Landslide Susceptibility Mapping Using the Stacking Ensemble Machine Learning Method in Lushui, Southwest China
Source abstract
Abstract
Landslide susceptibility mapping is considered to be a prerequisite for landslide prevention and mitigation. However, delineating the spatial occurrence pattern of the landslide remains a challenge. This study investigates the potential application of the stacking ensemble learning technique for landslide susceptibility assessment. In particular, support vector machine (SVM), artificial neural network (ANN), logical regression (LR), and naive Bayes (NB) were selected as base learners for the stacking ensemble method. The resampling scheme and Pearson’s correlation analysis were jointly used to evaluate the importance level of these base learners. A total of 388 landslides and 12 conditioning factors in the Lushui area (Southwest China) were used as the dataset to develop landslide modeling. The landslides were randomly separated into two parts, with 70% used for model training and 30% used for model validation. The models’ performance was evaluated using the area under the receiver operating characteristic (ROC) curve (AUC) and statistical measures. The results showed that the stacking-based ensemble model achieved an improved predictive accuracy as compared to the single algorithms, while the SVM-ANN-NB-LR (SANL) model, the SVM-ANN-NB (SAN) model, and the ANN-NB-LR (ANL) models performed equally well, with AUC values of 0.931, 0.940, and 0.932, respectively, for validation stage. The correlation coefficient between the LR and SVM was the highest for all resampling rounds, with a value of 0.72 on average. This connotes that LR and SVM played an almost equal role when the ensemble of SANL was applied for landslide susceptibility analysis. Therefore, it is feasible to use the SAN model or the ANL model for the study area. The finding from this study suggests that the stacking ensemble machine learning method is promising for landslide susceptibility mapping in the Lushui area and is capable of targeting areas prone to landslides.
Source: crossref · Quality: baseline
Research context
OpenAlex topics: Landslides and related hazards · Geotechnical Engineering and Analysis · Flood Risk Assessment and Management
SciVX discovery tags are terminology-based. OpenAlex topics are source-provided classifications.
Affiliations
School of Earth Resources, China University of Geosciences, Wuhan 430074, China
ZCCE, College of Engineering, Swansea University, Bay Campus, Fabian Way, Swansea SA1 8EN, UK
References (86)
Show source-provided references
1. Large landslides associated with a diapiric fold in Canelles Reservoir (Spanish Pyrenees): Detailed geological–geomorphological mapping, trenching and electrical resistivity imaging10.1016/j.geomorph.2015.04.016 ↗
2. A comparative study of different machine learning methods for landslide susceptibility assessment: A case study of Uttarakhand area (India)10.1016/j.envsoft.2016.07.005 ↗
3. Susceptibility assessment of earthquake-induced landslides using Bayesian network: A case study in Beichuan, China10.1016/j.cageo.2011.09.011 ↗
4. Performance evaluation for four GIS-based models purposed to predict and map landslide susceptibility: A case study at a World Heritage site in Southwest China10.1016/j.catena.2019.104221 ↗
5. Dou, J., Yunus, A.P., Bui, D.T., Merghadi, A., Sahana, M., Zhu, Z., Chen, C.W., Han, Z., and Pham, B.T. (2019). Improved landslide assessment using support vector machine with bagging, boosting, and stacking ensemble machine learning framework in a mountainous watershed, Japan. Landslides.10.1007/s10346-019-01286-5 ↗
6. Predictive modelling of rainfall-induced landslide hazard in the Lesser Himalaya of Nepal based on weights-of-evidence10.1016/j.geomorph.2008.05.041 ↗
7. Landslide hazard evaluation: A review of current techniques and their application in a multi-scale study, Central Italy10.1016/S0169-555X(99)00078-1 ↗
