A comparative study on the predictive ability of the decision tree, support vector machine and neuro-fuzzy models in landslide susceptibility mapping using GIS

被引:923
作者
Pradhan, Biswajeet [1 ]
机构
[1] Univ Putra Malaysia, Fac Engn, Dept Civil Engn, Geospatial Informat Sci Res Ctr GIS RC, Serdang 43400, Selangor Darul, Malaysia
关键词
Landslides; Decision tree (DT); Support vector machine (SVM); Adaptive neuro-fuzzy inference system (ANFIS); Malaysia; GIS; Remote sensing; HOA BINH PROVINCE; BLACK-SEA REGION; LOGISTIC-REGRESSION; SPATIAL PREDICTION; NETWORK MODEL; CONDITIONAL-PROBABILITY; FREQUENCY RATIO; HAZARD; LOGIC; VIETNAM;
D O I
10.1016/j.cageo.2012.08.023
中图分类号
TP39 [计算机的应用];
学科分类号
081203 ; 0835 ;
摘要
The purpose of the present study is to compare the prediction performances of three different approaches such as decision tree (DT), support vector machine (SVM) and adaptive neuro-fuzzy inference system (ANFIS) for landslide susceptibility mapping at Penang Hill area, Malaysia. The necessary input parameters for the landslide susceptibility assessments were obtained from various sources. At first, landslide locations were identified by aerial photographs and field surveys and a total of 113 landslide locations were constructed. The study area contains 340,608 pixels while total 8403 pixels include landslides. The landslide inventory was randomly partitioned into two subsets: (1) part 1 that contains 50% (4000 landslide grid cells) was used in the training phase of the models; (2) part 2 is a validation dataset 50% (4000 landslide grid cells) for validation of three models and to confirm its accuracy. The digitally processed images of input parameters were combined in GIS. Finally, landslide susceptibility maps were produced, and the performances were assessed and discussed. Total fifteen landslide susceptibility maps were produced using DT, SVM and ANFIS based models, and the resultant maps were validated using the landslide locations. Prediction performances of these maps were checked by receiver operating characteristics (ROC) by using both success rate curve and prediction rate curve. The validation results showed that, area under the ROC curve for the fifteen models produced using DT, SVM and ANFIS varied from 0.8204 to 0.9421 for success rate curve and 0.7580 to 0.8307 for prediction rate curves, respectively. Moreover, the prediction curves revealed that model 5 of DT has slightly higher prediction performance (83.07), whereas the success rate showed that model 5 of ANFIS has better prediction (94.21) capability among all models. The results of this study showed that landslide susceptibility mapping in the Penang Hill area using the three approaches (e.g., DT, SVM and ANFIS) is viable. As far as the performance of the models are concerned, the results appeared to be quite satisfactory, i.e., the zones determined on the map being zones of relative susceptibility. (c) 2012 Elsevier Ltd. All rights reserved.
引用
收藏
页码:350 / 365
页数:16
相关论文
共 50 条
[41]   GIS-Based Landslide Susceptibility Mapping Using Logistic Regression, Instability Index, and Support Vector Machine: Case Study of the Jingshan River, Taiwan [J].
Chan, Hsun-Chuan ;
Chen, Yu-Chin ;
Lee, Jung-Tai ;
Wen, Yu-Ting .
JOURNAL OF MARINE SCIENCE AND TECHNOLOGY-TAIWAN, 2021, 29 (03) :287-299
[42]   Forest Fire Susceptibility Assessment and Mapping Using Support Vector Regression and Adaptive Neuro-Fuzzy Inference System-Based Evolutionary Algorithms [J].
Mabdeh, Ali Nouh ;
Al-Fugara, A'kif ;
Khedher, Khaled Mohamed ;
Mabdeh, Muhammed ;
Al-Shabeeb, Abdel Rahman ;
Al-Adamat, Rida .
SUSTAINABILITY, 2022, 14 (15)
[43]   Forecasting and validation of landslide susceptibility using an integration of frequency ratio and neuro-fuzzy models: a case study of Seorak mountain area in Korea [J].
Moung-Jin Lee ;
Inhye Park ;
Saro Lee .
Environmental Earth Sciences, 2015, 74 :413-429
[44]   CONDITIONING FACTORS DETERMINATION FOR LANDSLIDE SUSCEPTIBILITY MAPPING USING SUPPORT VECTOR MACHINE LEARNING [J].
Kalantar, Bahareh ;
Ueda, Naonori ;
Lay, Usman Salihu ;
Al-Najjar, Husam Abdulrasool H. ;
Halin, Alfian Abdul .
2019 IEEE INTERNATIONAL GEOSCIENCE AND REMOTE SENSING SYMPOSIUM (IGARSS 2019), 2019, :9626-9629
[45]   Landslide susceptibility assessment by using a neuro-fuzzy model: a case study in the Rupestrian heritage rich area of Matera [J].
Sdao, F. ;
Lioi, D. S. ;
Pascale, S. ;
Caniani, D. ;
Mancini, I. M. .
NATURAL HAZARDS AND EARTH SYSTEM SCIENCES, 2013, 13 (02) :395-407
[46]   A comparative study of landslide susceptibility mapping using weight of evidence, logistic regression and support vector machine and evaluated by SBAS-InSAR monitoring: Zhouqu to Wudu segment in Bailong River Basin, China [J].
Xie, Zhengtuan ;
Chen, Guan ;
Meng, Xingmin ;
Zhang, Yi ;
Qiao, Liang ;
Tan, Long .
ENVIRONMENTAL EARTH SCIENCES, 2017, 76 (08)
[47]   GIS-based landslide susceptibility mapping using logistic regression, random forest and decision and regression tree models in Chattogram District, Bangladesh [J].
Chowdhury, Md Sharafat ;
Rahaman, Md Naimur ;
Sheikh, Md Sujon ;
Abu Sayeid, Md ;
Mahmud, Khandakar Hasan ;
Hafsa, Bibi .
HELIYON, 2024, 10 (01)
[48]   Application of Tree-Based Ensemble Models to Landslide Susceptibility Mapping: A Comparative Study [J].
Wei, Aihua ;
Yu, Kaining ;
Dai, Fenggang ;
Gu, Fuji ;
Zhang, Wanxi ;
Liu, Yu .
SUSTAINABILITY, 2022, 14 (10)
[49]   A comparative study based on AHP and fuzzy logic approaches for landslide susceptibility zoning using a GIS-based multi-criteria decision analysis [J].
Ksantini, Faten ;
Sdiri, Ali ;
Aydi, Abdelwaheb ;
Almeida-Naunay, Andres Felipe ;
Achour, Hammadi ;
Tarquis, Ana M. .
EURO-MEDITERRANEAN JOURNAL FOR ENVIRONMENTAL INTEGRATION, 2025, 10 (02) :649-668
[50]   Comparative Analysis of Neuro-Fuzzy and Support Vector Approaches for Flood Forecasting: Case Study of Godavari Basin, India [J].
Misra, Puneet ;
Shukla, Shobhit .
COMPUTING AND NETWORK SUSTAINABILITY, 2019, 75