Machine Learning for Environmental Hazard Assessment: Advances in Landslide Detection and Prediction
Keywords:
Landslide Detection, Machine Learning, Deep Learning, Susceptibility Mapping, Remote Sensing IntegrationAbstract
Landslides are among the most devastating natural hazards, causing significant human casualties and economic losses worldwide. With the growing impact of climate change on slope instability, the demand for accurate and scalable methods for landslide detection and prediction has intensified. This study systematically reviews and synthesizes recent advancements in applying machine learning and deep learning techniques for landslide hazard assessment, evaluating methodologies, challenges, and future directions. A systematic review was conducted using a detailed protocol, including a comprehensive literature search, defined inclusion and exclusion criteria, and structured data extraction. Studies were classified into three domains: landslide detection, susceptibility mapping, and temporal forecasting. Key performance indicators such as accuracy, precision, recall, F1-score, and area under the curve were synthesized to evaluate model performance. The findings reveal that traditional machine learning methods, notably Support Vector Machines and Random Forests, consistently achieve high accuracy. Deep learning architectures, particularly Convolutional Neural Networks and U-Net, outperform traditional approaches in segmentation accuracy and robustness across diverse spectral and topographic conditions. The integration of multimodal remote sensing data, such as optical imagery, LiDAR, and SAR, significantly improves model reliability by capturing complementary landslide characteristics. Despite these advancements, challenges including limited labelled data, class imbalance, and generalization issues persist. Addressing these limitations requires the development of advanced model architectures, data augmentation strategies, and the implementation of transfer learning and domain adaptation. In conclusion, machine learning and deep learning have substantially advanced landslide hazard assessment, yet further efforts are needed to enhance model scalability and operational applicability.
Downloads
References
Z. Jianqi et al., "Scenario simulation of the geohazard dynamic process of large-scale landslides: a case study of the Xiaomojiu landslide along the Jinsha River," Natural Hazards: Journal of the International Society for the Prevention and Mitigation of Natural Hazards, vol. 112, no. 2, pp. 1337-1357, 2022, doi: 10.1007/s11069-022-05229-7.
C. Morino, P. Coratza, and M. Soldati, "Landslides, a Key Landform in the Global Geological Heritage," (in English), Frontiers in Earth Science, Original Research vol. Volume 10 - 2022, 2022-March-25 2022, doi: 10.3389/feart.2022.864760.
A. Mohan, A. K. Singh, B. Kumar, and R. Dwivedi, "Review on remote sensing methods for landslide detection using machine and deep learning," Transactions on Emerging Telecommunications Technologies, vol. 32, no. 7, p. e3998, 2021, doi: https://doi.org/10.1002/ett.3998.
R. L. Ray, M. Lazzari, and T. Olutimehin, "Remote Sensing Approaches and Related Techniques to Map and Study Landslides," in Landslides - Investigation and Monitoring, R. L. Ray and M. Lazzari Eds. Rijeka: IntechOpen, 2020.
C. Chalkias, C. Polykretis, M. Ferentinou, and E. Karymbalis, "Integrating Expert Knowledge with Statistical Analysis for Landslide Susceptibility Assessment at Regional Scale," Geosciences, vol. 6, p. 14, 03/01 2016, doi: 10.3390/geosciences6010014.
P. Kainthura and N. Sharma, "Hybrid machine learning approach for landslide prediction, Uttarakhand, India," Scientific Reports, vol. 12, no. 1, p. 20101, 2022/11/22 2022, doi: 10.1038/s41598-022-22814-9.
J. Xu and Y. Zhao, "Stability Monitoring of Soil Slope via Big Data Technology in the Context of the Internet of Things," International Journal of Grid and High Performance Computing (IJGHPC), vol. 17, no. 1, pp. 1-18, 2025, doi: 10.4018/IJGHPC.373908.
D. Cao, H. Xing, M. S. Wong, M.-P. Kwan, H. Xing, and Y. Meng, "A Stacking Ensemble Deep Learning Model for Building Extraction from Remote Sensing Images," Remote Sensing, vol. 13, no. 19, doi: 10.3390/rs13193898.
K. Roy and D. M. Farid, "An Adaptive Feature Selection Algorithm for Student Performance Prediction," IEEE Access, vol. 12, pp. 75577-75598, 2024, doi: 10.1109/ACCESS.2024.3406252.
M. S. Adnan, M. S. Rahman, N. Ahmed, B. Ahmed, M. F. Rabbi, and R. M. Rahman, "Improving Spatial Agreement in Machine Learning-Based Landslide Susceptibility Mapping," Remote Sensing, vol. 12, no. 20, doi: 10.3390/rs12203347.
