Ensemble Machine Learning Models for Landslide Susceptibility Assessment in Uttaradit, Thailand
Article Sidebar
Main Article Content
Abstract
This research compared the performance of ensemble learning methods by using different boosting algorithms: adaptive (ADA), gradient (GB), and eXtreme gradient boosting (XGB) for assessing landslide susceptibility in Uttaradit Province. It uses 30 years of historical data on landslide occurrences and non-occurrences to train and validate the models. The analysis includes 14 natural and human-induced factors influencing landslide susceptibility. Multicollinearity testing set criteria (VIF < 5 and TOL > 0.10) with nine factors selected for modelling. Model performance was statistically evaluated. Key findings include: 1) geomorphological factors were consistently the most significant across all models; 2) all three models effectively assessed landslide susceptibility, with GB and XGB achieving the highest performance (97%) based on harmonic mean of precision and recall (F1) score and overall accuracy; 3) XGB demonstrated the highest effectiveness (99%) in receiver operating characteristic (ROC) curve analysis. Predictive susceptibility distributions among the three models were similar in high-risk areas, except ADA, which showed broader and less detailed segmentation than other models. These findings confirm the potential of ensemble learning techniques, especially GB and XGB for accurate landslide prediction and risk reduction strategy.
Downloads
Article Details
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
References
กรมทรัพยากรธรณี. (2551). ธรณีวิทยาของจังหวัดอุตรดิตถ์. จังหวัดอุตรดิตถ์ http://www.uttaradit.go.th
กรมอุตุนิยมวิทยา. (2566). ภูมิอากาศจังหวัดอุตรดิตถ์. ศูนย์ภูมิอากาศกรมอุตุนิยมวิทยา. http://climate.tmd.go.th/data/province/เหนือ/ภูมิอากาศอุตรดิตถ์.pdf
Akinci, H., Kilicoglu, C., & Dogan, S. (2020). Random forest-based landslide susceptibility mapping in coastal regions of Artvin, Turkey. ISPRS International Journal of Geo-Information, 9(9), 553. https://doi.org/10.3390/ijgi9090553
Akgun, A. (2012). A comparison of landslide susceptibility maps produced by logistic regression, multi-criteria decision, and likelihood ratio methods: a case study at zmir, Turkey. Landslides, 9(1), 93-106.
Alizadeh, M., Hashim, M., Alizadeh, E., Shahabi, H., Karami, M., Beiranvand Pour, A., Pradhan, B., & Zabihi, H. (2018). Multi-criteria decision making (MCDM) model for seismic vulnerability assessment (SVA) of urban residential buildings. ISPRS International Journal of Geo-Information, 7(11), 444. https://doi.org/10.3390/ijgi7110444
Aydin, H. E., & Iban, M. C. (2023). Predicting and analyzing flood susceptibility using boosting-based ensemble machine learning algorithms with SHapley Additive exPlanations. Natural Hazards, 116(1), 2957-2991. https://doi.org/10.1007/s11069-022-05793-y
Bui, D. T., Lofman, O., Revhaug, I., & Dick, O. (2011). Landslide susceptibility analysis in the Hoa Binh province of Vietnam using statistical index and logistic regression. Natural hazards, 59(3), 1413-1444. https://doi.org/10.1007/s11069-011-9844-2
Choi, J., Oh, H.-J., Lee, H.-J., Lee, C., & Lee, S. (2012). Combining landslide susceptibility maps obtained from frequency ratio, logistic regression, and artificial neural network models using ASTER images and GIS. Engineering Geology, 124, 12-23. https://doi.org/10.1016/j.enggeo.2011.09.011
Guzzetti, F., Cardinali, M., Reichenbach, P., Cipolla, F., Sebastiani, C., Galli, M., & Salvati, P. (2004). Landslide hazard assessment in the Collazzone area, Umbria, Central Italy. Natural Hazards and Earth System Sciences, 4(1), 1-15. https://doi.org/10.5194/nhess-4-1-2004
Keefer, D. K. (1984). Landslides caused by earthquakes. Geological Society of America Bulletin, 95(4), 406-421.
Reichenbach, P., Rossi, M., Malamud, B. D., Mihir, M., & Guzzetti, F. (2018). A review of statistically based landslide susceptibility models. Earth-science reviews, 180, 60-91.
