Novel Integration of JCHAIDStar with ensemble techniques for comprehensive landslide and flash flood susceptibility mapping

Dat Vu Cao; Nga Pham Thi Thanh; Thai Tran Hong; Phong Tran Van; Khiem Mai Van; Dai Hoang Van; Indra Prakash; Binh Thai Pham

doi:10.15625/2615-9783/24030

Author affiliations

Authors

Vu Cao Dat Viet Nam Institute of Meteorology, Hydrology and Climate Change, Hanoi, Vietnam
Pham Thi Thanh Nga Viet Nam Institute of Meteorology, Hydrology and Climate Change, Hanoi, Vietnam
Tran Hong Thai Viet Nam Academy of Science and Technology, Hanoi, Vietnam
Tran Van Phong 1-Institute of Earth Sciences, VAST, Hanoi, Vietnam; 2-Graduate University of Science and Technology, VAST, Hanoi, Vietnam
Mai Van Khiem Viet Nam Meteorological and Hydrological Administration, Hanoi, Vietnam
Hoang Van Dai Viet Nam Meteorological and Hydrological Administration, Hanoi, Vietnam
Indra Prakash DDG (R) Geological Survey of India, Gandhinagar 382010, India
Binh Thai Pham Geotechnical and Artificial Intelligence research group, University of Transport Technology, Hanoi, Vietnam Received

DOI:

https://doi.org/10.15625/2615-9783/24030

Keywords:

Landslides, flash floods, multi hazards, machine learning, Bagging, JCHAIDStar, Vietnam

Abstract

This study highlights a novel ensemble approach integrating the JCHAIDStar model with various ensemble techniques namely Dagging (Dag), Bagging (Bag), Decorate (Deco), and Cascade Generalization (CG) for multi-hazard susceptibility assessment and mapping of landslides and flash floods (LS-FF) in Ha Giang province, Vietnam. A total of 963 landslides and 106 flash flood events were used for model development and validation. Flash floods rapidly saturate soil, reducing its cohesion and destabilizing slopes, which leads to landslides. Conversely, landslides may block rivers, creating natural dams that fail abruptly, resulting in flash floods. In this study, a comprehensive dataset comprising 963 landslides, 106 flash floods, and thirteen conditioning factors related to topography, hydrology, geology, and meteorology was utilized. This dataset was split into training (70%) and test (30%) sets for model development and validation, with AUC used to evaluate performance; the Bag-JCHAIDStar model achieved the highest predictive accuracy (AUC = 0.985 for training and 0.951 for testing). The results demonstrated that ensemble-based JCHAIDStar models outperformed single benchmark models (LR and SVM). The generated susceptibility maps provided reliable spatial information for land-use planning and disaster risk mitigation.

Downloads

Download data is not yet available.

References

Akbar M., Bhat M.S., Khan A.A., 2023. Multi-hazard susceptibility mapping for disaster risk reduction in Kargil-Ladakh Region of Trans-Himalayan India. Environmental Earth Sciences, 82(2), 68.

Anh T.T., Viet H.P., Thi T.T., Anh N.N.T., Van D.N., Trong T.P., Tuan H.P., Van P.T., 2025. Landslide susceptibility in Phuoc Son, Quang Nam: A deep learning approach. Vietnam Journal of Earth Sciences, 47(1), 42−60. https://doi.org/10.15625/2615-9783/21658.

Bordbar M., Aghamohammadi H., Pourghasemi H.R., Azizi Z., 2022. Multi-hazard spatial modeling via ensembles of machine learning and meta-heuristic techniques. Scientific Reports 12(1), 1451.

Choubin B., Jaafari A., Mafi-Gholami D., 2025. A spatially explicit multi-hazard framework for assessing flood, landslide, wildfire, and drought susceptibilities. Advances in Space Research, 75(3), 2569−2583.

Costache R., Tin T.T., Arabameri A., Crăciun A., Costache I., Islam A.R.M.T., Sahana M., Pham B.T., 2022. Stacking state-of-the-art ensemble for flash-flood potential assessment. Geocarto International, 37(26), 13812−13838.

Deijns A.A., Dewitte O., Thiery W., d'Oreye N., Malet J.-P., Kervyn F., 2022. Timing landslide and flash flood events from SAR satellite: a regionally applicable methodology illustrated in African cloud-covered tropical environments. Natural Hazards and Earth System Sciences, 22(11), 3679−3700.

Deijns A.A., Michéa D., Déprez A., Malet J.-P., Kervyn F., Thiery W., Dewitte O., 2024. A semi-supervised multi-temporal landslide and flash flood event detection methodology for unexplored regions using massive satellite image time series. ISPRS Journal of Photogrammetry and Remote Sensing, 215, 400−418.

