasing, and the density of high-extremely high disaster points are 4.75/km²and 5.97/km² respectively. In addition, in the test data set, the area under curve (AUC) of the receiver operating characteristic (ROC) of the two models are 0.812 and 0.835 respectively. In the validation dataset, the AUC of the ROC of the two models are 0.862 and 0.891 respectively. Both models can effectively evaluate the susceptibility of geological disasters in the region, and the CF-LR model has higher evaluation accuracy.

Key words: hazards, assessment of susceptibility, logistic regression model, correlation coefficient, coefficient factors model

CLC Number:

P208

WANG Xuan, SHI Yun, CHEN Hao. Evaluation of geological hazard susceptibility based on certainty factors coupling logistic regression[J]. Bulletin of Surveying and Mapping, 2022, 0(11): 112-117.

References

[1] 国土资源部. 国土资源部印发《全国地质灾害防治"十三五"规划》[J]. 中国应急管理,2016(12):39-44.
[2] 夏辉, 殷坤龙, 梁鑫, 等. 基于SVM-ANN模型的滑坡易发性评价:以三峡库区巫山县为例[J]. 中国地质灾害与防治学报, 2018, 29(5):13-19.
[3] 谢明娟, 蒲瑞, 韩信, 等. 基于多模型的滑坡易发性评价[J]. 测绘与空间地理信息, 2019, 42(10):83-85.
[4] 黄发明. 基于3S和人工智能的滑坡位移预测与易发性评价[D]. 武汉:中国地质大学, 2017.
[5] 李远远, 梅红波, 任晓杰, 等. 基于确定性系数和支持向量机的地质灾害易发性评价[J]. 地球信息科学学报, 2018, 20(12):1699-1709.
[6] 葛大庆, 戴可人, 郭兆成, 等. 重大地质灾害隐患早期识别中综合遥感应用的思考与建议[J]. 武汉大学学报(信息科学版), 2019, 44(7):949-956.
[7] CHEN Wei, XIE Xiaoshen, WANG Jiale, et al. A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility[J]. Catena,2017, 151:147-160.
[8] TAALAB K, CHENG Tao, ZHANG Yang. Mapping landslide susceptibility and types using random forest[J]. Big Earth Data, 2018, 2(2):159-178.
[9] CHEN Wei, POURGHASEMI H R, NAGHIBI S A. A comparative study of landslide susceptibility maps produced using support vector machine with different kernel functions and entropy data mining models in China[J]. Bulletin of Engineering Geology and the Environment, 2018, 77(2):647-664.
[10] CHEN Tao, ZHU Li, NIU Ruiqing, et al. Mapping landslide susceptibility at the Three Gorges Reservoir, China, using gradient boosting decision tree, random forest and information value models[J]. Journal of Mountain Science, 2020, 17(3):670-685.
[11] DOU J, YUNUS A P, TIEN BUI D, et al. Assessment of advanced random forest and decision tree algorithms for modeling rainfall-induced landslide susceptibility in the Izu-Oshima Volcanic Island, Japan[J]. Science of the Total Environment, 2019, 662:332-346.
[12] 徐胜华, 刘纪平, 王想红, 等. 熵指数融入支持向量机的滑坡灾害易发性评价方法:以陕西省为例[J]. 武汉大学学报(信息科学版), 2020, 45(8):1214-1222.
[13] 林荣福, 刘纪平, 徐胜华, 等. 随机森林赋权信息量的滑坡易发性评价方法[J]. 测绘科学, 2020, 45(12):131-138.
[14] 陈飞, 蔡超, 李小双, 等. 基于信息量与神经网络模型的滑坡易发性评价[J]. 岩石力学与工程学报, 2020, 39(S1):2859-2870.
[15] 樊芷吟, 苟晓峰, 秦明月, 等. 基于信息量模型与Logistic回归模型耦合的地质灾害易发性评价[J]. 工程地质学报, 2018, 26(2):340-347.
[16] 李益敏, 李驭豪, 赵志芳. 基于确定性系数模型的泸水市泥石流易发性评价[J]. 水土保持研究, 2019, 26(4):336-342.
[17] BUDIMIR M E A, ATKINSON P M, LEWIS H G. A systematic review of landslide probability mapping using logistic regression[J]. Landslides, 2015, 12(3):419-436.