Evaluating machine learning efficiency and accuracy for real time flash flood mapping
Abstract
Flash floods endanger communities and ecosystems in rugged regions, but precise prediction is difficult due to environmental complexity. This study evaluates six machine learning algorithms for flash flood mapping in Iran’s Dez Basin, a region growing more vulnerable to climate extremes. We developed an integrated geospatial database incorporating 32 climatic, anthropogenic, and physiographic parameters, validated through extensive field surveys documenting historical flood events. The dataset (70% training, 30% validation) was analyzed using: (1) H2O Deep Learning framework, (2) Random Forest (RF), and (3) four boosting methods (AdaBoost, XGBoost, LightGBM, CatBoost). The RF model achieved exceptional predictive performance (AUC = 0.89, accuracy = 95%), outperforming other techniques by 6–12% in classification metrics. Sensitivity analysis identified precipitation intensity (β = 0.34, p < 0.01), watershed area (β = 0.28), and slope gradient (β = 0.25) as statistically significant dominant controls.These findings advance flood risk management in three key ways: First, they demonstrate RF’s superiority in handling heterogeneous geospatial data. Second, the 30 m-resolution susceptibility map provides actionable insights for land-use planning. Third, the methodology offers a transferable framework for arid/semi-arid regions globally. We recommend policymakers prioritize slope stabilization and early-warning systems in high-risk zones (AUC > 0.85) to enhance community resilience.
Data availability
The data are available upon request from the corresponding author.
References
Holton, J. R., Pyle, J. A. & Curry, J. A. Encyclopedia of Atmospheric Sciences. Second Edition. (Academic Press, 2015).
Georgakakos, K. P. Analytical results for operational flash flood guidance. J. Hydrol. 317 (1–2), 81–103. https://doi.org/10.1016/j.jhydrol.2005.05.009 (2006).
Norbiato, D., Borga, M., Esposti, D., Gaume, S., Anquetin, E. & S Flash flood warning based on rainfall depth-duration thresholds and soil moisture conditions: an assessment for gauged and ungauged basins. J. Hydrol. 362 (3–4), 274–290. https://doi.org/10.1016/j.jhydrol.2008.08.023 (2008).
Costache, R. et al. Flash-flood hazard using deep learning based on H2O R package and fuzzy-multicriteria decision-making analysis. J. Hydrol. 609, 127747. https://doi.org/10.1016/j.jhydrol.2022.127747 (2022).
Youssef, A. M., Pradhan, B. & Sefry, S. A. Flash flood susceptibility assessment in Jeddah City (Kingdom of Saudi Arabia) using bivariate and multivariate statistical models. Environ. Earth Sci. 75 (1), 12. https://doi.org/10.1007/s12665-015-4830-8 (2016).
Habibi, A., Delavar, M. R., Sadeghian, M. S. & Nazari, B. Flood susceptibility mapping and assessment using regularized Random forest and naïve bayes algorithms. ISPRS Annals Photogrammetry Remote Sens. Spat. Inform. Sci., 10, 241–248. https://doi.org/10.5194/isprs-annals-X-4-W1-2022-241-2023 (2023).
Ren, H. et al. Flood susceptibility assessment with random sampling strategy in ensemble learning (RF and XGBoost). Remote Sens. 16 (2), 320. https://doi.org/10.3390/rs16020320 (2024).
SELLAMI, E. M. & Rhinane, H. Google Earth engine and machine learning for flash flood exposure Mapping—Case study: Tetouan, Morocco. Geosciences 14 (6), 152. https://doi.org/10.3390/geosciences14060152 (2024).
Elghouat, A. et al. Integrated approaches for flash flood susceptibility mapping: Spatial modeling and comparative analysis of statistical and machine learning models. A case study of the Rheraya watershed, Morocco. J. Water Clim. Change. 15 (8), 3624–3646. https://doi.org/10.2166/wcc.2024.726 (2024).
Al-Kindi, K. M. & Alabri, Z. Investigating the role of the key conditioning factors in flood susceptibility mapping through machine learning approaches. Earth Syst. Environ. 8 (1), 63–81. https://doi.org/10.1007/s41748-023-00369-7 (2024).
