Modeling landslide susceptibility using LogitBoost alternating decision trees and forest by penalizing attributes with the bagging ensemble

doi:10.1016/j.scitotenv.2020.137231

	Modeling landslide susceptibility using LogitBoost alternating decision trees and forest by penalizing attributes with the bagging ensemble
	Hong, Haoyuan 1,4,5,6; Liu, Junzhi 4,5,6; Zhu, A-Xing 2,3,4,5,6,7
刊名	SCIENCE OF THE TOTAL ENVIRONMENT
	2020-05-20
卷号	718 页码:15
关键词	Landslide LogitBoost alternating decision trees Forest by penalizing attributes Bagging Integration model
ISSN号	0048-9697
DOI	10.1016/j.scitotenv.2020.137231
通讯作者	Hong, Haoyuan(171301013@stu.njnu.edu.cn) ; Liu, Junzhi(liujunzhi@njnu.edu.cn)
英文摘要	The major target of this study is to design two novel hybrid integration artificial intelligent models, which are denoted as LADT-Bagging and FPA-Bagging, for modeling landslide susceptibility in the Youfanggou district (China). First of all, we prepared a geospatial database in the study area, including 79 landslide points that were divided into a training and validating dataset and 14 landslide conditioning factors. Second, the Support Vector Machines classifier (SVMC) approach was adapted to analyze the predictive capability of the landslide predisposing factors in each method. Then, a multicollinearity analysis using TOL and VIF parameters and Pearson's correlation coefficient methods were applied to verify the multicollinearity and correlation between these factors. Third, the LADT-Bagging and FPA-Bagging models were built by the integration of the LogitBoost alternating decision trees (LADT) with the Bagging ensemble and Forest by Penalizing Attributes (FPA) with the Bagging ensemble, respectively. Besides, heuristic tests were also applied to identify the appropriate values of each model's parameters in order to obtain the best programmer. Finally, for the training dataset, the results reveal that the LADT-Bagging model acquire the largest AUC value (0.980), smallest standard error (SE) (0.0134), narrowest 95% confidence interval (Cl) (0.920-0.999), highest accuracy value (AV) (91.03%), highest specificity (94.44%), highest sensitivity (88.10%), highest F-measure (0.9115), lowest MAE (0.2016), lowest RMSE (0.2653), and highest Kappa (0.8205). About the result of validating dataset, it reveal that the LADT-Bagging model acquire the largest AUC value (0.781), the smallest SE (0.0539), the narrowest 95% CI (0.673-0.867), highest AV (71.19%), highest specificity (74.29%), highest sensitivity (69.77%), highest F-measure (0.7195), lowest MAE (0.3509), lowest RMSE (0.4335), and highest Kappa (0.4359). The results indicate that the LADT-Bagging model outperforms the FPA-Bagging, LADT and FPA models. Furthermore, the results of a Wilcoxon signed-rank test demonstrate that LADT-Bagging is significantly statistically different from other models. Therefore, in this study, the proposed new models are useful tools for land use planners or governments in high landslide risk areas. (C) 2020 Elsevier B.V. All rights reserved.
资助项目	National Natural Science Foundation of China[41871300] ; University of WisconsinMadison ; Postgraduate Research & Practice Innovation Program of Jiangsu Province[KYCX19_0785] ; China Scholarship Council[201906860029]
WOS关键词	SUPPORT VECTOR MACHINE ; RAINFALL-INDUCED LANDSLIDES ; FUZZY INFERENCE SYSTEM ; LOGISTIC-REGRESSION ; SPATIAL PREDICTION ; NEURAL-NETWORKS ; FREQUENCY RATIO ; RIVER-BASIN ; AREA NORTH ; COUNTY
WOS研究方向	Environmental Sciences & Ecology
语种	英语
出版者	ELSEVIER
WOS记录号	WOS:000526029000088
资助机构	National Natural Science Foundation of China ; University of WisconsinMadison ; Postgraduate Research & Practice Innovation Program of Jiangsu Province ; China Scholarship Council
内容类型	期刊论文
源URL	[http://ir.igsnrr.ac.cn/handle/311030/134042]
专题	中国科学院地理科学与资源研究所
通讯作者	Hong, Haoyuan; Liu, Junzhi
作者单位	1.Univ Vienna, Dept Geog & Reg Res, A-1010 Vienna, Austria 2.Southern Univ Sci & Technol, Ctr Social Sci, Guangzhou 518055, Peoples R China 3.Univ Wisconsin, Dept Geog, Madison, WI 53706 USA 4.Nanjing Normal Univ, Minist Educ, Key Lab Virtual Geog Environm, Nanjing 210023, Peoples R China 5.State Key Lab Cultivat Base Geog Environm Evolut, Nanjing 210023, Peoples R China 6.Jiangsu Ctr Collaborat Innovat Geog Informat Reso, Nanjing 210023, Jiangsu, Peoples R China 7.Chinese Acad Sci, Inst Geog Sci & Nat Resources Res, State Key Lab Resources & Environm Informat Syst, Beijing 100101, Peoples R China
推荐引用方式 GB/T 7714	Hong, Haoyuan,Liu, Junzhi,Zhu, A-Xing. Modeling landslide susceptibility using LogitBoost alternating decision trees and forest by penalizing attributes with the bagging ensemble[J]. SCIENCE OF THE TOTAL ENVIRONMENT,2020,718:15.
APA	Hong, Haoyuan,Liu, Junzhi,&Zhu, A-Xing.(2020).Modeling landslide susceptibility using LogitBoost alternating decision trees and forest by penalizing attributes with the bagging ensemble.SCIENCE OF THE TOTAL ENVIRONMENT,718,15.
MLA	Hong, Haoyuan,et al."Modeling landslide susceptibility using LogitBoost alternating decision trees and forest by penalizing attributes with the bagging ensemble".SCIENCE OF THE TOTAL ENVIRONMENT 718(2020):15.