Spatial prediction of landslides using a hybrid machine learning approach based on Random Subspace and Classification and Regression Trees

被引:210
作者
Binh Thai Pham [1 ,2 ]
Prakash, Indra [3 ]
Dieu Tien Bui [1 ,2 ]
机构
[1] Ton Duc Thang Univ, Geog Informat Sci Res Grp, Ho Chi Minh City, Vietnam
[2] Ton Duc Thang Univ, Fac Environm & Labour Safety, Ho Chi Minh City, Vietnam
[3] Govt Gujarati, Bhaskarcharya Inst Space Applicat & Geoinformat B, Dept Sci & Technol, Gandhinagar, India
关键词
Landslide susceptibility map; Machine learning; Emsembles; Random Subspace; Classification and Regression Trees; ARTIFICIAL NEURAL-NETWORKS; SUPPORT VECTOR MACHINES; RIVER FAULT ZONE; LOGISTIC-REGRESSION; SUSCEPTIBILITY ASSESSMENT; AREA; GIS; ENSEMBLES; INTEGRATION; TECTONICS;
D O I
10.1016/j.geomorph.2017.12.008
中图分类号
P9 [自然地理学];
学科分类号
0705 ; 070501 ;
摘要
A hybrid machine learning approach of Random Subspace (RSS) and Classification And Regression Trees (CART) is proposed to develop a model named RSSCART for spatial prediction of landslides. This model is a combination of the RSS method which is known as an efficient ensemble technique and the CART which is a state of the art classifier. The Luc Yen district of Yen Bai province, a prominent landslide prone area of Viet Nam, was selected for the model development. Performance of the RSSCART model was evaluated through the Receiver Operating Characteristic (ROC) curve, statistical analysis methods, and the Chi Square test. Results were compared with other benchmark landslide models namely Support Vector Machines (SVM), single CART, Nave Bayes Trees (NBT), and Logistic Regression (LR). In the development of model, ten important landslide affecting factors related with geomorphology, geology and geo-environment were considered namely slope angles, elevation, slope aspect, curvature, lithology, distance to faults, distance to rivers, distance to roads, and rainfall. Performance of the RSSCART model (AUC = 0.841) is the best compared with other popular landslide models namely SVM (0.835), single CART (0.822), NBT (0.821), and LR (0.723). These results indicate that performance of the RSSCART is a promising method for spatial landslide prediction. (C) 2017 Elsevier B.V. All rights reserved.
引用
收藏
页码:256 / 270
页数:15
相关论文
共 50 条
[31]   Spatiotemporal Prediction of Rainfall-induced Landslides Using Machine Learning Techniques [J].
Xiong, Jun ;
Pei, Te ;
Qiu, Tong .
GEOSHANGHAI INTERNATIONAL CONFERENCE 2024, VOL 8, 2024, 1337
[32]   An evolutionary approach for spatial prediction of landslide susceptibility using LiDAR and symbolic classification with genetic programming [J].
Gorsevski, Pece V. .
NATURAL HAZARDS, 2021, 108 (02) :2283-2307
[33]   Political Security Threat Prediction Framework Using Hybrid Lexicon-Based Approach and Machine Learning Technique [J].
Razali, Noor Afiza Mat ;
Malizan, Nur Atiqah ;
Hasbullah, Nor Asiakin ;
Wook, Muslihah ;
Zainuddin, Norulzahrah Mohd ;
Ishak, Khairul Khalil ;
Ramli, Suzaimah ;
Sukardi, Sazali .
IEEE ACCESS, 2023, 11 :17151-17164
[34]   A machine learning-based classification approach for phase diagram prediction [J].
Deffrennes, Guillaume ;
Terayama, Kei ;
Abe, Taichi ;
Tamura, Ryo .
MATERIALS & DESIGN, 2022, 215
[35]   Hybrid machine learning approach for landslide prediction, Uttarakhand, India [J].
Kainthura, Poonam ;
Sharma, Neelam .
SCIENTIFIC REPORTS, 2022, 12 (01)
[36]   Is machine learning a necessity? A regression-based approach for stock return prediction [J].
Cheng, Tingting ;
Jiang, Shan ;
Zhao, Albert Bo ;
Zhao, Junyi .
JOURNAL OF EMPIRICAL FINANCE, 2025, 81
[37]   Hardness prediction in the upsetting process of Al%ZrO2--an approach to machine learning using regression and classification models [J].
Ch, Harikrishna ;
Nagaraju, C. H. ;
Battina, N. Malleswararao ;
Kummitha, Obula Reddy .
TRANSACTIONS OF THE CANADIAN SOCIETY FOR MECHANICAL ENGINEERING, 2024, 48 (01) :39-52
[38]   A regression-based machine learning approach for the prediction of lung function decline [J].
Poulou, Angeliki ;
Poulos, Marios ;
Panas, Maximilianos .
2022 12TH INTERNATIONAL CONFERENCE ON DEPENDABLE SYSTEMS, SERVICES AND TECHNOLOGIES (DESSERT), 2022,
[39]   A New Hybrid Machine Learning Model for Short-Term Climate Prediction by Performing Classification Prediction and Regression Prediction Simultaneously [J].
Deqian Li ;
Shujuan Hu ;
Jinyuan Guo ;
Kai Wang ;
Chenbin Gao ;
Siyi Wang ;
Wenping He .
Journal of Meteorological Research, 2022, 36 :853-865
[40]   A New Hybrid Machine Learning Model for Short-Term Climate Prediction by Performing Classification Prediction and Regression Prediction Simultaneously [J].
Li, Deqian ;
Hu, Shujuan ;
Guo, Jinyuan ;
Wang, Kai ;
Gao, Chenbin ;
Wang, Siyi ;
He, Wenping .
JOURNAL OF METEOROLOGICAL RESEARCH, 2022, 36 (06) :853-865