8. Landslide prediction from machine learning10.1111/gto.12034 ↗
9. Evaluation of environmental parameters in logistic regression models for landslide susceptibility mapping10.1080/17538947.2011.586443 ↗
10. Landslide susceptibility analysis with logistic regression model based on FCM sampling strategy10.1016/j.cageo.2013.04.006 ↗
11. Fuzzy-based method for landslide hazard assessment in active seismic zone of Himalaya10.1007/s10346-006-0068-6 ↗
12. Integrating GIS Based Fuzzy Set Theory in Multicriteria Evaluation Methods for Landslide Susceptibility Mapping
13. Using maximum entropy modeling for landslide susceptibility mapping with multiple geoenvironmental data sets10.1007/s12665-014-3442-z ↗
14. Landslide susceptibility mapping at Vaz Watershed (Iran) using an artificial neural network model: A comparison between multilayer perceptron (MLP) and radial basic function (RBF) algorithms10.1007/s12517-012-0610-x ↗
15. Evaluation of prediction capability of the artificial neural networks for mapping landslide susceptibility in the Turbolo River catchment (northern Calabria, Italy)10.1016/j.catena.2013.08.006 ↗
16. Oh, H.-J., and Lee, S. (2017). Shallow Landslide Susceptibility Modeling Using the Data Mining Models Artificial Neural Network and Boosted Tree. Appl. Sci., 7.10.3390/app7101000 ↗
17. Landslide Susceptibility Assessment in Vietnam Using Support Vector Machines, Decision Tree, and Naïve Bayes Models
18. GIS-based support vector machine modeling of earthquake-triggered landslide susceptibility in the Jianjiang River watershed, China10.1016/j.geomorph.2011.12.040 ↗
19. Spatial prediction of landslide hazard at the Yihuang area (China) using two-class kernel logistic regression, alternating decision tree and support vector machines10.1016/j.catena.2015.05.019 ↗
20. Landslide susceptibility mapping based on Support Vector Machine: A case study on natural slopes of Hong Kong, China10.1016/j.geomorph.2008.02.011 ↗
21. Landslide susceptibility mapping using random forest, boosted regression tree, classification and regression tree, and general linear models and comparison of their performance at Wadi Tayyah Basin, Asir Region, Saudi Arabia10.1007/s10346-015-0614-1 ↗
22. Mapping landslide susceptibility with logistic regression, multiple adaptive regression splines, classification and regression trees, and maximum entropy methods: A comparative study10.1007/s10346-012-0320-1 ↗
23. A comparative study of logistic model tree, random forest, and classification and regression tree models for spatial prediction of landslide susceptibility10.1016/j.catena.2016.11.032 ↗
24. Landslide spatial modeling: Introducing new ensembles of ANN, MaxEnt, and SVM machine learning techniques10.1016/j.geoderma.2017.06.020 ↗
25. Tien Bui, D., Shirzadi, A., Shahabi, H., Geertsema, M., Omidvar, E., Clague, J., Thai Pham, B., Dou, J., Talebpour Asl, D., and Bin Ahmad, B. (2019). New Ensemble Models for Shallow Landslide Susceptibility Modeling in a Semi-Arid Watershed. Forests, 10.10.3390/f10090743 ↗
26. Merghadi, A., Abderrahmane, B., and Tien Bui, D. (2018). Landslide Susceptibility Assessment at Mila Basin (Algeria): A Comparative Assessment of Prediction Capability of Advanced Machine Learning Methods. ISPRS Int. J. Geo-Inf., 7.10.3390/ijgi7070268 ↗
27. Modeling landslide susceptibility in data-scarce environments using optimized data mining and statistical methods10.1016/j.geomorph.2017.12.007 ↗
28. Landslide susceptibility mapping using J48 Decision Tree with AdaBoost, Bagging and Rotation Forest ensembles in the Guangchang area (China)10.1016/j.catena.2018.01.005 ↗
29. Taxonomy for characterizing ensemble methods in classification tasks: A review and annotated bibliography10.1016/j.csda.2009.07.017 ↗
30. Ensemble learning
