U-Net-based flood segmentation using eentinel-1 SAR imagery in Zimbabwe

Flooding is a devastating climate-induced hazard that has severe effects in Sub-Saharan Africa, resulting in significant human, economic, environmental, and losses. Climatic changes have increased the frequency of flood events in Zimbabwe, especially in regions with high rainfall, such as Chimanimani. This investigation introduces a semantic segmentation framework for the detection of flooding that is based on U-Net and employing Sentinel-1 Synthetic Aperture Radar (SAR) imagery. The proposed model enhances flood mapping under cloud-cover conditions through the use of all-weather and day-night imaging capabilities of SAR. Preprocessing procedures which were implemented to enhance model generalization and mitigate class imbalance include speckle noise reduction, image normalization as well as binary mask generation. The model was evaluated and trained using benchmark flood datasets that included Sentinel-1 SAR imagery. The experimental results showed that the segmentation performance was exceptionally good, with an overall precision of 95%, F1-score of 0.88 and recall of 0.82 for flooded regions. Further, the intersection over Union (IoU) analysis confirmed the accurate delineation of floods at pixel level. The results prove the practicality of convolutional neural network-based SAR flood segmentation techniques for real-time disaster monitoring in Zimbabwe and provide a reliable and flexible system for future implementation with real-time meteorological data as well as national early warning mechanisms.

Flood Segmentation, U-Net, Sentinel-1 SAR, Deep Learning, Semantic Segmentation

1. Amit, S. N. K. B., & Aoki, Y. (2017). Disaster detection from aerial imagery with convolutional neural network. Proceedings - International Electronics Symposium on Knowledge Creation and Intelligent Computing, IES-KCIC 2017, 2017-January. https://doi.org/10.1109/KCIC.2017.8228593 [Google Scholar] [Crossref]

2. Chanza, N., Siyongwana, P. Q., Williams-Bruinders, L., Gundu-Jakarasi, V., Mudavanhu, C., Sithole, V. B., & Manyani, A. (2020). Closing the Gaps in Disaster Management and Response: Drawing on Local Experiences with Cyclone Idai in Chimanimani, Zimbabwe. International Journal of Disaster Risk Science, 11(5). https://doi.org/10.1007/s13753-020-00290-x [Google Scholar] [Crossref]

3. Das, A., Abrar Rajin, S. M., Kah Ong Michael, G., Biswas, S., Billah, N., & Khan, R. (2025). Dual-Attention ResUNet With Masked Focal-Tversky Loss for Robust SAR-Based Flood Mapping. IEEE Access, 13, 201460–201477. https://doi.org/10.1109/ACCESS.2025.3637023 [Google Scholar] [Crossref]

4. Dube, E., Mtapuri, O., & Matunhu, J. (2018). Jàmbá-Journal of Disaster Risk Studies. https://doi.org/10.4102/jamba [Google Scholar] [Crossref]

5. Edwing, D., Meng, L., Lv, S., & Yan, X. H. (2025). Characterizing Storm-Induced Coastal Flooding Using SAR Imagery and Deep Learning. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 18, 5619–5632. https://doi.org/10.1109/JSTARS.2025.3530255 [Google Scholar] [Crossref]

6. Homepage, J., Hidayat, M. A., Latifah Husni, N., & Damsi, F. (2022). Image Processing Based Flood Detector Using Convolutional Neural Network (CNN) Within Surveillance Camera Pendeteksi Banjir dengan Image Processing Berbasis Convolutional Neural Network (. MALCOM: Indonesian Journal of Machine Learning and Computer Science, 2(October). [Google Scholar] [Crossref]

7. Huang, B., Li, P., Lu, H., Yin, J., Li, Z., & Wang, H. (2024). WaterDetectionNet: A New Deep Learning Method for Flood Mapping With SAR Image Convolutional Neural Network. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 14471–14485. https://doi.org/10.1109/JSTARS.2024.3440995 [Google Scholar] [Crossref]

8. Miau, S., & Hung, W. H. (2020a). River flooding forecasting and anomaly detection based on deep learning. IEEE Access, 8. https://doi.org/10.1109/ACCESS.2020.3034875 [Google Scholar] [Crossref]

9. Miau, S., & Hung, W. H. (2020b). River flooding forecasting and anomaly detection based on deep learning. IEEE Access, 8, 198384–198402. https://doi.org/10.1109/ACCESS.2020.3034875 [Google Scholar] [Crossref]

10. Moghimi, A., Welzel, M., Celik, T., & Schlurmann, T. (2024). A Comparative Performance Analysis of Popular Deep Learning Models and Segment Anything Model (SAM) for River Water Segmentation in Close-Range Remote Sensing Imagery. IEEE Access, 12, 52067–52085. https://doi.org/10.1109/ACCESS.2024.3385425 [Google Scholar] [Crossref]

11. Munawar, H. S., Ullah, F., Qayyum, S., Khan, S. I., & Mojtahedi, M. (2021). Uavs in disaster management: Application of integrated aerial imagery and convolutional neural network for flood detection. Sustainability (Switzerland), 13(14). https://doi.org/10.3390/su13147547 [Google Scholar] [Crossref]

12. Munsaka, E., Mudavanhu, C., Sakala, L., Manjeru, P., & Matsvange, D. (2021). When Disaster Risk Management Systems Fail: The Case of Cyclone Idai in Chimanimani District, Zimbabwe. International Journal of Disaster Risk Science, 12(5). https://doi.org/10.1007/s13753-021-00370-6 [Google Scholar] [Crossref]

