River monitoring using Sentinel-2 imagery and deep learning-based object detection models

Shinhyeon Cho; Wanyub Kim; Minha Choi

doi:10.3741/JKWRA.2025.58.12.1365

All Issue

2025 Vol.58, Issue 12 Preview Page Next Page

Research Article

River monitoring using Sentinel-2 imagery and deep learning-based object detection models Sentinel-2 영상과 딥러닝 기반 객체 탐지 모델을 활용한 하천 모니터링

31 December 2025. pp. 1365-1377

PDF XML

Abstract

Efficient water system monitoring is an essential element for securing stable water resources and preventing water-related disasters. The significance of monitoring has increased in the context of rising frequencies of droughts and floods, a phenomenon attributable to recent climate change. Satellite remote sensing, in particular, has become a core tool in water resource management due to its ability to enable periodic detection across a wide spatial range. Accordingly, the present study was conducted with the objective of detecting water bodies, with a focus on domestic rivers. The study employed Sentinel-2 satellite imagery with a resolution of 10 meters and the Swin-Transformer model. The objective of the study was to identify alterations resulting from watershed monitoring and to assess the model's applicability. Initially, a comparative analysis was conducted among the classical water body detection techniques Otsu, Kittler-Illingworth (KI), and the Convolutional Neural Network (CNN)-based models U-net and High-Resolution Network (HRNet). These techniques were evaluated against a set of manually digitized and labeled images. The Swin-Transformer model demonstrated optimal performance, achieving an accuracy of 0.99, an Intersection over Union (IoU) of 0.88, and an F1-score of 0.87. Furthermore, the Swin- Transformer model, when employed for the purpose of evaluating the performance of watercourse change detection, demonstrated a high degree of efficacy, as evidenced by the high values obtained when evaluating the model's performance against labeled images. The model demonstrated an accuracy of 0.99, an IoU of 0.83, and an F1-score of 0.90. While changes in broad watercourse areas can be detected with high accuracy, limitations existed in detecting water bodies at the boundary edges of sandbars within thin tributaries and watercourse areas with complex structures. The Swin-Transformer model is expected to enable stable monitoring of water systems across diverse terrains, even in medium-to-low resolution satellite imagery. It is anticipated that the utilization of this technology will be effective in detecting changes in water systems and in disaster response.

Keywords

Swin-Transformer

Water body detection

Sentinel-2

River monitoring

Change detection

효율적인 수계 모니터링은 안정적인 수자원 확보와 수재해 예방을 위해 필수적인 요소이며, 최근 기후변화로 인한 가뭄 및 홍수 발생의 빈도가 증가함에 따라 모니터링의 중요성이 증대된다. 특히, 위성 원격 탐사는 넓은 공간적 범위를 주기적으로 탐지가 가능한 장점으로 인해 수자원 관리 분야에서 핵심적인 도구로 자리 잡고 있다. 이에 따라 본 연구에서는 10 m급 해상도를 지닌 Sentinel-2 위성 영상과 Swin-Transformer모델을 활용하여 국내 하천을 대상으로 수체 탐지를 진행하였으며, 수계의 모니터링으로 인한 변화 탐지 및 모델의 활용성을 평가하고자 하였다. 우선, 수체 탐지의 고전 기법인 Otsu, Kittler-Illingworth (KI) 와 Convolutional Neural Network (CNN) 기반의 U-net, High-Resolution Network (HRNet) 모델과 Tranformer 기반의 Swin-Transformer 모델을 수작업으로 디지타이징한 레이블 영상과 비교 및 검증한 결과, Swin-Transformer 모델에서 Accuracy 0.99, Intersection over Union (IoU) 0.88, F1-score 0.87로 가장 우수한 결과가 도출되었다. 추가적으로 Swin-Transformer 모델을 활용한 수계 변화탐지 성능을 레이블 영상과 비교하여 평가한 결과, Accuracy 0.99, IoU 0.83, F1-score 0.90으로 높은 수치가 도출되었다. 넓은 수계 영역에서의 변화는 높은 정확도로 탐지가 가능하지만, 얇은 지류 및 복잡한 구조를 지는 수계영역에서는 모래톱의 경계 가장자리 부분에서의 수체 탐지의 한계점이 존재하였다. 향후 Swin-Transformer 모델을 기반 수체 탐지는 중·저해상도 위성 영상에서도 다양한 지형에서의 수계 모니터링을 안정적으로 탐지할 수 있으며, 수계 변화탐지 및 재해 대응에 효과적으로 활용될 수 있을 것으로 기대된다.

