| Citation: |
XIE Yang-Long, QI Xin, GAO Peng, WANG Ying-Hao. 2025. Comparative Analysis of Slope Geological Hazard Susceptibility Assessment Based on Multiple Evaluation Models: A Case Study of Wuhan, China. South China Geology, 41(1): 185-196. doi: 10.3969/j.issn.2097-0013.2025.01.015
|
Comparative Analysis of Slope Geological Hazard Susceptibility Assessment Based on Multiple Evaluation Models: A Case Study of Wuhan, China
-
Abstract
The susceptibility evaluation of geological disasters is an indispensable part of disaster prevention and mitigation. It is of great significance to select effective evaluation methods and models for the susceptibility evaluation of geological disasters. This paper takes the slope geological disasters (collapse and landslide) in Wuhan city as the research object, selects 9 evaluation factors such as slope, slope direction, elevation, engineering geological rock group and vegetation coverage, and uses the information method (IV), the determination coefficient method (CF) and the random forest model (RF) to evaluate the susceptibility of geological disasters, and then uses the receiver operating characteristic curve (ROC) to test the accuracy of the evaluation model and compare the evaluation results of the three models. The results show that: (1) The three models can correctly reflect the development characteristics of slope geological disasters in the study area. The high-prone areas and extremely high-prone areas are concentrated in the mountainous areas in the northern, central and western parts of the study area and the eroded accumulation hilly areas formed by river denudation and leveling. The low-prone areas account for the vast majority and are mainly distributed in the plain areas around the banks and lakes of the Yangtze River and most of the low-mountain plain areas. (2) The AUC area of the three models from high to low is IV > CF > RF. The zoning results obtained by the IV and CF models have high similarity, and the disaster point density of the extremely high-prone areas of the two models is higher than that of the RF model. (3) Slope, elevation, engineering geological rock group and slope structure type are the most important factors in the evaluation system, indicating that the development factors of slope geological disasters in the study area are mainly related to topography and lithology.
-
-
References
[1] 陈建国,钟连祥.2023.基于CF-AHP耦合模型的高速公路沿线崩塌地质灾害易发性评价——以蓉遵高速公路土城——旺隆段为例[J]. 中国地质灾害与防治学报,34(6):105-115. [2] 黄 敏.2023.基于FR的多种机器学习模型在地质灾害易发性评价中的对比分析[J]. 福建地质,42(3):236-243. doi: 10.3969/j.issn.1001-3970.2023.03.010 [3] 焦伟之,张 明,谢鑫鹏,李成文,刘 涛,庞海松.2022.基于GIS与加权信息量模型的城镇地质灾害易发性评价—以大新镇为例[J]. 安全与环境工程,29(4):119-128. [4] 连志鹏,厉一宁,刘 磊,王宁涛.2022.基于ArcGIS的湖北省远安县地质灾害风险定量评价[J]. 华南地质,38(4):680-688. doi: 10.3969/j.issn.2097-0013.2022.04.010 [5] 刘 坚,李树林,陈 涛.2018.基于优化随机森林模型的滑坡易发性评价[J]. 武汉大学学报(信息科学版),43(7):1085-1091. [6] 孟凡奇,高 峰,林 波,张京钊,徐京梁,牛 伟.2023.基于AHP和信息量模型的地质灾害易发性评价——以鲁东片区为例[J]. 灾害学,38(3):111-117. doi: 10.3969/j.issn.1000-811X.2023.03.018 [7] 彭建兵,徐能雄,张永双,夏开文,薛翊国,张 彬,杨国香,陈 剑,王飞永,臧明东,梅 钢,穆文平,王祚鹏,李 星,张 欣.2022.论地质安全研究的框架体系[J]. 工程地质学报,30(6):1798-1810. [8] 邵大江,叶 辉,王金亮,周京春,角媛梅,沙晋明.2023.基于机器学习均值化的地质灾害易发性评价[J]. 云南大学学报(自然科学版),45(3):653-665. doi: 10.7540/j.ynu.20220109 [9] 孙剑锋,马 超,胡金树,闫铁生,杲加俊,徐 辉.2023.基于灰色关联度与层次分析法耦合的地质灾害易发性评价—以浙江省云和县崇头镇为例[J]. 工程地质学报,31(2):538-551. [10] 王雪冬,张超彪,王 翠,朱永东,王海鹏.2022.基于Logistic回归与随机森林的和龙市地质灾害易发性评价[J]. 吉林大学学报(地球科学版),52(6):1957-1970. [11] 温 鑫,范宣梅,陈 兰,刘世康.2022.基于信息量模型的地质灾害易发性评价:以川东南古蔺县为例[J]. 地质科技通报,41(2):290-299. [12] 于喜坤,张紫昭,史光明,李崇博,刘毅业,朱建华,陈伟楠.2023.基于确定性系数与信息量耦合模型的新疆额敏县地质灾害易发性评价[J]. 工程地质学报,31(4):1333-1349. [13] 张 威,胡舫瑞,綦 巍,彭 琳,王咏林,陈 枫.2023.基于XGBoost和云模型的地质灾害易发性评价[J]. 中国地质灾害与防治学报,34(6):136-145. [14] 章 昱,王 磊,伏永朋,刘亚磊,黄 皓.2023.