Flood inundation mapping in mountainous basins remains challenging because of complex terrain, frequent cloud cover, and limited ground observations. This study reconstructs monsoon flood inundation in the Kabul River Basin (KRB) during 2015–2025 using Sentinel-1 Synthetic Aperture Radar (SAR) and a Random Forest (RF) machine-learning framework. A multi-feature dataset comprising pre- and post-flood VV and VH backscatter, polarization metrics, GLCM texture descriptors, and topographic variables was developed, while high-confidence pseudo-labels were used for event-specific RF classification. The results reveal substantial interannual variability in flood extent, with the largest inundation recorded in 2020 (1004 km2), followed by high flood extents in 2021 and 2022. Except for 2017, monsoon-related inundations were detected in every year, and the cumulative inundated area exceeded 4000 km2, with flooding predominantly concentrated in downstream lowland areas. The RF framework achieved overall accuracies of 0.86–0.93, Cohen’s Kappa values of 0.78–0.86, and an integrated ROC-AUC of 0.924. These findings demonstrate the utility of Sentinel-1 SAR and RF for consistent reconstruction of historical monsoon inundation in data-scarce mountainous basins and provide a temporally consistent flood inventory for hydrological analysis and subsequent flood-susceptibility assessment.
- Open Access
- Article
Decadal Reconstruction of Monsoon Flood Inundation in the Kabul River Basin Using Sentinel-1 SAR and Machine Learning
Author Information
Received: 29 Jun 2026 | Revised: 18 Aug 2026 | Accepted: 10 Sep 2026 | Published: 29 Sep 2026
Abstract
Keywords
Sentinel-1 SAR | machine learning | flood inundation mapping | monsoon floods | Kabul River Basin
References
- 1.
Rahman, Z.U.; Zhang, M.; Chen, F.; et al. Spatiotemporal dynamics of flood susceptibility under future precipitation variability, population growth, and land cover change. Int. J. Appl. Earth Obs. Geoinf. 2026, 147, 105193. https://doi.org/10.1016/j.jag.2026.105193.
- 2.
Sadhwani, K.; Eldho, T.I. Machine Learning-Driven Flood Hazard Assessment: Integrating SAR and Elevation Data for Inundation Mapping and Depth Estimation. Nat. Hazards 2026, 122, 177. https://doi.org/10.1007/s11069-025-07949-y.
- 3.
Rahman, Z.U.; Chen, F.; Zhang, M.; et al. Identification and mapping of multi-type flood hotspots using an ensemble technique in the transboundary of Kabul River Basin. J. Hydrol. Reg. Stud. 2025, 60, 102468. https://doi.org/10.1016/j.ejrh.2025.102468.
- 4.
Hussain, M.; Tayyab, M.; Ullah, K.; et al. Development of a new integrated flood resilience model using machine learning with GIS-based multi-criteria decision analysis. Urban Clim. 2023, 50, 101589. https://doi.org/10.1016/j.uclim.2023.101589.
- 5.
Rahman, Z.U.; Zhang, M.; Chen, F.; et al. Flood susceptibility mapping using supervised machine learning models: Insights into predictors’ significance and models’ performance. Geomat. Nat. Hazards Risk 2025, 16, 2516728. https://doi.org/10.1080/19475705.2025.2516728.
- 6.
Ullah, M.; Wang, C.; Ullah, S.; et al. Summer monsoon precipitation patterns and their relationship to flood probabilities across Pakistan. J. Hydrol. Reg. Stud. 2026, 65, 103485. https://doi.org/10.1016/j.ejrh.2026.103485.
- 7.
Gao, D.; Wang, W.; Yin, J.; et al. Validation of flood inundation modelling using multi-source SAR imagery. Water Res. 2026, 296, 125590. https://doi.org/10.1016/j.watres.2026.125590.
- 8.
Sharma, N.K.; Saharia, M. DeepSARFlood: Rapid and automated SAR-based flood inundation mapping using vision transformer-based deep ensembles with uncertainty estimates. Sci. Remote Sens. 2025, 11, 100203. https://doi.org/10.1016/j.srs.2025.100203.
- 9.
Li, Y.; Martinis, S.; Plank, S.; et al. An automatic change detection approach for rapid flood mapping in Sentinel-1 SAR data. Int. J. Appl. Earth Obs. Geoinf. 2018, 73, 123–135. https://doi.org/10.1016/j.jag.2018.05.023.
- 10.