Wahba, M. et al. Forecasting of flash flood susceptibility mapping using Random forest regression model and geographic information systems. Heliyon https://doi.org/10.1016/j.heliyon.2024.e33982 (2024).
Rutledge, D. N. & Barros, A. S. Durbin–Watson statistic as a morphological estimator of information content. Anal. Chim. Acta. 454 (2), 277–295. https://doi.org/10.1016/S0003-2670(01)01555-0 (2002).
Salas, J. D. Analysis and modeling of hydrological time series. In: Maidment DR, editor. Handbook of hydrology. (McGraw-Hill, 1993).
Mohammadzadeh, A. & Massoudzadegan, S. Forecasting daily volatility and value at risk with high frequency data. Dev. Transformation Manage. Q. 8 (27), 63–74 (2015).
Choubin, B. et al. Regional groundwater potential analysis using classification and regression trees. In Spatial modeling in GIS and R for earth and environmental sciences. 485–498 https://doi.org/10.1016/B978-0-12-815226-3.00022-3 (2019).
Monfared, B., Najafabadi, M. & Nafarzadegan, A. R., Flood zoning and identification of effective factors in flood occurrence: A case study of the urban watershed of Bastak. Master’s thesis, Department of Desert Management and Control. (Hormozgan University, 2021).
Eisfelder, C. et al. Cropland and crop type classification with Sentinel-1 and Sentinel-2 time series using Google Earth engine for agricultural monitoring in Ethiopia. Remote Sens. 16 (5), 866. https://doi.org/10.3390/rs16050866 (2024).
Rasti, S., Mahdavifardnh, M., Shaykh Ghaderi, H., Nasiri, A. & Taktaz, N. Z. Improving classification accuracy by combining multi-season images of Sentinel 1 and 2 in order to prepare a landuse map in the cloud space of Google Earth engine (case study: Guilan province). Geogr. Hum. Relations. 5 (3), 357–373. https://doi.org/10.22034/gahr.2022.336692.1696 (2022).
Yoothong, K., Moncharoen, L., Vijarnson, P. & Eswaran, H. Clay mineralogy of Thai soils. Appl. Clay Sci. 11 (5–6), 357–371. https://doi.org/10.1016/S0169-1317(96)00033-6 (1997).
Kariuki, P. C., Woldai, T. & Van Der Meer, F. Effectiveness of spectroscopy in identification of swelling indicator clay minerals. Int. J. Remote Sens. 25 (2), 455–469. https://doi.org/10.1080/0143116031000084314 (2004).
Stenberg, B., Rossel, R. A. V., Mouazen, A. M. & Wetterlind, J. Visible and near infrared spectroscopy in soil science. Adv. Agron. 107, 163–215. https://doi.org/10.1016/S0065-2113(10)07005-7 (2010).
Danoedoro, P. & Zukhrufiyati, A. Integrating spectral indices and geostatistics based on Landsat-8 imagery for surface clay content mapping in Gunung Kidul area, Yogyakarta, Indonesia. In: Proceedings of the 36th Asian Conference on Remote Sensing; ; Asia Quezon, Metro Manila, Philippines. (2015).
Sabins, F. F. Remote sensing for mineral exploration. Ore Geol. Rev. 14, 157–183. https://doi.org/10.1016/S0169-1368(99)00007-4 (1999).
Khan, N. M., Rastoskuev, V. V., Sato, Y. & Shiozawa, S. Assessment of hydrosaline land degradation by using a simple approach of remote sensing indicators. Agric. Water Manag. 77, 96–109. https://doi.org/10.1016/j.agwat.2004.09.038 (2005).
Asfaw, E., Suryabhagavan, K. V. & Argaw, M. Soil salinity modeling and mapping using remote sensing and GIS: the case of Wonji sugar cane irrigation farm, Ethiopia. J. Saudi Soc. Agric. Sci. 17, 250–258. https://doi.org/10.1016/j.jssas.2016.05.003 (2018).
Caloz, R., Abednego, B. & Collet, C. The Normalisation of a Soil Brightness Index for the Study of Changes in Soil Conditions. In: Proceedings of the 4th International Colloquium on Spectral Signatures of Objects in Remote Sensing. 18–22 (1988).
