Archives
 
Year 2026
 
Vol 67, Issue 5, [10 - 2026]

Flood inundation detection using multi-temporal dual-polarization Sentinel-1 SAR imagery and Convolutional Neural Networks: A case study in Hue City, Vietnam

DOI:10.46326/JMES.2026.67(5).05

  • Affiliations:

    Institute of Construction Technology, Le Quy Don Technical University, Hanoi, Vietnam

  • *Corresponding:
    This email address is being protected from spambots. You need JavaScript enabled to view it.
  • Received: 22nd-Jan-2026
  • Revised: 27th-June-2026
  • Accepted: 17th-July-2026
  • Online: 1st-Oct-2026
Pages: 59 - 71
Views: 27
View onlineView online
Downloads: 1
Downdload PDF
★★★★★Rating: , Total rating: 0
  • ★
  • ★
  • ★
  • ★
  • ★
Yours rating

Abstract:

Flooding is one of the most destructive natural hazards, causing substantial impacts on socio-economic systems and the environment. Rapid and accurate delineation of flood extent plays a crucial role in disaster monitoring and decision-making processes. This study presents a deep learning framework based on Convolutional Neural Network (CNN) for flood inundation mapping in Hue City, Vietnam, using multi-temporal dual-polarization Sentinel-1 Synthetic Aperture Radar (SAR) imagery. The input dataset was constructed from pre-flood and post-flood Sentinel-1 acquisitions, including the VV and VH polarization bands. In addition, two change-detection bands (ΔVV and ΔVH) were generated to capture temporal variations in surface backscatter intensity between the two observation periods. These six bands were integrated and used as input features for the CNN model. The proposed CNN architecture was designed to exploit both spatial contextual information and radar backscatter characteristics through 5×5 pixel image patches, enabling effective discrimination between flooded and non-flooded areas. A total of 16,000 labeled samples representing flooded and non-flooded areas were used for model training and evaluation. The experimental results demonstrate that the CNN achieves a classification accuracy of 95.13% on the test dataset with a loss value of 0.1918. Independent validation using 1000 random reference points yielded an overall accuracy of 96,4% and a Kappa coefficient of 0.928. The results confirm the effectiveness and applicability of integrating multi-temporal Sentinel-1 SAR data with a CNN-based deep learning framework for flood inundation mapping. The proposed approach improves flood boundary delineation and provides an effective tool for rapid flood mapping, disaster response, and flood risk management.

How to Cite
Le, H.Minh, Le, H.Hong Vu and Nguyen, H.Vinh Tran 2026. Flood inundation detection using multi-temporal dual-polarization Sentinel-1 SAR imagery and Convolutional Neural Networks: A case study in Hue City, Vietnam (in Vietnamese). Journal of Mining and Earth Sciences. 67, 5 (Oct, 2026), 59-71. DOI:https://doi.org/10.46326/JMES.2026.67(5).05.
References

Alexandre, C., Johary, R., Catry, T., Mouquet, P., Révillion, C., Rakotondraompiana, S., Pennober, G. (2020). A sentinel-1 based processing chain for detection of cyclonic flood impacts. Remote sensing, 12(2), 252.

Cao, H., Zhang, H., Wang, C., Zhang, B. (2019). Operational flood detection using Sentinel-1 SAR data over large areas. Water, 11(4), 786.

DeVries, B., Huang, C., Armston, J., Huang, W., Jones, J. W., Lang, M. W. (2020). Rapid and robust monitoring of flood events using Sentinel-1 and Landsat data on the Google Earth Engine. Remote sensing of Environment, 240, 111664.

Disperati, L., Virdis, S. G. P. (2015). Assessment of land-use and land-cover changes from 1965 to 2014 in Tam Giang-Cau Hai Lagoon, central Vietnam. Applied Geography, 58, 48-64.

Ghosh, B., Garg, S., Motagh, M., Martinis, S. (2024). Automatic flood detection from Sentinel-1 data using a nested UNet model and a NASA benchmark dataset. PFG-Journal of Photogrammetry, Remote Sensing and Geoinformation Science, 92(1), 1-18.

Google Earth Engine (GEE). (2026). Copernicus Sentinel-1 GRD. https://developers.google. com/earth-engine/datasets/catalog/ COPERNICUS_S1_GRD?hl=vi

Ioffe, S., Szegedy, C. (2015). Batch normalization: Accelerating deep network training by reducing internal covariate shift. In International conference on machine learning, PMLR 37 (pp. 448-456).

Le Ngoc, H., Nguyen, H. S., Le Phuc, C. L., Nguyen, V. A., Tran, T. A. (2024). Flood mapping and impact assessment in agricultural land in Hoa Vang, Da Nang using remote sensing and Google Earth Engine. VNU Journal of Science: Earth and Environmental Sciences, 40(2), 77-92 (in Vietnamese).

Lin, M., Chen, Q., Yan, S. (2013). Network in network. arXiv preprint arXiv:1312.4400.

Martinis, S., Plank, S., Ćwik, K. (2018). The use of Sentinel-1 time-series data to improve flood monitoring in arid areas. Remote Sensing, 10(4), 583.

Phan, H. A., Van Le, T., Tran, T. A., and Nguyen, S. H. (2021). An environmental zoning for sustainable development in Thua Thien Hue Province, Vietnam. In Global Changes and Sustainable Development in Asian Emerging Market Economies Vol. 2: Proceedings of EDESUS 2019, 817-841.

Quốc hội. (2024). Nghị quyết về việc thành lập thành phố Huế trực thuộc trung ương (Nghị quyết số 175/2024/QH15).

Saleh, T., Weng, X., Holail, S., Hao, C., Xia, G. S. (2024). DAM-Net: Flood detection from SAR imagery using differential attention metric-based vision transformers. ISPRS Journal of Photogrammetry and Remote Sensing, 212, 440-453.

Srivastava, N., Hinton, G., Krizhevsky, A., Sutskever, I., Salakhutdinov, R. (2014). Dropout: A simple way to prevent neural networks from overfitting. The journal of machine learning research, 15(1), 1929-1958.

Tiwari, V., Kumar, V., Matin, M. A., Thapa, A., Ellenburg, W. L., Gupta, N., Thapa, S. (2020). Flood inundation mapping-Kerala 2018; Harnessing the power of SAR, automatic threshold detection method and Google Earth Engine. Plos one, 15(8), e0237324.

Trinh, L.H., Mai, D.S., Nguyen, N.H., Le, V.P., (2021). Automatic flood detection using Sentinel-1 images in Google Earth Engine. Journal of Science and Technique: Section on Special Construction Engineering, 4(2), 29-43.

Tuan, V. Q., Khai, D. H., Nhan, H. T. K., and Hoa, N. T. (2018). Developing a flood monitoring algorithm for the Mekong Delta region based on Google Earth Engine. Can Tho University Journal of Science, 54(9A), 29-36. (in Vietnamese).

Weather and Climate. (2026). Average monthly precipitation (rainfall) in Hue, Vietnam. https://weather-and-climate.com/average-monthly-precipitation-Rainfall,Hue,Vietnam

Zhao, J., Xiong, Z., Zhu, X. X. (2024). UrbanSARFloods: Sentinel-1 SLC-based benchmark dataset for urban and open-area flood mapping. In Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition (pp. 419-429).

Zhao, Z., Zhang, B., Wu, F., Yang, J. (2023, September). Deep Learning-Based Flood Detection Using Multi-Temporal Sentinel-1 SAR Data: A Case Study in Beijing Area, 2023. In 2023 SAR in Big Data Era (BIGSARDATA) (pp. 1-4). IEEE.

Other articles