基于斜坡单元与信息量法的丹江口库区典型流域地质灾害易发性评价[J]. 华南地质,39(3):512-522. doi: 10.3969/j.issn.2097-0013.2023.03.010 [15] 赵晓燕,李永平,谈树成.2022.GIS支持下CF与信息量耦合模型的攀枝花市矿山地质灾害易发性评价[J]. 云南大学学报(自然科学版),44(4):754-764. [16] 翟文华,王小东,吴明堂,吴晓亮,李倩倩.2023.基于频率比模型和随机森林模型耦合的地质灾害易发性评价[J]. 自然灾害学报,32(6):74-82. [17] Jiang N, Li Y E, Han Z, Yang J M, Fu B J, Li J Y, Li C L. 2024. A side-sampling based Linformer model for landslide susceptibility assessment: a case study of the railways in China[J]. Geomatics, Natural Hazards and Risk, 15(1): 2354507. [18] Ksantini F, Sdiri A, Aydi A, Almeida-Naunay A F, Achour H, Tarquis A M. 2024. A comparative study based on AHP and fuzzy logic approaches for landslide susceptibility zoning using a GIS-based multi-criteria decision analysis[J]. Euro-Mediterranean Journal for Environmental Integration, 9(2): 1-20. [19] Li L P, Lan H X. 2024. Analytical ‘decisiveness’ as a robust measure of the absolute importance of landslide predisposing factors[J]. International Journal of Digital Earth, 17(1): 2356161. doi: 10.1080/17538947.2024.2356161 [20] Li R W, Tan S C, Zhang M F, Zhang S H, Wang H S, Zhu L. 2024. Geological Disaster Susceptibility Evaluation Using a Random Forest Empowerment Information Quantity Model[J]. Sustainability, 16(2): 765. doi: 10.3390/su16020765 [21] Lombardo L, Opitz T, Ardizzone F, Guzzetti F, Huser R. 2020. Space-time landslide predictive modelling[J]. Earth-Science Reviews, 209: 103318. doi: 10.1016/j.earscirev.2020.103318 [22] Nocentini N, Rosi A, Piciullo L, Liu Z Q, Segoni S, Fanti R. 2024. Regional-scale spatiotemporal landslide probability assessment through machine learning and potential applications for operational warning systems: a case study in Kvam (Norway)[J]. Landslides, 21(10): 1-19. [23] Pradhan B. 2013. A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS[J]. Computers & Geosciences, 51: 350-365. [24] Reichenbach P, Rossi M, Malamud B D, Mihir M, Guzzetti F. 2018. A review of statistically-based landslide susceptibility models[J]. Earth-Science Reviews, 180: 60-91. doi: 10.1016/j.earscirev.2018.03.001 [25] Sun K, Li Z Q, Wang S J, Hu R L. 2024. A support vector machine model of landslide susceptibility mapping based on hyperparameter optimization using the Bayesian algorithm: a case study of the highways in the southern Qinghai–Tibet Plateau[J]. Natural Hazards, 120(12): 11377-11398. doi: 10.1007/s11069-024-06665-3 [26] Wang Z P, Chen J P, Lian Z C, Li F, Pang L, Xin Y B. 2024. Influence of buffer distance on environmental geological hazard susceptibility assessment[J]. Environmental Science and Pollution Research, 31(6): 9582-9595. doi: 10.1007/s11356-023-31739-3 [27] Zhang S H, Tan S C, Wang H S, Shi Y Q, Ding D Y, Sun Y Q, Gao H X. 2024. To explore the optimal solution of different mapping units and classifiers and their application in the susceptibility evaluation of slope geological disasters[J]. Ecological Indicators, 163: 112073. doi: 10.1016/j.ecolind.2024.112073 -
Access History
Figures(7)
Tables(4)
Export File
Citation
XIE Yang-Long, QI Xin, GAO Peng, WANG Ying-Hao. 2025. Comparative Analysis of Slope Geological Hazard Susceptibility Assessment Based on Multiple Evaluation Models: A Case Study of Wuhan, China. South China Geology, 41(1): 185-196. doi: 10.3969/j.issn.2097-0013.2025.01.015
Format
Content
DownLoad:
-
Figure 1.
Overview map of elevation and geological hazard distribution in Wuhan city
-
Figure 2.
Evaluation flow chart
-
Figure 3.
Grading chart of evaluation factors in the study area
-
Figure 4.
Statistical chart of evaluation factor classification in the study area
-
Figure 5.
Output plot of model results
-
Figure 6.
Geological hazard susceptibility zoning map of the study area
-
Figure 7.
ROC plots for the three models