F. S. Tehrani, M. Calvello, Z. Liu, L. Zhang, and S. Lacasse, "Machine learning and landslide studies: recent advances and applications," Natural Hazards, vol. 114, no. 2, pp. 1197-1245, 2022/11/01 2022, doi: 10.1007/s11069-022-05423-7.
T. Liu, T. Chen, R. Niu, and A. Plaza, "Landslide Detection Mapping Employing CNN, ResNet, and DenseNet in the Three Gorges Reservoir, China," IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, vol. 14, pp. 11417-11428, 2021, doi: 10.1109/JSTARS.2021.3117975.
M. I. Sameen and B. Pradhan, "Landslide Detection Using Residual Networks and the Fusion of Spectral and Topographic Information," IEEE Access, vol. 7, pp. 114363-114373, 2019, doi: 10.1109/ACCESS.2019.2935761.
B. Zhang, S. Qiu, and T. Liang, "Dual Attention-Based 3D U-Net Liver Segmentation Algorithm on CT Images," Bioengineering, vol. 11, no. 7, doi: 10.3390/bioengineering11070737.
J. Vega and C. Hidalgo, "Evaluation of U-Net transfer learning model for semantic segmentation of landslides in the Colombian tropical mountain region," MATEC Web Conf., 10.1051/matecconf/202439619002 vol. 396, // 2024. [Online]. Available: https://doi.org/10.1051/matecconf/202439619002.
G. Mandlburger, C. Hauer, B. Höfle, H. Habersack, and N. Pfeifer, "Optimisation of LiDAR derived terrain models for river flow modelling," Hydrology and Earth System Sciences, vol. 13, pp. 1453-1466, 2009, doi: 10.5194/hess-13-1453-200910.5194/hessd-5-3605-2008.
O. A. Alrusaini, "Deep learning for steganalysis: evaluating model robustness against image transformations," Frontiers in Artificial Intelligence, Original Research vol. Volume 8 - 2025, 2025. [Online]. Available: https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2025.1532895.
A. Rizaldy, A. J. Afifi, P. Ghamisi, and R. Gloaguen, "Improving Mineral Classification Using Multimodal Hyperspectral Point Cloud Data and Multi-Stream Neural Network," Remote Sensing, vol. 16, no. 13, doi: 10.3390/rs16132336.
O. Oak, R. Nazre, S. Naigaonkar, S. Sawant, and H. Vaidya, "A Comparative Analysis of CNN-based Deep Learning Models for Landslide Detection," in 2024 Asian Conference on Intelligent Technologies (ACOIT), 6-7 Sept. 2024 2024, pp. 1-6, doi: 10.1109/ACOIT62457.2024.10939989.
R. Fu et al., "Fast Seismic Landslide Detection Based on Improved Mask R-CNN," Remote Sensing, vol. 14, no. 16, doi: 10.3390/rs14163928.
F. França Pereira et al., "Comparison of LiDAR- and UAV-derived data for landslide susceptibility mapping using Random Forest algorithm," Landslides, vol. 20, no. 3, pp. 579-600, 2023/03/01 2023, doi: 10.1007/s10346-022-02001-7.
A. C. Mondini, M. Santangelo, M. Rocchetti, E. Rossetto, A. Manconi, and O. Monserrat, "Sentinel-1 SAR Amplitude Imagery for Rapid Landslide Detection," Remote Sensing, vol. 11, no. 7, doi: 10.3390/rs11070760.
S. Mihalić Arbanas et al., "Landslide Detection and Spatial Prediction: Application of Data and Information from Landslide Maps," in Progress in Landslide Research and Technology, Volume 1 Issue 2, 2022, I. Alcántara-Ayala et al. Eds. Cham: Springer International Publishing, 2023, pp. 195-212.
D. F. T. Machado, S. H. G. Silva, N. Curi, and M. D. d. Menezes, "Soil type spatial prediction from Random Forest: different training datasets, transferability, accuracy and uncertainty assessment," Scientia Agricola, vol. 76, 2019.
H. Suryanto, A. Mahidadia, M. Bain, C. Guan, and A. Guan, "Credit Risk Modeling Using Transfer Learning and Domain Adaptation," Frontiers in Artificial Intelligence, Original Research vol. Volume 5 - 2022, 2022. [Online]. Available: https://www.frontiersin.org/journals/artificial-intelligence/articles/10.3389/frai.2022.868232.
Downloads
Published
Issue
Section
License
Copyright (c) 2025 Zulhelmi Zulhelmi, Elizar Elizar, Nural Fajri, Aulia Rahman (Author)
This work is licensed under a Creative Commons Attribution-ShareAlike 4.0 International License.
