A random forest model of karst ground collapse susceptibility based on factor and parameter coupling optimization. Issue 27 (13th December 2022)

• Record Type: Journal Article
• Authors: Wang, Guilin; Hao, Jinyu; Wen, Haijia; Cao, Chong
• Is Part Of: Geocarto international. Volume 37:Issue 27(2023)
• Page Start: 15548
• Page End: 15567
• Publication Date: 2022-12-13
• Subjects: karst ground collapse -- Bayesian optimization -- Selection of evaluation factors -- Random forest -- Susceptibility evaluation; Remote sensing -- Periodicals; Geographic information systems -- Periodicals; Geology -- Periodicals; Cartography -- Periodicals; 621.3678
• DOI: 10.1080/10106049.2022.2102216
• Languages: English
• ISSNs: 1010-6049

Abstract

Abstract: The purpose of this study is to develop a coupling model to improve the ability of random forest model to accurately predict karst collapse. Therefore, an inventory map consisting of 327 collapse points and 1962 non-collapse points was created. The database also contains 18 influencing factors, ranked with GeoDetector. 16 optimized factors were obtained. Bayesian algorithm was used to optimize the parameters of RF model. The optimized factors and RF model were used to create a collapse map, compared with the original map. After coupling and optimizing the factors and parameters, the accuracy of the RF model was 0.935; precision, 0.964, and AUC value, 0.977. Compared with the unoptimized model, the accuracy, precision and AUC value of the optimized RF model improved by 0.197, 0.146 and 0.134, respectively. The results show that the method of optimizing and coupling the factors and parameters contributes to improve the karst collapse susceptibility model.