Duc N.D., Nguyen M.D., Prakash I., Van H.N., Van Le H., Thai P.B., 2025. Prediction of safety factor for slope stability using machine learning models. Vietnam Journal of Earth Sciences.

Hong H., 2023. Assessing landslide susceptibility based on hybrid Best-first decision tree with ensemble learning model. Ecological Indicators, 147, 109968.

Kass G.V., 1980. An exploratory technique for investigating large quantities of categorical data. Journal of the royal statistical society: series c (Applied statistics), 29(2), 119−127.

Le Minh N., Truyen P.T., Van Phong T., Jaafari A., Amiri M., Van Duong N., Van Bien N., Duc D.M., Prakash I., Pham B.T., 2023. Ensemble models based on radial basis function network for landslide susceptibility mapping. Environmental Science and Pollution Research, 30(44), 99380−99398.

Li C., Wang M., Chen F., Coulthard T.J., Wang L., 2023. Integrating the SLIDE model within CAESAR-Lisflood: Modeling the 'rainfall-landslide-flash flood'disaster chain mechanism under landscape evolution in a mountainous area. Catena, 227, 107124.

Luu C., Nguyen D.D., Amiri M., Van P.T., Bui Q.D., Prakash I., Pham B.T., 2022. Flood susceptibility modeling using Radial Basis Function Classifier and Fisher's linear discriminant function. Vietnam Journal of Earth Sciences, 44(1), 55−72. https://doi.org/10.15625/2615-9783/16626.

Mfondoum A.H.N., Nguet P.W., Seuwui D.T., Mfondoum J.V.M., Ngenyam H.B., Diba I., Tchindjang, M., Djiangoue, B., Mihi, A., Hakdaoui, S., 2023. Stepwise integration of analytical hierarchy process with machine learning algorithms for landslide, gully erosion and flash flood susceptibility mapping over the North-Moungo perimeter, Cameroon. Geoenvironmental Disasters, 10(1), 22.

Nachappa T.G., Ghorbanzadeh O., Gholamnia K., Blaschke T., 2020. Multi-hazard exposure mapping using machine learning for the State of Salzburg, Austria. Remote Sensing, 12(17), 2757.

Ngo T.Q., Nguyen L.Q., Tran V.Q., 2022. Predicting tensile strength of cemented paste backfill with aid of second order polynomial regression. Journal of Science and Transport Technology, 43−51.

Nguyen C.Q., Nguyen D.A., Tran H.T., Nguyen T.T., Thao B.T.P., Cong N.T., Van Phong T., Van Le H., Prakash I., Pham B.T., 2024. Predicting landslide and debris flow susceptibility using Logitboost alternating decision trees and ensemble techniques. Natural Hazards, 121(2), 1661−1686.

Nguyen D.D., Nguyen H.P., Vu D.Q., Prakash I., Pham B.T., 2023a. Using GA-ANFIS machine learning model for forecasting the load bearing capacity of driven piles. Journal of Science and Transport Technology, 3(2), 26−33.

Nguyen H.D., Dang D.K., Bui Q.T., Petrisor A.I., 2023b. Multi‐hazard assessment using machine learning and remote sensing in the North Central region of Vietnam. Transactions in GIS, 27(5), 1614−1640.

Nguyen H.D., Dang D.K., Nguyen Y.N., Van C.P., Truong Q.-H., Bui Q.-T., Petrisor A.-I., 2023c. A framework for flood depth using hydrodynamic modeling and machine learning in the coastal province of Vietnam. Vietnam Journal of Earth Sciences.

Nhat V.H., Trinh P.T., Cam L.V., Dieu B.T., Van Hiep L., Prakash I., Anh N.N., Van Hong N., Thanh N.D., Thao N.P., 2025. Mapping Cadmium Contamination Potential in Surface Soil for Civil Engineering Applications: A Comparative Study of Machine Learning and Deep Learning Models in the Gianh River Basin, Vietnam. Journal of Science and Transport Technology, 48−70.

Nohani E., Khazaei S., Dorjahangir M., Asadi H., Elkaee S., Mahdavi A., Hatamiafkoueieh J., Tiefenbacher J.P., 2024. Delineating flood-prone areas using advanced integration of reduced-error pruning tree with different ensemble classifier algorithms. Acta Geophysica, 72(5), 3473−3484.

Pal S., Hieu V.T., Nguyen D.D., Vu D.Q., Prakash I., 2024. Investigation of support vector machines with different kernel functions for prediction of compressive strength of concrete. Journal of Science and Transport Technology, 55−68.