Arora, M.; Sahoo, S.; Bhatt, C.M.; et al. Rapid flood inundation mapping and impact assessment using Sentinel-1 SAR data over Ghaggar River basin of Punjab, India. J. Earth Syst. Sci. 2023, 132, 183. https://doi.org/10.1007/s12040-023-02199-7.
- 11.
Halder, K.; Ghosh, A.; Srivastava, A.K.; et al. SAR-driven flood inventory and multi-factor ensemble susceptibility modelling using machine learning frameworks. Geomat. Nat. Hazards Risk 2024, 15, 2409202. https://doi.org/10.1080/19475705.2024.2409202.
- 12.
Tavus, B.; Kocaman, S. Flood Mapping in Mountainous Areas Using Sentinel-1 & 2 Data and GLCM Features. Int. Arch. Photogramm. Remote Sens. Spat. Inf. Sci. 2023, 48, 1575–1580. https://doi.org/10.5194/isprs-archives-xlviii-1-w2-2023-1575-2023.
- 13.
Jishnu, V.; Arora, M.; Singh, H.; et al. Flood Inundation Mapping Over Kerala Region During 2018 Flood—Based on Cloud Computing and Automatic Threshold Detection Approach. In Climate, Environment and Agricultural Development; Springer Nature: Singapore, 2024; pp. 145–165.
- 14.
Arora, M.; Setia, R.; Singh, R.; et al. Mapping of Flood Inundated Areas Using Earth Observation Data and Cloud Computing Platform. J. Atmos. Sol.-Terr. Phys. 2025, 274, 106567.
- 15.
Zhou, C.; Wu, W.; Ke, X.; et al. Assessment of flooding and drought disaster risk in Henan, China by a multiscale approach. Geomat. Nat. Hazards Risk 2025, 16, 2491474. https://doi.org/10.1080/19475705.2025.2491474.
- 16.
Misra, A.; White, K.; Nsutezo, S.F.; et al. Mapping Global Floods with 10 Years of Satellite Radar Data. Nat. Commun. 2025, 16, 5762.
- 17.
Breiman, L. Random Forests. Mach. Learn. 2001, 45, 5–32. https://doi.org/10.1023/a:1010933404324.
- 18.
Jiao, Z.; Zhang, Z.; Wu, L. SAR-based dynamic information retrieving of the Beijing-Tianjin-Hebei flood-inundation happened in July 2023, North China. Geomat. Nat. Hazards Risk 2024, 15, 2366361. https://doi.org/10.1080/19475705.2024.2366361.
- 19.
Irukumati, S.; Vittal, A.R.; Gurunarayan, S.L. Comparative analysis of classification techniques for flood mapping using Sentinel 1 SAR data. Environ. Earth Sci. 2025, 84, 398. https://doi.org/10.1007/s12665-025-12381-3.
- 20.
Subramonian, K.; Girisha, S.; Savitha, G.; et al. Ensemble Teacher Models for Semi-Supervised Semantic Segmentation of Flood Zones from Synthetic Aperture Radar Images. Multimed. Tools Appl. 2026, 85, 308. https://doi.org/10.1007/s11042-026-21500-6.
- 21.
Savitha, G.; Girisha, S.; Sughosh, P.; et al. Consistency Regularization for Semi-Supervised Semantic Segmentation of Flood Regions from SAR Images. IEEE Access 2025, 13, 9642–9653. https://doi.org/10.1109/access.2025.3526244.
- 22.
Lashkaripour, G.R.; Hussaini, S.A. Water Resource Management in Kabul River Basin, Eastern Afghanistan. Environ. 2008, 28, 253–260. https://doi.org/10.1007/s10669-007-9136-2.
- 23.
Khatiwada, K.R.; Pradhananga, S.; Nepal, S. Inferring the impacts of climate extreme in the Kabul River Basin. Reg. Environ. Chang. 2024, 24, 17. https://doi.org/10.1007/s10113-023-02167-3.
- 24.
Sayama, T.; Ozawa, G.; Kawakami, T.; et al. Rainfall–Runoff–Inundation Analysis of the 2010 Pakistan Flood in the Kabul River Basin. Hydrol. Sci. J. 2012, 57, 298–312. https://doi.org/10.1080/02626667.2011.644245.
- 25.
Ullah, W.; Wang, G.; Lou, D.; et al. Large-Scale Atmospheric Circulation Patterns Associated with Extreme Monsoon Precipitation in Pakistan during 1981–2018. Atmos. Res. 2021, 253, 105489. https://doi.org/10.1016/j.atmosres.2021.105489.