31. Tien Bui, D., Ho, T.-C., Pradhan, B., Pham, B.-T., Nhu, V.-H., and Revhaug, I. (2016). GIS-based modeling of rainfall-induced landslides using data mining-based functional trees classifier with AdaBoost, Bagging, and MultiBoost ensemble frameworks. Environ. Earth Sci., 75.10.1007/s12665-016-5919-4 ↗
32. Hybrid integration of Multilayer Perceptron Neural Networks and machine learning ensembles for landslide susceptibility assessment at Himalayan area (India) using GIS10.1016/j.catena.2016.09.007 ↗
33. Truong, X., Mitamura, M., Kono, Y., Raghavan, V., Yonezawa, G., Truong, X., Do, T., Tien Bui, D., and Lee, S. (2018). Enhancing Prediction Performance of Landslide Susceptibility Model Using Hybrid Machine Learning Approach of Bagging Ensemble and Logistic Model Tree. Appl. Sci., 8.10.3390/app8071046 ↗
34. Chen, W., Shahabi, H., Zhang, S., Khosravi, K., Shirzadi, A., Chapi, K., Pham, B., Zhang, T., Zhang, L., and Chai, H. (2018). Landslide Susceptibility Modeling Based on GIS and Novel Bagging-Based Kernel Logistic Regression. Appl. Sci., 8.10.3390/app8122540 ↗
35. Park, S., and Kim, J. (2019). Landslide Susceptibility Mapping Based on Random Forest and Boosted Regression Tree Models, and a Comparison of Their Performance. Appl. Sci., 9.10.3390/app9050942 ↗
36. Landslide susceptibility modeling using Reduced Error Pruning Trees and different ensemble techniques: Hybrid machine learning approaches10.1016/j.catena.2018.12.018 ↗
37. Bagging predictors10.1007/BF00058655 ↗
38. The strength of weak learnability10.1007/BF00116037 ↗
39. A decision-theoretic generalization of on-line learning and an application to boosting10.1006/jcss.1997.1504 ↗
40. Random forest10.1023/A:1010933404324 ↗
41. Rotation forest: A new classifier ensemble method10.1109/TPAMI.2006.211 ↗
42. Determination and application of the weights for landslide susceptibility mapping using an artificial neural network10.1016/S0013-7952(03)00142-X ↗
43. A comparative study of conventional, ANN black box, fuzzy and combined neural and fuzzy weighting procedures for landslide susceptibility zonation in Darjeeling Himalayas10.1016/j.enggeo.2006.03.004 ↗
44. Optimal landslide susceptibility zonation based on multiple forecasts10.1016/j.geomorph.2009.06.020 ↗
45. Landslide susceptibility mapping using an ensemble statistical index (Wi) and adaptive neuro-fuzzy inference system (ANFIS) model at Alborz Mountains (Iran)10.1007/s12665-015-5233-6 ↗
46. A comparative assessment of ensemble learning for credit scoring10.1016/j.eswa.2010.06.048 ↗
47. Shu, C., and Burn, D.H. (2004). Artificial neural network ensembles and their application in pooled flood frequency analysis. Water Resour. Res., 40.10.1029/2003WR002816 ↗
48. Improving the reliability of landslide susceptibility mapping through spatial uncertainty analysis: A case study of Al Hoceima, Northern Morocco10.1080/10106049.2017.1357767 ↗
49. Comparing probabilistic and statistical methods in landslide susceptibility modeling in Rwanda/Centre-Eastern Africa10.1016/j.scitotenv.2018.12.248 ↗
50. Random forests and evidential belief function-based landslide susceptibility assessment in Western Mazandaran Province, Iran10.1007/s12665-015-4950-1 ↗
51. Comparative analysis of statistical methods for landslide susceptibility mapping in the Bostanlik District, Uzbekistan10.1016/j.scitotenv.2018.10.431 ↗
52. Space–time prediction of rainfall-induced shallow landslides through a combined probabilistic/deterministic approach, optimized for initial water table conditions10.1007/s10064-013-0546-8 ↗
53. Landslides, threshold slopes, and the survival of relict terrain in the wake of the Mendocino Triple Junction10.1130/G37530.1 ↗
54. Landslide susceptibility assessment using maximum entropy model with two different data sampling methods10.1016/j.catena.2017.01.010 ↗
55. MacQueen, J. (1967, January 19). Some Methods for classification and Analysis of Multivariate Observations. Proceedings of the Fifth Berkeley Symposium on Mathematical Statistics and Probability, Berkeley, CA, USA.