Pham B.T., Vu V.D., Costache R., Phong T.V., Ngo T.Q., Tran T.-H., Nguyen H.D., Amiri M., Tan M.T., Trinh P.T., 2022. Landslide susceptibility mapping using state-of-the-art machine learning ensembles. Geocarto International, 37(18), 5175−5200.

Pham N.T.T., Nong D., Garschagen M., 2021. Natural hazard's effect and farmers' perception: Perspectives from flash floods and landslides in remotely mountainous regions of Vietnam. Science of the Total Environment, 759, 142656.

Pham N.T.T., Nong D., Sathyan A.R., Garschagen M., 2020. Vulnerability assessment of households to flash floods and landslides in the poor upland regions of Vietnam. Climate Risk Management, 28, 100215.

Pham T.A., 2024. Developing a Machine Learning Model for Predicting the Settlement of Bored Piles. Journal of Science and Transport Technology, 95−109.

Pourghasemi H.R., Gayen A., Panahi M., Rezaie F., Blaschke T., 2019. Multi-hazard probability assessment and mapping in Iran. Science of the Total Environment, 692, 556−571.

Pourghasemi H.R., Kariminejad N., Amiri M., Edalat M., Zarafshar M., Blaschke T., Cerda A., 2020. Assessing and mapping multi-hazard risk susceptibility using a machine learning technique. Scientific Reports, 10(1), 3203.

Pourghasemi H.R., Pouyan S., Bordbar M., Golkar F., Clague J.J., 2023. Flood, landslides, forest fire, and earthquake susceptibility maps using machine learning techniques and their combination. Natural Hazards, 116(3), 3797−3816.

Prakash I., Gandhi F., Songara J., Darji K., Pham B.T., 2024a. Geotechnical Challenges and Solutions in the Construction of Underground Powerhouse with Shallow Basalt Rock Cover: A Review of Sardar Sarovar Narmada Project Case Study. Journal of Science and Transport Technology, 1−18.

Prakash I., Nguyen D.D., Tuan N.T., Van Phong T., Van Hiep L., 2024b. Landslide susceptibility zoning: integrating multiple Intelligent models with SHAP Analysis. Journal of Science and Transport Technology, 23−41.

Prakash I., Pham B.T., 2024. Geotechnical Forensic Investigations of a Gravity Dam: Addressing Seepage and Sliding Problems in the Basalt Foundations of Karjan Dam, Gujarat, India. Journal of Science and Transport Technology, 24−38.

Saha S., Bera B., Shit P.K., Sengupta D., Bhattacharjee S., Sengupta N., Majumdar P., Adhikary P.P., 2023. Modelling and predicting of landslide in Western Arunachal Himalaya, India. Geosystems and Geoenvironment, 2(2), 100158.

Sarker S., Adnan M.S.G., 2024. Evaluating multi-hazard risk associated with tropical cyclones using the fuzzy analytic hierarchy process model. Natural Hazards Research, 4(1), 97−109.

Shen Z., Deng H., Arabameri A., Santosh M., Vojtek M., Vojteková J., 2023. Mapping potential inundation areas due to riverine floods using ensemble models of credal decision tree with bagging, dagging, decorate, multiboost, and random subspace. Advances in Space Research, 72(11), 4778−4794.

Ullah K., Wang Y., Fang Z., Wang L., Rahman M., 2022. Multi-hazard susceptibility mapping based on Convolutional Neural Networks. Geoscience Frontiers, 13(5), 101425.

Wang Y., Wang L., Liu S., Liu P., Zhu Z., Zhang W., 2024. A comparative study of regional landslide susceptibility mapping with multiple machine learning models. Geological Journal, 59(9), 2383−2400.

Youssef A.M., Mahdi A.M., Pourghasemi H.R., 2022. Landslides and flood multi-hazard assessment using machine learning techniques. Bulletin of Engineering Geology and the Environment, 81(9), 370.

Youssef A.M., El Haddad B.A., Skilodimou H.D., Bathrellos G.D., Golkar F., Pourghasemi H.R., 2024. Landslide susceptibility, ensemble machine learning, and accuracy methods in the southern Sinai Peninsula, Egypt: Assessment and Mapping. Natural Hazards, 120(15), 14227−14258.

Zhang K., Chen G., Xia Y., Wang S., 2022. An Ensemble‐Based, Remote‐Sensing‐Driven, Flood‐Landslide Early Warning System. Remote Sensing of Water‐Related Hazards, 123−134.

Zhao C., Peng R., Wu D., 2023. Bagging and boosting fine-tuning for ensemble learning. IEEE Transactions on Artificial Intelligence, 5(4), 1728−1742.