Bousbih, S. et al. Soil texture Estimation using radar and optical data from Sentinel-1 and Sentinel-2. Remote Sens. 11 (13), 1520. https://doi.org/10.3390/rs11131520 (2019).
Parvaresh, A., Mahdavi, R., Melkian, A., Ismailpour, Y. & Halisaz, A. Prioritizing the flood potential of sub-watersheds in Sokhon. Hormozgan using fuzzy TOPSIS and ELECTRE methods. Doctoral dissertation in Watershed Sciences and Engineering. (Hormozgan University, 2018).
Moore, I. D. & Grayson, R. B. Landson. Digital terrain modeling: A review of hydrological, Geomorphological and biological application. Modelling Hydrology. 5, 3–30. https://doi.org/10.1002/hyp.3360050103 (1991).
Moore, I. D. & Burch, G. J. Sediment transport capacity of sheet and Rill flow: application of unit stream power theory. Water Resour. Res. 22 (8), 1350–1360. https://doi.org/10.1029/WR022i008p01350 (1986).
Nookaratnam, K., Srivastava, Y. K., Venkateswarao, V., Amminedu, E. & Murthy, K. S. R. Check dam positioning by prioritization of micro watersheds using SYI model and morphometric analysis remote sensing and GIS perspective. J. Indian Soc. Remote Sens. 33 (1), 25–28. https://doi.org/10.1007/BF02989988 (2005).
Schumn, S. A. Evolution of drainage basins and slopes in bund land of Peth Amboy, new Jersey. Bull. Geol. Soc. Am. 67, 597–646 (1956).
Horton, R. E. Erosional development of streams and their drainage basins; hydrophysical approach to quantitative morphology. Geol. Soc. Am. Bull. 56, 275–370. https://doi.org/10.1130/0016-7606%281945%2956%5B275%3AEDOSAT%5C2.0.CO%3B2 (1945).
Miller, V. C. A Quantitative Geomorphic Study of Drainage Basin Characteristics on the Clinch Mountain Area, Virgina and Tennessee, Proj. 389–402 (Columbia University, 1953).
Strahler, A. N. Quantitative analysis of watershed geomorphology. Eos Trans. Am. Geophys. Union. 38, 913–920 (1957).
Strahler, A. N. & Part, I. I. Quantitative geomorphology of drainage basins and channel networks. In Handbook of Applied Hydrology 4–39 (McGraw-Hill, 1964).
Schumm, S. A. Evolution of drainage systems and slopes in badlands at Perth Amboy, New Jersey. Geol. Soc. Am. Bull. 67, 597–646. https://doi.org/10.1130/0016-7606%281956%2967%5B597%3AEODSAS%5C2.0.CO%3B2 (1956).
LeCun, Y. & Yoshua, B. Deep learning. Nature 521(7553), 436–444. https://doi.org/10.1038/nature14539 (2015).
Schmidhuber, J. Deep Learning in Neural Network: An Overview. Neural Networks 61, 85–117. https://doi.org/10.1016/j.neunet.2014.09.003 (2015).
Choi, J. et al. An optimal boosting algorithm based on nonlinear conjugate gradient method. J. Korean Soc. Industr. Appl. Mathemat. 22(1), 1–13 (2018).
Divakar, K. & Chitharanjan, K. Performance evaluation of credit card fraud transactions using boosting algorithms. Int. J. Electron. Commun. Comput. Eng. IJECCE. 10 (6), 262–270 (2019).
Freund, Y. & Schapire, R. E. A decision-theoretic generalization of on-line learning and an application to boosting. J. Comput. Syst. Sci. 55 (1), 119–139. https://doi.org/10.1006/jcss.1997.1504 (1997).
Iban, M. C. & Bilgilioglu, S. S. Snow avalanche susceptibility mapping using novel tree-based machine learning algorithms (XGBoost, NGBoost, and LightGBM) with eXplainable artificial intelligence (XAI) approach. Stoch. Env. Res. Risk Assess. 37 (6), 2243–2270. https://doi.org/10.1007/s00477-023-02392-6 (2023).
