Journal of Korea Water Resources Association (한국수자원학회논문집)

Korea Water Resources Association (한국수자원학회)
권호 표지
DOI QR코드

DOI QR Code

Comparative study of flood detection methodologies using Sentinel-1 satellite imagery

Sentinel-1 위성 영상을 활용한 침수 탐지 기법 방법론 비교 연구

  • Lee, Sungwoo (Department of Global Smart City, Sungkyunkwan University) ;
  • Kim, Wanyub (Department of Global Smart City, Sungkyunkwan University) ;
  • Lee, Seulchan (Department of Water Resources, Sungkyunkwan University) ;
  • Jeong, Hagyu (Disaster Information Research Division, National Disaster Management Research Institute) ;
  • Park, Jongsoo (Disaster Information Research Division, National Disaster Management Research Institute) ;
  • Choi, Minha (Department of Water Resources, Sungkyunkwan University)
  • 이성우 (성균관대학교 글로벌스마트시티융합전공) ;
  • 김완엽 (성균관대학교 글로벌스마트시티융합전공) ;
  • 이슬찬 (성균관대학교 수자원학과) ;
  • 정하규 (국립재난안전연구원 재난정보연구실) ;
  • 박종수 (국립재난안전연구원 재난정보연구실) ;
  • 최민하 (성균관대학교 수자원학과)
  • Received : 2023.11.25
  • Accepted : 2024.03.06
  • Published : 2024.03.31
Download PDF
⟨ Previous Next ⟩

Abstract

The increasing atmospheric imbalance caused by climate change leads to an elevation in precipitation, resulting in a heightened frequency of flooding. Consequently, there is a growing need for technology to detect and monitor these occurrences, especially as the frequency of flooding events rises. To minimize flood damage, continuous monitoring is essential, and flood areas can be detected by the Synthetic Aperture Radar (SAR) imagery, which is not affected by climate conditions. The observed data undergoes a preprocessing step, utilizing a median filter to reduce noise. Classification techniques were employed to classify water bodies and non-water bodies, with the aim of evaluating the effectiveness of each method in flood detection. In this study, the Otsu method and Support Vector Machine (SVM) technique were utilized for the classification of water bodies and non-water bodies. The overall performance of the models was assessed using a Confusion Matrix. The suitability of flood detection was evaluated by comparing the Otsu method, an optimal threshold-based classifier, with SVM, a machine learning technique that minimizes misclassifications through training. The Otsu method demonstrated suitability in delineating boundaries between water and non-water bodies but exhibited a higher rate of misclassifications due to the influence of mixed substances. Conversely, the use of SVM resulted in a lower false positive rate and proved less sensitive to mixed substances. Consequently, SVM exhibited higher accuracy under conditions excluding flooding. While the Otsu method showed slightly higher accuracy in flood conditions compared to SVM, the difference in accuracy was less than 5% (Otsu: 0.93, SVM: 0.90). However, in pre-flooding and post-flooding conditions, the accuracy difference was more than 15%, indicating that SVM is more suitable for water body and flood detection (Otsu: 0.77, SVM: 0.92). Based on the findings of this study, it is anticipated that more accurate detection of water bodies and floods could contribute to minimizing flood-related damages and losses.

기후변화에 의해 발생하는 대기 불균형은 강우량의 증가로 이어지고, 침수 발생 빈도가 증가함에 따라 이를 탐지할 수 있는 기술의 필요성이 증가하고 있다. 침수 피해를 최소화하기 위해 지속적인 모니터링이 필요하며, 날씨의 영향을 받지 않는 합성개구레이더(Synthetic Aperture Radar, SAR) 영상을 활용하여 침수지역을 탐지하였다. 관측된 데이터는 median 필터를 통해 노이즈를 감소시키는 전처리 과정을 진행하였으며, 객체 탐지 기법을 통해 수체와 비수체를 분류하여 각 기법의 침수탐지 활용성을 평가하고자 하였다. 본 연구에서는 Otsu 기법과 SVM 기법을 통해 수체 및 침수 탐지를 수행하였으며, Confusion Matrix를 통해 전체적인 모델의 성능을 평가하였다. Otsu 기법은 수체와 비수체의 경계를 구분하는데 적합함을 보였으나, 혼합물의 영향을 받아 오탐지의 비율이 높게 나타났다. 반면, SVM 기법을 사용한 경우, 오탐지 비율이 낮고 혼합물에 의한 영향에 민감하지 않은 것으로 관측되었다. 이에 따라 침수 상태를 제외한 다른 조건에서 SVM 기법의 정확도가 높게 나타났다. Otsu 기법이 침수 조건에서 SVM 기법보다 다소 높은 정확도를 보였지만, 정확도의 차이가 5% 미만임을 확인할 수 있었다(Otsu: 0.93, SVM: 0.90). SVM 기법이 Otsu 기법보다 침수 전, 침수 후의 조건에서 정확도 차이가 최대 15% 이상 발생하여 수체 및 침수탐지에 더 적합하게 나타났다(Otsu: 0.77, SVM: 0.92). 이러한 결과는 SVM 기법이 수체 및 침수탐지에서 효과적으로 활용될 수 있음을 시사하며, 미래의 수재해 탐지 시스템에 적용될 때 유용한 정보를 제공할 수 있을 것으로 기대된다.

