Environmental Management Hazards

Environmental Management Hazards

Comparison of Visual and Object-Based Automated Methods for Floodplain Mapping: A Case Study of the Karganrud Watershed, Talesh

Document Type : Applied Article

Authors
Leila Ebrahimi Jamnani 1
Maryam Ilanloo 2
1 Department of Geography, Cha.C.Islamic Azad University, Chalous, Iran
2 Department of Geography, Mahs.C. Islamic Azad University, Mahshahr, Iran
10.22059/jhsci.2026.418153.948
Abstract
Objective: Accurate floodplain mapping using remote sensing data plays a vital role in crisis management, damage reduction, and effective planning for natural hazards. The present study was conducted to compare the performance of a visual threshold-based approach using the Normalized Difference Vegetation Index (NDVI) and an automated Object-Based Image Analysis (OBIA) approach for floodplain extraction in the Karganrud Watershed, Talesh County.
Methods: Sentinel-2 imagery acquired during the September 2020 flood event was used in this study. In the visual approach, floodplain areas were extracted through visual image interpretation and analysis of spectral indices. In the automated approach, the image was first segmented into homogeneous objects and then classified based on spectral, textural, geometric, and spatial features. To evaluate the results, 194 reference points, including 100 flood points and 94 non-flood points, were used, and the performance of the two methods was compared using evaluation metrics such as Overall Accuracy (OA) and the Kappa coefficient.
Results: The results showed that although the NDVI-based method successfully identified a large proportion of flood-affected areas, it overestimated the flood extent due to its reliance on a single spectral index. The extracted flood area was 540.81 km², with an Overall Accuracy of 49.5%, a Kappa coefficient of −0.041, a Precision of 50.5%, a Recall of 96.0%, and an F1-score of 66.2%. In contrast, the OBIA approach, by integrating spectral, textural, geometric, and spatial features, extracted a flood area of 240.26 km² and achieved an Overall Accuracy of 93.3%, a Kappa coefficient of 0.866, a Precision of 90.7%, a Recall of 97.0%, and an F1-score of 93.7%, demonstrating substantially better performance than the NDVI-based method.
Conclusion: Comparison of the results indicated that the OBIA approach, by reducing classification errors caused by spectral similarity, providing more accurate delineation of floodplains, and substantially improving the evaluation metrics, outperformed the visual NDVI-based approach in floodplain extraction. Therefore, the use of Object-Based Image Analysis combined with the Random Forest algorithm can be recommended as an effective approach for producing accurate flood maps and supporting flood risk management and damage reduction planning in similar watershed areas.
Keywords
Flood mapping
Object-Based Image Analysis (OBIA)
Visual interpretation method
Korganrud Watershed
Normalized Difference Vegetation Index (NDVI)
ابراهیمی، لیلا؛ و ایلانلو، مریم (1403). پهنه‌بندی وقوع سیلاب حوضۀ زهکشی شهرستانک با استفاده از مدل هیدرولوژیکی WMS و تلفیق GIS. مدیریت مخاطرات محیطی، 11(1)، 15–29. https://doi.org/10.22059/jhsci.2024.374472.824
حائری، ساناز؛ و مثنوی، محمدرضا (1402). تحلیل راهبردهای بهسازی اکولوژیک منظر رودخانۀ خشک شیراز در چارچوب توسعۀ پایدار شهری با تأکید بر مدیریت مخاطرات سیلاب. مدیریت مخاطرات طبیعی، 10(1)، 71–90. https://doi.org/10.22059/jhsci.2023.356409.771
حاجی‌کریمی، زهرا؛ شایان، سیاوش؛ و خوش‌رفتار، رضا (1399). ارزیابی تکتونیک فعال حوضۀ آبریز کرگانرود در دامنۀ شرقی تالش (بغروداغ) با استفاده از شاخص‌های ژئومورفیک. پژوهش‌های ژئومورفولوژیک، 9(1)، 217–236. https://doi.org/10.22034/gmpj.2020.109989
رحیم‌پور، توحید؛ رضائی‌مقدم، محمدحسین؛ حجازی، سیداسدالله؛ و خلیل‌ولی‌زاده، کامران (1402). تحلیل تغییرات فضایی حساسیت خطر وقوع سیل بر پایۀ نوعی مدل ترکیبی نوین (مطالعۀ موردی: حوضۀ آبریز الندچای، شهرستان خوی). مدیریت مخاطرات طبیعی، 8(4)، 371–393. https://doi.org/ 10.22059/jhsci.2022.335204.692
