AI-Enabled Remote Sensing for Multi-Hazard Disaster Risk Management: Advances, Challenges, and Future Research Directions
DOI:
https://doi.org/10.66132/Keywords:
Artificial Intelligence, GeoAI, Disaster risk reduction, Multi hazard, Remote sensingAbstract
Earth observation (EO) and artificial intelligence (AI) are increasingly integrated to support disaster risk management through rapid hazard detection, impact assessment, monitoring and decision support. Advances in machine learning, deep learning, transformers, multimodal learning and geospatial foundation models have substantially improved the analysis of satellite, synthetic aperture radar (SAR), thermal, LiDAR, UAV and ancillary geospatial data. However, high predictive accuracy does not necessarily translate into operational reliability, particularly when models are evaluated using geographically narrow datasets, random data partitions or individual disaster events. This critical review synthesizes AI-enabled remote sensing for floods, droughts, wildfires, landslides, earthquakes, tropical cyclones and compound hazards across the disaster-management cycle. Particular attention is given to data representativeness, spatial and temporal leakage, domain shift, sensor interoperability, class imbalance, interpretability, physical consistency, uncertainty calibration and computational latency. The review argues that disaster Geospatial Artificial Intelligence (GeoAI) should be evaluated not only through conventional predictive metrics but also through independent-event validation, geographic transferability, uncertainty calibration, timeliness and decision relevance.Future research should prioritize multimodal and process-aware learning, self-supervised pretraining, rigorously evaluated foundation models, open multi-hazard benchmarks and human-in-the-loop systems. The transition from accurate hazard mapping to transferable, uncertainty-aware and operationally credible disaster intelligence is identified as a key priority for the next generation of AI-enabled disaster risk management
Downloads
References
Akosah, S., Gratchev, I., Kim, D.-H., & Ohn, S.-Y. (2024). Application of artificial intelligence and remote sensing for landslide detection and prediction: Systematic review. Remote Sensing, 16(16), 2947. https://doi.org/10.3390/rs16162947
August, O. (2026). Remote sensing and machine learning approaches for hydrological drought detection: A PRISMA review. Water, 18(3), 369.
Bonafilia, D., Tellman, B., Anderson, T., & Issenberg, E.(2020). Sen1Floods11: A georeferenced datasetto train and test deep learning flood algorithmsfor Sentinel-1. Proceedings of the IEEE/CVFConference on Computer Vision and PatternRecognition Workshops, 835–845.https://doi.org/10.1109/CVPRW50498.2020.00113
Copernicus Emergency Management Service. (2026). CEMS On-Demand Mapping: About the service. European Commission Joint Research Centre.
Dong, L., & Shan, J. (2013). A comprehensive review of earthquake-induced building damage detection with remote sensing techniques. ISPRS Journal of Photogrammetry and Remote Sensing, 84, 85–99.
Ghali, R., & Akhloufi, M. A. (2023a). Deep learning approaches for wildland fires remote sensing: Classification, detection, and segmentation. Remote Sensing, 15(7), 1821. https://doi.org/10.3390/rs15071821
Ghali, R., & Akhloufi, M. A. (2023b). Deep learning approaches for wildland fires using satellite remote sensing data: Detection, mapping, and prediction. Fire, 6(5), 192.https://doi.org/10.3390/fire6050192
Hänsch, R., Arndt, J., Lunga, D., Gibb, M., Pedelose, T., Boedihardjo, A. P., Petrie, D., & Bacastow, T. M.(2022). SpaceNet 8—The detection of floodedroads and buildings. Proceedings of theIEEE/CVF Conference on Computer Vision andPattern Recognition Workshops, 1471–1479.https://doi.org/10.1109/CVPRW56347.2022.00153
Li, H., Zhu, M., Li, F., & Skitmore, M. (2024). Solving flood problems with deep learning technology: Research status, strategies, and future directions. Sustainable Development, 32(6), 7011–7035. https://doi.org/10.1002/sd.3074
Li, Y., Fu, B., Yin, Y., Hu, X., Wang, W., Wang, W., Li, X., & Long, G. (2024). Review on the artificial intelligence-based methods in landslide detection and susceptibility assessment: Current progress and future directions. Intelligent Geoengineering, 1(1), 1–18. https://doi.org/10.1016/j.ige.2024.10.003
Ma, L., Liu, Y., Zhang, X., Ye, Y., Yin, G., & Johnson, B. A. (2019). Deep learning in remote sensing applications: A meta-analysis and review. ISPRS Journal of Photogrammetry and Remote Sensing, 152, 166–177. https://doi.org/10.1016/j.isprsjprs.2019.04.015
Saleh, A., Zulkifley, M. A., Harun, H. H., et al. (2024). Forest fire surveillance systems: A review of deep learning methods. Heliyon, 10(1), e23127. https://doi.org/10.1016/j.heliyon.2023.e23127
Sun, X., Wang, P., Lu, W., Zhu, Z., Lu, X., He, Q., Li, J., Rong, X., Yang, Z., Chang, H., He, Q., Yang, G., Wang, R., Lu, J., & Fu, K. (2023). RingMo: A remote sensing foundation model with masked image modeling. IEEE Transactions on Geoscience and Remote Sensing, 61, 1–22. https://doi.org/10.1109/TGRS.2022.3194732
Szwarcman, D., et al. (2025). Prithvi-EO-2.0: A versatile multitemporal foundation model for Earth observation applications. IEEE Transactions on Geoscience and Remote Sensing, 64, Article 4400120. https://doi.org/10.1109/TGRS.2025.3642610
United Nations Office for Disaster Risk Reduction. (2015). Sendai framework for disaster risk reduction 2015–2030. United Nations.
Zhang, C., et al. (2024). Geospatial foundation models for image analysis: Evaluating and enhancing NASA–IBM Prithvi’s domain adaptability. International Journal of Geographical Information Science, 39(9), 2096–2125. https://doi.org/10.1080/13658816.2024.2397441
Downloads
Published
Data Availability Statement
Data made available on resonable request to the corresponding author
Issue
Section
License
Copyright (c) 2026 NG Civil Engineering
This work is licensed under a Creative Commons Attribution 4.0 International License.