Regmi, A. D., Devkota, K. C., Yoshida, K., & Pourghasemi, H. R. (2014). Application of frequency ratio, statistical index, and weights-of-evidence models and their comparison in landslide susceptibility mapping in Central Nepal Himalaya. Arabian Journal of Geosciences, 7, 725–742. https://doi.org/10.1007/s12517-012-0807-z
Rong, G., Alu, S., Li, K., Su, Y., Zhang, J., Zhang, Y., & Li, T. (2020). Rainfall induced landslide susceptibility mapping based on Bayesian optimized random forest and gradient boosting decision tree models—A case study of Shuicheng County, China. Water, 12(11), 3066. https://doi.org/10.3390/w12113066
Sokolova, M., Japkowicz, N., & Szpakowicz, S. (2006). Beyond accuracy, F-score and ROC: A family of discriminant measures for performance evaluation. In A. Sattar, & B. H. Kang (Eds.), AI 2006: Advances in Artificial Intelligence (pp. 1015-1021). Springer. https://doi.org/10.1007/11941439_114
Inan, M. S. K., & Rahman, I. (2023). Explainable AI integrated feature selection for landslide susceptibility mapping using Tree SHAP. SN Computer Science, 4, 482. https://doi.org/10.1007/s42979-023-01960-5
Intarat, K., Yoomee, P., Hussadin, A., & Lamprom, W. (2024). Assessment of landslide susceptibility in the intermontane basin area of Northern Thailand. Environment and Natural Resources Journal, 22(2), 158-170. https://doi.org/10.32526/ennrj/22/20230241
Halder, K., Srivastava, A. K., Ghosh, A., Das, S., Banerjee, S., Pal, S. C., Chatterjee, U., Bisai, D., Ewert, F., & Gaiser, T. (2024). Improving landslide susceptibility prediction through ensemble Recursive Feature Elimination and meta-learning framework. Research Square. Advance online publication. https://doi.org/10.21203/rs.3.rs-3991474/v1
Huan, Y., Song, L., Khan, U., & Zhang, B. (2023). Stacking ensemble of machine learning methods for landslide susceptibility mapping in Zhangjiajie City, Hunan Province, China. Environmental Earth Sciences, 82(1), Article 35. https://doi.org/10.1007/s12665-022-10413-1
Hydro-Informatics Institute. (n.d.). North flood situation in May 2006. Retrieved May 06, 2024, from https://tiwrm.hii.or.th/current/FloodNorth_May49.html
Trigila, A., Frattini, P., Casagli, N., Catani, F., Crosta, G., Esposito, C., Ladanza, C., Lagomarsino, D., Mugnozza, G. S., Segoni, S., Spizzichino, D., Tofani, V., & Lari, S. (2013). Landslide susceptibility mapping at national scale: The Italian case study. In C. Margottini, P. Canuti, & K, Sassa (Eds.), Landslide science and practice (pp. 287-295). Springer.
Park, S., Choi, C., Kim, B., & Kim, J. (2013). Landslide susceptibility mapping using frequency ratio, analytic hierarchy process, logistic regression and artificial neural network methods at the Inje area, Korea. Environmental Earth Sciences, 68, 1443-1464. https://doi.org/10.1007/s12665-012-1842-5
Pham, B. T., Pradhan, B., Bui, D. T., Prakash, I., & Dholakia, M. (2016). A comparative study of different machine learning methods for landslide susceptibility assessment: A case study of Uttarakhand area (India). Environmental Modelling & Software, 84, 240-250. https://doi.org/10.1016/j.envsoft.2016.06.019
Freund, Y., & Schapire, R. E. (1997). A decision-theoretic generalization of on-line learning and an application to boosting. Journal of computer and system sciences, 55(1), 119-139.
Jennifer, J. J. (2022). Feature elimination and comparison of machine learning algorithms in landslide susceptibility mapping. Environmental Earth Sciences, 81, 489. https://doi.org/10.1007/s12665-022-10620-5
Muschelli, J. (2020). ROC and AUC with a binary predictor: A potentially misleading metric. Journal of Classification, 37(3), 696-708. https://doi.org/10.1007/s00357-019-09345-1
Wu, Y., Ke, Y., Chen, Z., Liang, S., Zhao, H., & Hong, H. (2020). Application of alternating decision tree with AdaBoost and bagging ensembles for landslide susceptibility mapping. CATENA, 187, 104396. https://doi.org/10.1016/j.catena.2019.104396
Yu, H., Pei, W., Zhang, J., & Chen, G. (2023). Landslide susceptibility mapping and driving mechanisms in a vulnerable region based on multiple machine learning models. Remote Sensing, 15(7), 1886. https://doi.org/10.3390/rs15071886
Yu, X., Zhang, K., Song, Y., Jiang, W., & Zhou, J. (2021). Study on landslide susceptibility mapping based on rock-soil characteristic factors. Scientific Reports, 11(1), 15476. https://doi.org/10.1038/s41598-021-94936-5
Yalcin, A. (2008). GIS-based landslide susceptibility mapping using analytical hierarchy process and bivariate statistics in Ardesen (Turkey): Comparisons of results and confirmations. CATENA, 72(1), 1-12. https://doi.org/10.1016/j.catena.2007.01.003