키워드

Swin-Transformer

수체 탐지

Sentinel-2

하천 모니터링

변화 탐지

References

Choi, S., Youn, Y., Kang, J., Park, G., Kim, G., Lee, S., Choi, M., Jeong, H., and Lee, Y. (2022). “An artificial intelligence approach to waterbody detection of the agricultural reservoirs in South Korea using Sentinel-1 SAR images.” Korean Journal of Remote Sensing, Vol. 38, No. 5_3, pp. 925-938. doi: 10.7780/kjrs.2022.38.5.3.10.

10.7780/kjrs.2022.38.5.3.10

Cordeiro, M.C.R., Martinez, J.-M., and Peña-Luque, S. (2021). “Automatic water detection from multidimensional hierarchical clustering for Sentinel-2 images and a comparison with Level 2A processors.” Remote Sensing of Environment, Vol. 253, 112209. doi: 10.1016/j.rse.2020.112209.

10.1016/j.rse.2020.112209

Du, Y., Zhang, Y., Ling, F., Wang, Q., Li, W., and Li, X. (2016). “Water bodies’ mapping from Sentinel-2 imagery with modified normalized difference water index at 10-m spatial resolution produced by sharpening the swir band.” Remote Sensing, Vol. 8, No. 4, 354. doi: 10.3390/rs8040354.

10.3390/rs8040354

Feng, W., Sui, H., Huang, W., Xu, C., and An, K. (2018). “Water body extraction from very high-resolution remote sensing imagery using deep U-Net and a superpixel-based conditional random field model.” IEEE Geoscience and Remote Sensing Letters, Vol. 16, No. 4, pp. 618-622. doi: 10.1109/LGRS.2018.2879492.

10.1109/LGRS.2018.2879492

Han, K., Xiao, A., Wu, E., Guo, J., Xu, C., and Wang, Y. (2021). “Transformer in transformer.” Advances in Neural Information Processing Systems, Vol. 34, pp. 15908-15919.

Jeong, J., Oh, S., Lee, S., Kim, J., and Choi, M. (2021). “Sentinel-1 SAR image-based waterbody detection technique for estimating the water storage in agricultural reservoirs.” Journal of Korea Water Resources Association, Vol. 54, No. 7, pp. 535-544. doi: 10.3741/JKWRA.2021.54.7.535.

10.3741/JKWRA.2021.54.7.535

Kang, J., Guan, H., Ma, L., Wang, L., Xu, Z., and Li, J. (2023). “WaterFormer: A coupled transformer and CNN network for waterbody detection in optical remotely-sensed imagery.” ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 206, pp. 222-241. doi: 10.1016/j.isprsjprs.2023.11.006.

10.1016/j.isprsjprs.2023.11.006

Kavats, O., Khramov, D., and Sergieieva, K. (2022). “Surface water mapping from SAR images using optimal threshold selection method and reference water mask.” Water, Vol. 14, No. 24, 4030. doi: 10.3390/w14244030.

10.3390/w14244030

Khandelwal, A., Karpatne, A., Marlier, M.E., Kim, J., Lettenmaier, D.P., and Kumar, V. (2017). “An approach for global monitoring of surface water extent variations in reservoirs using MODIS data.” Remote Sensing of Environment, Vol. 202, pp. 113-128. doi: 10.1016/j.rse.2017.05.039.

10.1016/j.rse.2017.05.039

Kim, W., Jeong, J., and Choi, M. (2022). “Evaluation of reservoir monitoring-based hydrological drought index using Sentinel-1 SAR waterbody detection technique.” Korean Journal of Remote Sensing, Vol. 38, No. 2, pp. 153-166. doi: 10.7780/kjrs.2022.38.2.2.

10.7780/kjrs.2022.38.2.2

Kim, W., Lee, S., and Choi, M. (2024). “A comparative study of remotely sensed reservoir monitoring across multiple land cover types.” Science of the Total Environment, Vol. 948, 174678. doi: 10.1016/j.scitotenv.2024.174678.

10.1016/j.scitotenv.2024.174678

Kittler, J., and Illingworth, J. (1986). “Minimum error thresholding.” Pattern Recognition, Vol. 19, No. 1, pp. 41-47.

10.1016/0031-3203(86)90030-0

Lee, S., Jeong, J., Oh, S., Jeong, H., and Choi, M. (2022). “Multi-resolution SAR image-based agricultural reservoir monitoring.” Korean Journal of Remote Sensing, Vol. 38, No. 5_1, pp. 497-510. doi: 10.7780/kjrs.2022.38.5.1.5.

10.7780/kjrs.2022.38.5.1.5

Lee, S., Kim, W., Cho, S., Jeon, H., and Choi, M. (2023). “Water resources monitoring technique using multi-source satellite image data fusion.” Journal of Korea Water Resources Association, Vol. 56, No. 8, pp. 497-508. doi: 10.3741/JKWRA.2023.56.8.497.