Keywords

Acknowledgement

본 연구는 행정안전부 국립재난안전연구원의 지원("다종위성기반 재난위험 추적형 위성정보 융합분석 기술개발", "NDMI-주요-2023-03-02")에 의해 수행되었습니다. 이 논문은 2022년도 정부(과학기술정보통신부)의 재원으로 한국연구재단의 지원을 받아 수행된 연구임(NRF-2022R1A2C2010266). 본 연구는 교육부 및 한국연구재단의 4단계 두뇌 한국21 사업(4단계 BK21 사업)으로 지원된 연구임. 이 논문은 국토교통부의 스마트시티 혁신인재육성사업으로 지원되었습니다.

References

  1. Bioresita, F., Puissant, A., Andre, S., and Malet, J.P. (2018). "A method for automatic and rapid mapping of water surfaces from sentinel-1 imagery." Remote Sensing, Vol. 10, No. 2, 217.
  2. Bourgeau-Chavez, L.L., Kasischke, E.S., Brunzell, S.M., Mudd, J.P., Smith, K.B., and Frick, A.L. (2001). "Analysis of spaceborne SAR data f or wetland mapping in Virginia riparian ecosystems." International Journal of Remote Sensing, Vol. 22, No. 18, pp. 3665-3687.
  3. Chung, J.H., Son, M.B., Lee, Y.G., and Kim S.J. (2021). "Estimation of soil moisture using Sentinel-1 SAR images and multiple linear regression model considering antecedent precipitations." Korean Journal of Remote Sensing, Vol. 37, No. 3, pp. 515-530. https://doi.org/10.7780/KJRS.2021.37.3.12
  4. Dong, X., Hu, C., and Zhao, Y. (2023). "Novel threshold self-regulating water extraction method." Journal of Hydrologic Engineering, Vol. 28, No. 8. doi: 10.1061/JHYEFF.HEENG-5891
  5. Huang, W., DeVries, B., Huang, C., Lang, M.W., Jones, J.W., Creed, I.F., and Carroll, M.L. (2018). "Automated extraction of surface water extent from Sentinel-1 data." Remote Sensing, Vol. 10, No. 5, 797.
  6. Jiang, H., Feng, M., Zhu, Y., Lu, N., Huang, J., and Xiao, T. (2014). "An automated method for extracting rivers and lakes from Landsat imagery." Remote Sensing, Vol. 6, No. 6, pp. 5067-5089.
  7. Kim, W.Y., Jeong, J.W., and Choi, M.H. (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.
  8. Lee, S.C., Jeong, J.W., Oh, S.C., Jeong, H.G., and Choi, M.H. (2022). "Multi-resolution SAR image-based agricultural reservoir monitoring." Korean Journal of Remote Sensing, Vol. 38, No. 5, pp. 497-510.
  9. Li, Z.X., and Kim, S.W. (2006). "A Multi-thresholding approach improved with Otsu's Method." The Institute of Electroncis and Information Engineers-CI, Vol. 43, No .5, pp. 29-37.
  10. Martinis, S., Groth, S., Wieland, M., Knopp, L., and Rattich, M. (2022). "Towards a global seasonal and permanent reference water product from Sentinel-1/2 data for improved flood mapping." Remote Sensing of Environment, Vol. 278, 113077.
  11. 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.
  12. Moharrami, M., Javanbakht, M., and Attarchi S. (2021). "Automatic flood detection using Sentinel-1 images on the google earth engine." Environmental Monitoring and Assessment, Vol. 193, No. 248, pp. 1-17.
  13. Mountrakis, G., Im, J., and Ogole, C. (2011). "Support vector machines in remote sensing: A review." ISPRS Journal of Photogrammetry and Remote Sensing, Vol. 66, No. 3, pp. 247-259.
  14. Namikawa, L., Korting, T.S., and Castejon, E.F. (2016). "Water body extraction from Rapideye images: An automated methodology based on hue component of color transformation from RGB to HSV model." Revista Brasileira de Cartografia, Vol. 68, No. 6, pp. 1097-1111.
  15. Otsu, N. (1979). "A threshold selection method from gray level histograms." IEEE Transactions on Systems, Man, and Cybernetics, Vol. 9, pp. 62-66.
  16. Pham-Duc, B., Prigent, C., and Aires, F. (2017). "Surface water monitoring within Cambodia and the Vietnamese Mekong Delta over a year, with Sentinel-1 SAR observations." Water, Vol. 9, No. 6, 366.
