Assessment of Liquefaction Hazard Potential Using Decision Tree, Random Forest and Support Vector Machine: A Case Study of Samarinda, Indonesia
DOI:
https://doi.org/10.57152/malcom.v6i3.2541Keywords:
Decision Treex, Liquefaction Hazard Mapping, Machine Learning, Random Forest, Support Vector MachineAbstract
Earthquake-induced soil liquefaction is a major hazard for urban areas in Indonesia built on recent alluvial deposits. This study evaluates three supervised machine learning algorithms Decision Tree (DT), Random Forest (RF), and Support Vector Machine (SVM) liquefaction hazard mapping in Samarinda, East Kalimantan. Four predictor variables were used: shear wave velocity (Vs30), peak ground acceleration (PGA), groundwater level (GWL), and slope. Because only four Cone Penetration Test (CPT) locations were available, the dataset was expanded to 532 labeled samples through stratified spatial sampling of a previously published CPT-based fuzzy GIS liquefaction map. An 80:20 train-test split was used, and SMOTE was applied only to the training data to address class imbalance. Model performance was evaluated using accuracy, precision, recall, F1-score, and confusion matrices. DT achieved the best performance with an accuracy and weighted F1-score of 0.87, followed by SVM (0.80) and RF (0.78). The resulting hazard map classified Samarinda into Very Low (68%), Low (6%), High (7%), and Very High (19%) hazard zones. High-risk areas were concentrated in the eastern part of the city, where shallow groundwater, Sulfaquent soils, and recent alluvial deposits are present.
Downloads
References
I. M. Idriss and R. W. Boulanger, Soil Liquefaction During Earthquakes. Oakland, CA, USA: Earthquake Engineering Research Institute, 2008.
R. Jena, B. Pradhan, M. Almazroui, M. Assiri, and H. J. Park, "Earthquake-induced liquefaction hazard mapping at national-scale in Australia using deep learning techniques," Geosci. Front., vol. 14, no. 1, p. 101460, 2023, doi: 10.1016/j.gsf.2022.101460.
G. M. Muftuoglu and K. Dehghanian, "Soil liquefaction assessment using machine learning," Artif. Intell. Geosci., vol. 6, no. 1, p. 100122, 2025, doi: 10.1016/j.aiig.2025.100122.
J. Zhu, L. G. Baise, and E. M. Thompson, “An updated geospatial liquefaction model for global application,” Bull. Seismol. Soc. Am., vol. 107, no. 3, pp. 1365–1385, 2017, doi: 10.1785/0120160198.
Badan Meteorologi, Klimatologi, dan Geofisika, Katalog Gempa Bumi Merusak Tahun 1821-2024. Jakarta: Badan Meteorologi, Klimatologi, dan Geofisika, 2025. Accessed: Jan. 23, 2026. [Online]. Available: https://content.bmkg.go.id/wp-content/uploads/Katalog-Gempabumi-Signifikan-Merusak-1821-2025_BMKG.pdf
R. Jena, B. Pradhan, G. Beydoun, A. M. Alamri, Ardiansyah, Nizamuddin, and H. Sofyan, H., "Earthquake hazard and risk assessment using machine learning approaches at Palu, Indonesia," Sci. Total Environ., vol. 749, p. 141582, Dec. 2020, doi: 10.1016/j.scitotenv.2020.141582.
A. M. Kamal, M. T. Sahebi, M. S. Hossain, M. Z. Rahman, and A. K. F. Fahim, "Liquefaction hazard mapping of the south-central coastal areas of Bangladesh," Nat. Hazards Res., vol. 4, no. 3, pp. 520–529, 2024, doi: 10.1016/j.nhres.2023.12.016.
A. Ayele, K. Woldearegay, and M. Meten, "Seismic hazard evaluation using site response analysis and amplitude parameters at Hawassa town, Main Ethiopian Rift," Arab. J. Geosci., vol. 16, no. 3, p. 212, 2023, doi: 10.1007/s12517-023-11301-8.
A. Rachmadi, M. R. Septyandy, and M. A. Syam, “Determination of Liquefaction Hazard in Samarinda Using Fuzzy-GIS Method,” El-Jughrafiyah, vol. 4, no. 2, p. 273, 2024, doi: 10.24014/jej.v4i2.33050.
J. Hu, L. Huang, and Q. Shao, "Combination models of random forest for predicting seismic liquefaction based on SPT, CPT, Vs databases considering sampling strategies," Soil Dyn. Earthq. Eng., vol. 198, p. 109642, 2025, doi: https://doi.org/10.1016/j.soildyn.2025.109642.
V. R. Kohestani, M. Hassanlourad, and A. Ardakani, "Evaluation of liquefaction potential based on CPT data using random forest," Nat. Hazards, vol. 79, no. 2, pp. 1079–1089, 2015, doi: 10.1007/s11069-015-1893-5.
A. H. Gandomi, M. M. Fridline, and D. A. Roke, "Decision tree approach for soil liquefaction assessment," Sci. World J., vol. 2013, no. 1, p. 346285, Jan. 2013, doi: 10.1155/2013/346285.