10.3741/JKWRA.2023.56.8.497

Liu, Z., Lin, Y., Cao, Y., Hu, H., Wei, Y., Zhang, Z., Lin, S., and Guo, B. (2021). “Swin transformer: Hierarchical vision transformer using shifted windows.” In Proceedings of the IEEE/CVF International Conference on Computer Vision, Montreal, Canada, pp. 10012-10022.

10.1109/ICCV48922.2021.00986

McFeeters, S.K. (1996). “The use of the Normalized Difference Water Index (NDWI) in the delineation of open water features.” International Journal of Remote Sensing, Vol. 17, No. 7, pp. 1425-1432. doi: 10.1080/01431169608948714.

10.1080/01431169608948714

Otsu, N. (1975). “A threshold selection method from gray-level histograms.” Automatica, Vol. 11, No. 285-296, pp. 23-27.

Qin, P., Cai, Y., and Wang, X. (2021). “Small waterbody extraction with improved U-Net using Zhuhai-1 hyperspectral remote sensing images.” IEEE Geoscience and Remote Sensing Letters, Vol. 19, 5502705. doi: 10.1109/LGRS.2020.3047918.

10.1109/LGRS.2020.3047918

Russo, L., Mauro, F., Memar, B., Sebastianelli, A., Gamba, P., and Ullo, S. (2024). “Using multi-temporal Sentinel-1 and Sentinel-2 data for water bodies mapping.” IGARSS 2024-2024 IEEE International Geoscience and Remote Sensing Symposium, Athens, Greece, pp. 1922-1926. doi: 10.1109/IGARSS53475.2024.10641660.

10.1109/IGARSS53475.2024.10641660

Singh, S., and Kansal, M.L. (2022). “Chamoli flash-flood mapping and evaluation with a supervised classifier and NDWI thresholding using Sentinel-2 optical data in Google earth engine.” Earth Science Informatics, Vol. 15, pp. 1073-1086. doi: 10.1007/s12145-022-00786-8.

10.1007/s12145-022-00786-8

Valman, S.J., Boyd, D.S., Carbonneau, P.E., Johnson, M.F., and Dugdale, S.J. (2024) “An AI approach to operationalise global daily PlanetScope satellite imagery for river water masking.” Remote Sensing of Environment, Vol. 301, 113932. doi: 10.1016/j.rse.2023.113932.

10.1016/j.rse.2023.113932

Wang, J., Ding, J., Li, G., Liang, J., Yu, D., Aishan, T., Zhang, F., Yang, J., Abulimiti, A., and Liu, J. (2019). “Dynamic detection of water surface area of Ebinur Lake using multi-source satellite data (Landsat and Sentinel-1A) and its responses to changing environment. Catena, Vol. 177, pp. 189-201. doi: 10.1016/j.catena.2019.02.020.

10.1016/j.catena.2019.02.020

Xu, Y., Lin, J., Zhao, J., and Zhu, X. (2021). “New method improves extraction accuracy of lake water bodies in Central Asia.” Journal of Hydrology, Vol. 603, 127180. doi: 10.1016/j.jhydrol.2021.127180.

10.1016/j.jhydrol.2021.127180

Yang, L., Driscol, J., Sarigai, S., Wu, Q., Lippitt, C., and Morgan, M. (2022). “Towards synoptic water monitoring systems: A review of AI methods for automating water body detection and water quality monitoring using remote sensing.” Sensors, Vol. 22, No. 6, 2416. doi: 10.3390/s22062416.

10.3390/s2206241635336587PMC8949619

Yu, Y., Huang, L., Lu, W., Guan, H., Ma, L., Jin, S., Yu, C., Zhang, Y., Tang, P., Liu, Z., Wang, W., and Li, J. (2022). “WaterHRNet: A multibranch hierarchical attentive network for water body extraction with remote sensing images.” International Journal of Applied Earth Observation and Geoinformation, Vol. 115, 103103. doi: 10.1016/j.jag.2022.103103.

10.1016/j.jag.2022.103103

Yuan, Q., Wu, L., Huang, Y., Guo, Z., and Li, N. (2023). “Water-body detection from spaceborne SAR images with DBO-CNN.” IEEE Geoscience and Remote Sensing Letters, Vol. 20, 4013405. doi: 10.1109/LGRS.2023.3325939.

10.1109/LGRS.2023.3325939

Information

Publisher :KOREA WATER RESOURECES ASSOCIATION
Publisher(Ko) :한국수자원학회
Journal Title :Journal of Korea Water Resources Association
Journal Title(Ko) :한국수자원학회 논문집
Volume : 58
No :12
Pages :1365-1377
Received Date : 2025-06-24
Revised Date : 2025-11-10
Accepted Date : 2025-11-14
DOI :https://doi.org/10.3741/JKWRA.2025.58.12.1365

Journal of Korea Water Resources Association ISSN:2799-8746(Print) 2799-8754(Online) 한국수자원학회 논문집

All Issue