Friedman, J. H. Greedy function approximation: a gradient boosting machine. Ann. Stat. https://doi.org/10.1214/aos/1013203451 (2001).
Du, J., Fang, J., Xu, W. & Shi, P. alysis of dry/wet conditions using the standardized precipitation index and its potential usefulness for drought/flood monitoring in Hunan Province, China. Stochastic Environ. Res. Risk Assess. 27, 377–387. https://doi.org/10.1007/s00477-012-0589-6 (2013).
Hajizadeh, H., Farhang, M. & Vafaie Sadr, A. Searching for cosmic strings in Planck data using image processing tools and machine learning. Master’s thesis in Physics. (Shahid Beheshti University, 2020).
Chen, T. & Guestrin, C. Xgboost: A scalable tree boosting system. In Proceedings of the 22nd acm sigkdd international conference on knowledge discovery and data mining. 785–794 https://doi.org/10.1145/2939672.2939785 (2016).
Brownlee, J. Imbalanced Classification with Python: Better metrics, Balance Skewed classes, cost-sensitive Learning. (Machine Learning Mastery, 2020).
Truong, V. H., Papazafeiropoulos, G., Vu, Q. V., Pham, V. T. & Kong, Z. Predicting the patch load resistance of stiffened plate girders using machine learning algorithms. Ocean Eng. 240, 109886. https://doi.org/10.1016/j.oceaneng.2021.109886 (2021).
Liang, Y. et al. Product marketing prediction based on XGboost and LightGBM algorithm, In: 2nd International Conference on Artificial Intelligence and Pattern Recognition. 150–153 https://doi.org/10.1145/3357254.3357290 (2019).
Ke, G. et al. Lightgbm: A highly efficient gradient boosting decision tree. Adv. Neural. Inf. Process. Syst., 30. (2017).
Dorogush, A. V., Ershov, V. & Gulin, A. CatBoost: gradient boosting with categorical features support. ArXiv Preprint. https://doi.org/10.48550/arXiv.1810.11363 (2018). arXiv:1810.11363.
Prokhorenkova, L., Gusev, G., Vorobev, A., Dorogush, A. V. & Gulin, A. CatBoost: unbiased boosting with categorical features. Adv. Neural. Inf. Process. Syst. 31. (2018).
Saber, M. et al. Enhancing flood risk assessment through integration of ensemble learning approaches and physical-based hydrological modeling. Geomatics Nat. Hazards Risk. 14 (1), 2203798. https://doi.org/10.1080/19475705.2023.2203798 (2023).
Mahdavi, M. Applied hydrology 8th edn, Vol. 2, 437 (Tehran University, 2013).
Talikhoshk, S., Mohseni Saravi, M., Vafakhah, M. & Khalighi Sigaroodi, S. Comparison of neuro-fuzzy and SCS methods in prioritizing sub-watersheds for watershed management actions: A case study of the Talghan watershed. Scientific-Research J. Rangel. Watershed Manage. 68 (2), 213–225. https://doi.org/10.22059/jrwm.2015.54922 (2015).
Hosseini, Y. Comparison of SCS unit hydrograph and uniform methods in estimating the maximum flood discharge of the Amoughin basin. Hydrogeomorphology 21 (6), 87–107 (2019).
Esfandiari, F., Pourganji, Z., Mostafazadeh, R. & Aghaei, M. Comparison of methods for converting effective precipitation to surface runoff in simulating flood hydrographs in the Naneh Karan basin, ardabil Province. Hydrogeomorphology 9 (32), 63–86. https://doi.org/10.22034/hyd.2022.50000.1624 (2022).
Soleimani, K., Shokrian, F., Abdoli, S. & Sabri, E. Prioritizing flood risk potential in the Talhar watershed using. Geographic Inform. Syst. Ecohydrology 8(3), 749–762. https://doi.org/10.22059/ije.2021.324244.1509 (2021).
Haghizadeh, A., Mohammadlou, M. & Noori, F. Simulation of rainfall-runoff processes using artificial neural networks, adaptive neuro-fuzzy systems, and multivariate regression: A case study of the Khorramabad watershed. Hydrogeomorphology 2 (2), 233–243. https://doi.org/10.22059/ije.2015.56243 (2015).