S. Demir and E. K. Sahin, “Comparison of tree-based machine learning algorithms for predicting liquefaction potential using canonical correlation forest, rotation forest, and random forest based on CPT data,” Soil Dyn. Earthq. Eng., vol. 154, p. 107130, 2022, doi: 10.1016/j.soildyn.2021.107130.
P. Chithuloori and J. M. Kim, "Soft voting ensemble classifier for liquefaction prediction based on SPT data," Artif. Intell. Rev., vol. 58, no. 8, p. 228, 2025, doi: 10.1007/s10462-025-11230-w.
M. Ahmad, X. W. Tang, J. N. Qiu, F. Ahmad, and W. J. Gu, "Application of machine learning algorithms for the evaluation of seismic soil liquefaction potential," Front. Struct. Civ. Eng., vol. 15, no. 2, pp. 490–505, 2021, doi: 10.1007/s11709-020-0669-5.
C. Y. Liu, C. Y. Ku, T. Y. Wu, Y. J. Chiu, and C. W. Chang, “Liquefaction susceptibility mapping using artificial neural network for offshore wind farms in Taiwan,” Eng. Geol., vol. 351, p. 108013, 2025, doi: 10.1016/j.enggeo.2025.108013.
Z. Ba, S. Han, M. Wu, Y. Lu, and J. Liang, "An enhanced hybrid approach for spatial distribution of seismic liquefaction characteristics by integrating physics-based simulation and machine learning," Soil Dyn. Earthq. Eng., vol. 187, p. 109007, 2024, doi: 10.1016/j.soildyn.2024.109007.
A. S. Nejad, E. Guler, and M. Ozturan, "Evaluation of Liquefaction Potential Using Random Forest Method and Shear Wave Velocity Results," in Proceedings - 2018 International Conference on Applied Mathematics and Computational Science, ICAMCS.NET 2018, 2018, pp. 23–26. doi: 10.1109/ICAMCS.NET46018.2018.00012.
K. Jas and G. R. Dodagoudar, "Liquefaction Potential Assessment of Soils Using Machine Learning Techniques: A State-of-the-Art Review from 1994–2021," Int. J. Geomech., vol. 23, no. 7, p. 3123002, 2023, doi: 10.1061/ijgnai.gmeng-7788.
D. Ranjan Kumar and W. Wipulanusat, "Advancements in predicting soil liquefaction susceptibility: a comprehensive analysis of ensemble and deep learning approaches," Sci. Rep., vol. 15, no. 1, p. 26453, Jul. 2025, doi: 10.1038/s41598-025-04280-1.
C. Y. Liu, C. Y. Ku, Y. J. Chiu, and T. Y. Wu, "Evaluation of liquefaction potential in central Taiwan using random forest method," Sci. Rep., vol. 14, no. 1, p. 27517, Nov. 2024, doi: 10.1038/s41598-024-79127-2.
Y. Yang and Y. Wei, "A New Shear Wave Velocity-Based Liquefaction Probability Model Using Logistic Regression: Emphasizing Fines Content Optimization," Appl. Sci., vol. 14, no. 15, 2024, doi: 10.3390/app14156793.
T. L. Youd et al., "Liquefaction Resistance of Soils: Summary Report from the 1996 NCEER and 1998 NCEER/NSF Workshops on Evaluation of Liquefaction Resistance of Soils," J. Geotech. Geoenvironmental Eng., vol. 127, no. 10, pp. 817–833, Oct. 2001, doi: 10.1061/(asce)1090-0241(2001)127:10(817).
] I. M. Idriss and R. W. Boulanger, "SPT- and CPT-based relationships for the residual shear strength of liquefied soils," Soil Dyn. Earthq. Eng., vol. 68, pp. 57–68, 2015, doi: 10.1016/j.soildyn.2014.09.010.
N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, "SMOTE: Synthetic Minority Over-sampling Technique," J. Artif. Intell. Res., vol. 16, pp. 321–357, 2002, doi: 10.1613/jair.953.
P. K. Robertson, "Estimating soil unit weight from CPT," in Proc. 2nd Int. Symp. Cone Penetration Testing (CPT'10), Huntington Beach, CA, USA, 2010, pp. 1–8.
L. Breiman, "Random forests," Mach. Learn., vol. 45, no. 1, pp. 5–32, 2001, doi: 10.1023/A:1010933404324.
C. Cortes and V. Vapnik, “Support-vector networks,” Mach. Learn., vol. 20, no. 3, pp. 273–297, 1995, doi: 10.1007/bf00994018.
Downloads
Published
How to Cite
Issue
Section
License
Copyright (c) 2026 Muhammad Rizqy Septyandy, Divo Dwi Bramantyo, Muhammad Amin Syam
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
Copyright © by Author; Published by Institut Riset dan Publikasi Indonesia (IRPI)
This Indonesian Journal of Machine Learning and Computer Science is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