سلیمانی، بهناز؛ ایلانلو، مریم؛ و غروبی، مجید (1405). شبیه‌سازی و پهنه‌بندی پتانسیل سیلاب با تلفیق مدل‌های WMS و HEC-RAS (مطالعه موردی: شهرستان سوادکوه). اکوهیدرولوژی، 13(1)، 1220–1240. https://doi.org/10.22059/ije.2026.411871.1908
گنجی گوهری، فاطمه؛ نظری‌پور، حمید؛ پودینه، محمدرضا؛ حمیدیان‌پور، محسن؛ قائمی، علیرضا؛ و تیموری، رضا (1405). روش خودکار برای انتخاب رویدادهای سیلاب و شناسایی ویژگی‌های آن‌ها (مطالعۀ موردی: حوضۀ آبریز رودخانه کاجو، ایران). جغرافیا و مخاطرات محیطی، 15(2)، 1–26. https://doi.org/10.22067/geoeh.2026.97442.1642
محمدی، میرعلی؛ ابراهیم‌نژادیان، حمزه؛ عسگرخان‌مسکن، محسن؛ و وزیری، ونوس (1401). ارزیابی عملکرد مدل‌های یک‌بعدی و دوبعدی HEC-RAS در تعیین پهنۀ سیلابی رودخانه‌ها. علوم آب و خاک، 26(2)، 187–201. https://doi.org/10.47176/jwss.26.2.43941
Antzoulatos, G., Kouloglou, I.O., Bakratsas, M., Moumtzidou, A., Gialampoukidis, I., Karakostas, A., Lombardo, F., Fiorin, R., Norbiato, D., Ferri, M., Symeonidis, A., Vrochidis, S., & Kompatsiaris, I. (2022). Flood hazard and risk mapping by applying an explainable machine learning framework using satellite imagery and GIS data. Sustainability, 14(6), 3251. https://doi.org/10.3390/su14063251
Bayik, C., Abdikan, S., Ozbulak, G., Alasag, T., Aydemir, S., & Balik Sanli, F. (2018). Exploiting multi-temporal Sentinel-1 SAR data for flood extent mapping. International Archives of the Photogrammetry, Remote Sensing and Spatial Information Sciences, XLII-3/W4, 109–113. https://doi.org/10.5194/isprs-archives-XLII-3-W4-109-2018
Bonafilia, D., Tellman, B., Anderson, T., & Issenberg, E. (2020). Sen1Floods11: A georeferenced dataset to train and test deep learning flood algorithms for Sentinel-1. Proceedings of the IEEE/CVF Conference on Computer Vision and Pattern Recognition Workshops, 210–211.
Cao, H., Zhang, H., Wang, C., & Zhang, B. (2019). Operational flood detection using Sentinel-1 SAR data over large areas. Water, 11(4), 786. https://doi.org/10.3390/w11040786
Carreño Conde, F., & De Mata Muñoz, M. (2019). Flood monitoring based on the study of Sentinel-1 SAR images: The Ebro River case study. Water, 11(12), 2454. https://doi.org/10.3390/w11122454
Chakma, P., & Akter, A. (2021). Flood mapping in the coastal region of Bangladesh using Sentinel-1 SAR images: A case study of Super Cyclone Amphan. Journal of the Civil Engineering Forum, 7(3), 267–278. https://doi.org/10.22146/jcef.64497
Chen, S., Huang, W., Chen, Y., & Feng, M. (2021). An adaptive thresholding approach toward rapid flood coverage extraction from Sentinel-1 SAR imagery. Remote Sensing, 13(23), 4899. https://doi.org/10.3390/rs13234899
Colacicco, R., Refice, A., Nutricato, R., Bovenga, F., Caporusso, G., D'Addabbo, A., La Salandra, M., Lovergine, F. P., Nitti, D. O., & Capolongo, D. (2024). High-resolution flood monitoring based on advanced statistical modeling of Sentinel-1 multi-temporal stacks. Remote Sensing, 16(2), 294. https://doi.org/10.3390/rs16020294
Drakonakis, G. I., Tsagkatakis, G., Fotiadou, K., & Tsakalides, P. (2022). OmbriaNet—Supervised flood mapping via convolutional neural networks using multi-temporal Sentinel-1 and Sentinel-2 data fusion. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing, 15, 2341–2356. https://doi.org/10.1109/JSTARS.2022.3155559
Gašparović, M., & Klobučar, D. (2021). Mapping floods in lowland forest using Sentinel-1 and Sentinel-2 data and an object-based approach. Forests, 12(5), 553. https://doi.org/10.3390/f12050553
Halder, S., & Bose, S. (2024). Sustainable flood hazard mapping with GLOF: A Google Earth Engine approach. Natural Hazards Research. https://doi.org/10.1016/j.nhres.2024.01.002
Hao, C., Yunus, A. P., Subramanian, S. S., & Avtar, R. (2021). Basin-wide flood depth and exposure mapping from SAR images and machine learning models. Journal of Environmental Management, 297, 113367. https://doi.org/10.1016/j.jenvman.2021.113367