  17. Possa, M.E., and Maillard, P. (2018). "Precise delineation of small water bodies from Sentinel-1 data using support vector machine classification." Canadian Journal of Remote Sensing, Vol. 44, No. 3, pp. 179-190.
  18. Pulvirenti, L., Squicciarino, G., Fiori, E., Ferraris, L., and Puca, S. (2021). "A tool for pre-operational daily mapping of floods and permanent water using Sentinel-1 data." Remote Sensing, Vol. 13, No. 7, 1342.
  19. Qing, S., Cui, T., Lai, Q., Bao, Y., Diao, R., Yue, Y., and Hao, Y. (2021). "Improving remote sensing retrieval of water clarity in complex coastal and inland waters with modified absorption estimation and optical water classification using Sentinel-2 MSI." International Journal of Applied Earth Observation and Geoinformation, Vol. 102, 102377.
  20. Qiu, F., Berglund, J., Jensen, J.R., Thakkar, P., and Ren, D. (2004). "Speckle noise reduction in SAR imagery using a local adaptive median filter." GIScience & Remote Sensing, Vol. 41, No. 3, pp. 244-266.
  21. Rana, V.K., and Suryanarayana, T.M.V. (2019). "Evaluation of SAR speckle filter technique for inundation mapping." Remote Sensing Applications: Society and Environment, Vol. 16, 100271.
  22. Ruzza, G., Guerriero, L., Grelle, G., Guadagno, F.M., and Revellion, P. (2019). "Multi-method tracking of monsoon floods using Sentinel-1 imagery." Water, Vol. 11, No. 11, 2289.
  23. Sharifzadeh, S., and Sanchayeeta A. (2020). "A support vector machine-based water detection analysis in a heterogeneous landscape using Landsat TM imagery." The California Geographer, Vol. 59, pp. 1-22.
  24. Shen, G., Fu, W., Guo, H., and Liao, J. (2022). "Water body mapping using long time series Sentinel-1 SAR data in Poyang Lake." Water, Vol. 14 No. 12, 1902.
  25. Soria-Ruiz, J., Fernandez-Ordonez, Y.M, Ambrosio-Ambrosio, J.P., Escalona-Maurice, M.J., Medina-Garcia, G.M., Sotelo-Ruiz, E.D., and Ramirez-Guzman, M.E. (2022). "Flooded extent and depth analysis using optical and SAR remote sensing with machine learning algorithms." Atmosphere, Vol. 13, No. 11, 1852.
  26. Tabari, H. (2020). "Climate change impact on flood and extreme precipitation increases with water availability." Scientific Reports, Vol. 10, No. 1, 13768.
  27. Tavus, B.T., Kocaman, S., Gokceoglu, C., Nefeslioglu, H.A. (2018). "Considerations on the use of Sentinel-1 data in flood mapping in urban areas: Ankara (Turkey) 2018 floods." The International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, Vol. 42, pp. 575-581.
  28. Tran, K.H., Menenti, M., and Jia, L. (2022). "Surface water mapping and flood monitoring in the Mekong Delta using Sentinel-1 SAR time series and Otsu Threshold." Remote Sensing, Vol. 14, No. 22, 5721.
  29. 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.
  30. Yang, X., Qin, Q., Grussenmeyer, P., and Koehl, M. (2018). "Urban surface water body detection with suppressed built-up noise based on water indices from Sentinel-2 MSI imagery." Remote Sensing of Environment, Vol. 219, pp. 259-270.
  31. Ye, C.S. (2016). "Water body extraction using block-based image partitioning and extension of water body boundaries." Korean Journal of Remote Sensing, Vol. 32, No. 5, pp. 471-482.
  32. Yuan, J., Chi, Z., Cheng, X., Zhang, T., Li, T., and Chen, Z. (2020). "Automatic extraction of supraglacial lakes in southwest greenland during the 2014-2018 melt seasons based on convolutional neural network." Water, Vol. 12 No. 3, 891.