Zema, D. A., Parhizkar, M., Plaza-Alvarez, P. A., Xu, X. & Lucas-Borja, M. E. Using random forest and multiple-regression models to predict changes in surface runoff and soil erosion after prescribed fire. Model. Earth Syst. Environ. 10 (1), 1215–1228. https://doi.org/10.1007/s40808-023-01838-8 (2024).
Hasnaoui, Y. et al. Enhanced machine learning models development for flash flood mapping using Geospatial data. Euro-Mediterranean J. Environ. Integr. 9 (3), 1087–1107 (2024).
Xu, K., Han, Z., Xu, H. & Bin, L. Rapid prediction model for urban floods based on a light gradient boosting machine approach and Hydrological–Hydraulic model. Int. J. Disaster Risk Sci. 14 (1), 79–97. https://doi.org/10.1007/s13753-023-00465-2 (2023).
Hasnaoui, Y. et al. Integrated Remote Sensing and Deep Learning Models for Flash Flood Detection Based on Spatio-temporal Land Use and Cover Changes in the Mediterranean Region 1–23 (Environmental modeling & assessment, 2025).
Abedi, R., Costache, R., Shafizadeh-Moghadam, H. & Pham, Q. B. Flash-flood susceptibility mapping based on XGBoost, random forest and boosted regression trees. Geocarto Int. 37 (19), 5479–5496. https://doi.org/10.1080/10106049.2021.1920636 (2022).
Janizadeh, S., Vafakhah, M., Kapelan, Z. & Mobarghaee Dinan, N. Hybrid XGboost model with various bayesian hyperparameter optimization algorithms for flood hazard susceptibility modeling. Geocarto Int. 37 (25), 8273–8292. https://doi.org/10.1080/10106049.2021.1996641 (2022).
Vafakhah, M., Nasiri Khiavi, A., Janizadeh, S. & Ganjkhanlo, H. Evaluating different machine learning algorithms for snow water equivalent prediction. Earth Sci. Inf. 15 (4), 2431–2445. https://doi.org/10.1007/s12145-022-00846-z (2022).
Moharrami, M., Attarchi, S., Gloaguen, R. & Alavipanah, S. K. Integration of Sentinel-1 and Sentinel-2 data for ground truth sample migration for multi-temporal land cover mapping. Remote Sens. ; 16(9):1566. https://doi.org/10.3390/rs16091566 (2024).
Mullissa, A. et al. LUCA: A Sentinel-1 SAR-Based global forest landuse change alert. Remote Sens. 16 (12), 2151. https://doi.org/10.3390/rs16122151 (2024).
Author information
Authors and Affiliations
Contributions
AH, HM; Methodology: AH, HM; Formal analysis and investigation: AH, HM, MS; Writing—original draft preparation: AH, HM; Writing— review and editing: AH, HM, MS; Supervision: AH. All authors read and approved the final manuscript.
Corresponding author
Ethics declarations
Competing interests
The authors declare no competing interests.
Additional information
Publisher’s note
Springer Nature remains neutral with regard to jurisdictional claims in published maps and institutional affiliations.
Rights and permissions
Open Access This article is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License, which permits any non-commercial use, sharing, distribution and reproduction in any medium or format, as long as you give appropriate credit to the original author(s) and the source, provide a link to the Creative Commons licence, and indicate if you modified the licensed material. You do not have permission under this licence to share adapted material derived from this article or parts of it. The images or other third party material in this article are included in the article’s Creative Commons licence, unless indicated otherwise in a credit line to the material. If material is not included in the article’s Creative Commons licence and your intended use is not permitted by statutory regulation or exceeds the permitted use, you will need to obtain permission directly from the copyright holder. To view a copy of this licence, visit http://creativecommons.org/licenses/by-nc-nd/4.0/.
About this article
Cite this article
Mirzapour, H., Haghizadeh, A. & Motlagh, M.S. Evaluating machine learning efficiency and accuracy for real time flash flood mapping. Sci Rep (2025). https://doi.org/10.1038/s41598-025-34037-9
Received:
Accepted:
Published:
DOI: https://doi.org/10.1038/s41598-025-34037-9