Hardy, A., Ettritch, G., Cross, D., Bunting, P., Liywalii, F., Sakala, J., Silumesii, A., Singini, D., Smith, M., Willis, T., & Thomas, C. J. (2019). Automatic detection of open and vegetated water bodies using Sentinel-1 to map African malaria vector mosquito breeding habitats. Remote Sensing, 11(5), 593. https://doi.org/10.3390/rs11050593
Huang, Z., Wu, W., Liu, H., Zhang, W., & Hu, J. (2021). Identifying dynamic changes in water surface using Sentinel-1 data based on genetic algorithm and machine learning techniques. Remote Sensing, 13(18), 3745. https://doi.org/10.3390/rs13183745
Jamali, A., Kumar Roy, S., Hashemi Beni, L., Pradhan, B., Li, J., & Ghamisi, P. (2024). Residual wave vision U-Net for flood mapping using dual polarization Sentinel-1 SAR imagery. International Journal of Applied Earth Observation and Geoinformation, 127, 103662. https://doi.org/10.1016/j.jag.2024.103662
Jiang, X., Liang, S., He, X., Ziegler, A. D., Lin, P., Pan, M., Wang, D., Zou, J., Hao, D., Mao, G., Zeng, Y., Yin, J., Feng, L., Miao, C., Wood, E. F., & Zeng, Z. (2021). Rapid and large-scale mapping of flood inundation via integrating spaceborne synthetic aperture radar imagery with unsupervised deep learning. ISPRS Journal of Photogrammetry and Remote Sensing, 178, 36–50. https://doi.org/10.1016/j.isprsjprs.2021.05.019
Markert, K. N., Markert, A. M., Mayer, T., Nauman, C., Haag, A., Poortinga, A., Bhandari, B., Thwal, N. S., Kunlamai, T., Chishtie, F., Kwant, M., Phongsapan, K., Clinton, N., Towashiraporn, P., & Saah, D. (2020). Comparing Sentinel-1 surface water mapping algorithms and radiometric terrain correction processing in Southeast Asia utilizing Google Earth Engine. Remote Sensing, 12(15), 2469. https://doi.org/10.3390/rs12152469
Moghimi, E., Glade, T., Al-Ansari, N., & Shahabi, H. (2025). Floods and new housing design theory to sustain and reduce hazards (A scientific strategy). Geofluids, 1–21. https://doi.org/10.1155/2025/1234567
Schumann, G. J.-P., & Moller, D. K. (2015). Microwave remote sensing of flood inundation. Physics and Chemistry of the Earth, Parts A/B/C, 83–84, 84–95. https://doi.org/10.1016/j.pce.2015.05.002
Shen, X., Wang, D., Mao, K., Anagnostou, E., & Hong, Y. (2019). Inundation extent mapping by synthetic aperture radar: A review. Remote Sensing, 11(7), 879. https://doi.org/10.3390/rs11070879
Toma, A., Șandric, I., & Mihai, B.-A. (2024). Flooded area detection and mapping from Sentinel-1 imagery: Complementary approaches and comparative performance evaluation. European Journal of Remote Sensing. https://doi.org/10.1080/22797254.2024.24140042
Tsyganskaya, V., Martinis, S., Marzahn, P., & Ludwig, R. (2018). Detection of temporary flooded vegetation using Sentinel-1 time series data. Remote Sensing, 10(8), 1286. https://doi.org/10.3390/rs10081286
Uddin, M., & Meyer, F. J. (2019). Operational flood mapping using multi-temporal Sentinel-1 SAR images: A case study from Bangladesh. Remote Sensing, 11(13), 1581. https://doi.org/10.3390/rs11131581
Wagner, W., Freeman, V., Cao, S., Matgen, P., Chini, M., Salamon, P., McCormick, N., Martinis, S., Bauer-Marschallinger, B., Navacchi, C., Schramm, M., Reimer, C., & Briese, C. (2020). Data processing architectures for monitoring floods using Sentinel-1. ISPRS Annals of the Photogrammetry, Remote Sensing and Spatial Information Sciences, V-3-2020, 641–648. https://doi.org/10.5194/isprs-annals-V-3-2020-641-2020
Zhang, M., Chen, F., Liang, D., Tian, B., & Yang, A. (2020). Use of Sentinel-1 GRD SAR images to delineate flood extent in Pakistan. Sustainability, 12(14), 5784. https://doi.org/10.3390/su12145784
Zhang, X., Weng Chan, N., Pan, B., Ge, X., & Yang, H. (2021). Mapping flood by the object-based method using backscattering coefficient and interferometric coherence of Sentinel-1 time series. Science of the Total Environment, 794, 148388. https://doi.org/10.1016/j.scitotenv.2021.148388
Environmental Management Hazards
Volume 13, Issue 2
Summer 2026
Pages 113-128