- 26.
Rahman, Z.U.; Ullah, W.; Bai, S.; et al. GIS-Based Flood Susceptibility Mapping Using Bivariate Statistical Model in Swat River Basin, Eastern Hindukush Region, Pakistan. Front. Environ. Sci. 2023, 11, 1178540. https://doi.org/10.3389/fenvs.2023.1178540.
- 27.
Moorthy, R.; Bibi, S. Water Security and Cross-Border Water Management in the Kabul River Basin. Sustainability 2023, 15, 792. https://doi.org/10.3390/su15010792.
- 28.
Ougahi, J.H.; Karim, S.; Mahmood, S.A. Application of the SWAT model to assess climate and land use/cover change impacts on water balance components of the Kabul River Basin, Afghanistan. J. Water Clim. Chang. 2022, 13, 3977–3999. https://doi.org/10.2166/wcc.2022.261.
- 29.
Shams, A.K.; Muhammad, N.S. Towards Sustainable Transboundary Water Cooperation between Afghanistan and Pakistan: A Case Study of Kabul River. Ain Shams Eng. J. 2023, 14, 101842. https://doi.org/10.1016/j.asej.2022.101842.
- 30.
Baig, S.; Hasson, S.U. Flood Inundation and Streamflow Changes in the Kabul River Basin under Climate Change. Sustainability 2023, 16, 116. https://doi.org/10.3390/su16010116.
- 31.
Hussain, M.; Ullah, K.; Tayyab, M.; et al. Data-driven multi-hazard susceptibility and community perceptions assessment using a mixed-methods approach. J. Environ. Manag. 2025, 388, 126009. https://doi.org/10.1016/j.jenvman.2025.126009.
- 32.
Hashmi, M.Z.U.R.; Masood, A.; Mushtaq, H.; et al. Exploring climate change impacts during first half of the 21st century on flow regime of the transboundary Kabul River in the Hindukush region. J. Water Clim. Chang. 2020, 11, 1521–1538. https://doi.org/10.2166/wcc.2019.094.
- 33.
Torres, R.; Snoeij, P.; Geudtner, D.; et al. GMES Sentinel-1 mission. Remote Sens. Environ. 2012, 120, 9–24. https://doi.org/10.1016/j.rse.2011.05.028.
- 34.
Pulvirenti, L.; Pierdicca, N.; Chini, M.; et al. An Algorithm for Operational Flood Mapping from Synthetic Aperture Radar (SAR) Data Using Fuzzy Logic. Nat. Hazards Earth Syst. Sci. 2011, 11, 529–540. https://doi.org/10.5194/nhess-11-529-2011.
- 35.
Martinis, S.; Kersten, J.; Twele, A. A Fully Automated TerraSAR-X Based Flood Service. ISPRS J. Photogramm. Remote Sens. 2015, 104, 203–212. https://doi.org/10.1016/j.isprsjprs.2014.07.014.
- 36.
Zhu, Z.; Zhang, Y. Flood disaster risk assessment based on random forest algorithm. Neural Comput. Appl. 2022, 34, 3443–3455. https://doi.org/10.1007/s00521-021-05757-6.
- 37.
Tayyab, M.; Zhang, J.; Hussain, M.; et al. GIS-Based Urban Flood Resilience Assessment Using Urban Flood Resilience Model: A Case Study of Peshawar City, Khyber Pakhtunkhwa, Pakistan. Remote Sens. 2021, 13, 1864. https://doi.org/10.3390/rs13101864.
- 38.
Mehmood, Z.; Rahman, G. Assessing Flood Inundation and its impacts Using Sentinel-1A SAR Data and the Sentinel Application Platform in the Indus River Basin. Ecol. Quest. 2026, 37, 1–33. https://doi.org/10.12775/eq.2026.027.
- 39.
Ghouri, A.Y.; ur Rehman, A.; Rasheed, F.; et al. Flood Mapping Using the Sentinel-1 SAR Dataset and Application of the Change Detection Approach Technique (CDAT) to the Google Earth Engine in Sindh Province, Pakistan. Ecol. Quest. 2024, 35, 149–159.
This work is licensed under a Creative Commons Attribution 4.0 International License.
Suite 4002 Level 4, 447 Collins Street, Melbourne, Victoria 3000, Australia
General Inquiries: info@sciltp.com