56. Improving Credit Scorecard Modeling Through Applying Text Analysis
57. Refaat, M. (2011). Credit Risk Scorecard: Development and Implementation Using SAS, Lulu.
58. Jopia, H.R. (2019, April 01). Package ‘Smbinning’ Optimal Binning for Scoring Modeling. Available online: https://www.blog.revolutionanalytics.com201503r-package-smbinning-optimal-binning-for-scoring-modeling.html.
59. Hothorn, T., Hornik, K., and Zeileis, A. (2015). Ctree: Conditional inference trees. Compr. R Arch. Netw., 1–34.
60. Stacked Generalization10.1016/S0893-6080(05)80023-1 ↗
61. Zhou, Z. (2012). Ensemble Methods: Foundations and Algorithms, Chapman and Hall/CRC.10.1201/b12207 ↗
62. Landslide susceptibility analysis and its verification using likelihood ratio, logistic regression, and artificial neural network models: Case study of Youngin, Korea10.1007/s10346-007-0088-x ↗
63. Comparison of a logistic regression and Naïve Bayes classifier in landslide susceptibility assessments: The influence of models complexity and training dataset size10.1016/j.catena.2016.06.004 ↗
64. Issues in Stacked Generalization10.1613/jair.594 ↗
65. Witten, I.H., and Frank, E. (2005). Data Mining: Practical Machine Learning Tools and Techniques, Todd Green.
66. Vapnik, V.N. (1995). The Nature of Statistical Learning Theory, Springer.10.1007/978-1-4757-2440-0 ↗
67. Multispectral landuse classification using neural networks and support vector machines: One or the other, or both?10.1080/01431160701294661 ↗
68. Flood susceptibility mapping using a novel ensemble weights-of-evidence and support vector machine models in GIS10.1016/j.jhydrol.2014.03.008 ↗
69. Landslide susceptibility mapping using geological data, a DEM from ASTER images and an Artificial Neural Network (ANN)10.1016/j.geomorph.2009.06.006 ↗
70. Learning representations by back-propagating errors
71. Delineation of landslide hazard areas on Penang Island, Malaysia, by using frequency ratio, logistic regression, and artificial neural network models10.1007/s12665-009-0245-8 ↗
72. Landslide susceptibility mapping using GIS-based multi-criteria decision analysis, support vector machines, and logistic regression10.1007/s10346-013-0391-7 ↗
73. A ‘Non-Parametric’ Version of the Naive Bayes Classifier10.1016/j.knosys.2011.02.014 ↗
74. Domingos, P., and Pazzani, M. (2013, January 4–7). Beyond independence: Conditions for the optimality of the simple Bayesian classifier. Proceedings of the 13th Intl. Conf. Machine Learning, Miami, FL, USA.
75. The design and analysis of benchmark experiments10.1198/106186005X59630 ↗
76. Quadratic programming feature selection
77. Landslide Susceptibility Modeling Using Integrated Ensemble Weights of Evidence with Logistic Regression and Random Forest Models10.3390/app9010171 ↗
78. A GIS-based extended fuzzy multi-criteria evaluation for landslide susceptibility mapping10.1016/j.cageo.2014.08.001 ↗
79. Flood susceptibility mapping using novel ensembles of adaptive neuro fuzzy inference system and metaheuristic algorithms10.1016/j.scitotenv.2017.09.262 ↗
80. Troika—An improved stacking schema for classification tasks10.1016/j.ins.2009.08.025 ↗
81. Is combining classifiers with stacking better than selecting the best one?10.1023/B:MACH.0000015881.36452.6e ↗
82. Ensembling neural networks: Many could be better than all10.1016/S0004-3702(02)00190-X ↗
83. Zeng, X.D., Chao, S., and Wong, F. (2010, January 11–14). Optimization of bagging classifiers based on SBCB algorithm. Proceedings of the 2010 International Conference on Machine Learning and Cybernetics, Qingdao, China.10.1109/ICMLC.2010.5581054 ↗
84. Performance assessment of individual and ensemble data-mining techniques for gully erosion modeling10.1016/j.scitotenv.2017.07.198 ↗
85. Krogh, A., and Vedelsby, J. (1994). Neural network ensembles, cross validation, and active learning. Proceedings of the 7th International Conference on Neural Information Processing Systems, MIT Press.
86. Measures of diversity in classifier ensembles10.1023/A:1022859003006 ↗