13. Ntajal, J., Lamptey, B. L., Mahamadou, I. B., & Nyarko, B. K. (2017). Flood disaster risk mapping in the Lower Mono River Basin in Togo, West Africa. International Journal of Disaster Risk Reduction, 23. https://doi.org/10.1016/j.ijdrr.2017.03.015 [Google Scholar] [Crossref]

14. Pally, R. J., & Samadi, S. (2022). Application of image processing and convolutional neural networks for flood image classification and semantic segmentation. Environmental Modelling and Software, 148. https://doi.org/10.1016/j.envsoft.2021.105285 [Google Scholar] [Crossref]

15. Pascaline, W., House, R., McClean, D., & Below, R. (2018). UNISDR and CRED report: Economic Losses, Poverty & Disasters (1998 - 2017). Unisdr - Cred, 6. [Google Scholar] [Crossref]

16. Pech-May, F., Aquino-Santos, R., Alvarez-Cardenas, O., Arandia, J. L., & Rios-Toledo, G. (2024). Segmentation and Visualization of Flooded Areas Through Sentinel-1 Images and U-Net. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 17, 8996–9008. https://doi.org/10.1109/JSTARS.2024.3387452 [Google Scholar] [Crossref]

17. Raspini, F., Bianchini, S., Ciampalini, A., Del Soldato, M., Solari, L., Novali, F., Del Conte, S., Rucci, A., Ferretti, A., & Casagli, N. (2018). Continuous, semi-automatic monitoring of ground deformation using Sentinel-1 satellites. Scientific Reports, 8(1). https://doi.org/10.1038/s41598-018-25369-w [Google Scholar] [Crossref]

18. Rathupetsane, E. M., & Kganyago, M. (2026). Geospatial analysis of flooding events using Sentinel-1 and Sentinel-2 data: a tale of two South African cities. Environmental Monitoring and Assessment, 198(5). https://doi.org/10.1007/s10661-026-15321-1 [Google Scholar] [Crossref]

19. Ray, S., Goronga, T., Chigiya, P. T., & Madzimbamuto, F. D. (2022). Climate change, disaster management and primary health care in Zimbabwe. African Journal of Primary Health Care and Family Medicine, 14(1). https://doi.org/10.4102/PHCFM.V14I1.3684 [Google Scholar] [Crossref]

20. Sharma, S. K., Misra, S. K., & Singh, J. B. (2020). The role of GIS-enabled mobile applications in disaster management: A case analysis of cyclone Gaja in India. International Journal of Information Management, 51. https://doi.org/10.1016/j.ijinfomgt.2019.10.015 [Google Scholar] [Crossref]

21. Stateczny, A., Praveena, H. D., Krishnappa, R. H., Chythanya, K. R., & Babysarojam, B. B. (2023). Optimized Deep Learning Model for Flood Detection Using Satellite Images. Remote Sensing, 15(20). https://doi.org/10.3390/rs15205037 [Google Scholar] [Crossref]

22. Thapa, A., Horanont, T., & Neupane, B. (2022). Parcel-Level Flood and Drought Detection for Insurance Using Sentinel-2A, Sentinel-1 SAR GRD and Mobile Images. Remote Sensing, 14(23). https://doi.org/10.3390/rs14236095 [Google Scholar] [Crossref]

23. Umar, N., & Gray, A. (2023). Flooding in Nigeria: a review of its occurrence and impacts and approaches to modelling flood data. International Journal of Environmental Studies, 80(3). https://doi.org/10.1080/00207233.2022.2081471 [Google Scholar] [Crossref]

24. Williamson, C., McCordic, C., & Doberstein, B. (2023). The compounding impacts of Cyclone Idai and their implications for urban inequality. International Journal of Disaster Risk Reduction, 86. https://doi.org/10.1016/j.ijdrr.2023.103526 [Google Scholar] [Crossref]

25. Windheuser, L., Karanjit, R., Pally, R., Samadi, S., & Hubig, N. C. (2023). An End-To-End Flood Stage Prediction System Using Deep Neural Networks. Earth and Space Science, 10(1). https://doi.org/10.1029/2022EA002385 [Google Scholar] [Crossref]

26. Wu, C., Yang, X., & Wang, J. (2019). Flood Detection in Sar Images Based on Multi-Depth Flood Detection Convolutional Neural Network. 2019 6th Asia-Pacific Conference on Synthetic Aperture Radar, APSAR 2019. https://doi.org/10.1109/APSAR46974.2019.9048485 [Google Scholar] [Crossref]

27. Zhao, J., Li, Y., Matgen, P., Pelich, R., Hostache, R., Wagner, W., & Chini, M. (2022). Urban-Aware U-Net for Large-Scale Urban Flood Mapping Using Multitemporal Sentinel-1 Intensity and Interferometric Coherence. IEEE Transactions on Geoscience and Remote Sensing, 60. https://doi.org/10.1109/TGRS.2022.3199036 [Google Scholar] [Crossref]

• AI -Driven Green Support System for Sustainability and Responsible Innovation
• A Critical Analysis of Artificial Intelligence and Service Delivery in South Africa: Exploring Opportunities and Obstacles
• Development of a Graduate Employability Dashboard for Community Colleges