Integrating the RUSLE Model and AI in Water Erosion Assessment
(A Case Study of the Karbala–Arar Watersheds in Western Iraq)
Abstract
This study aims to assess water erosion across five watersheds in western Karbala toward Arar using the RUSLE model supported by GIS, remote sensing data, and artificial intelligence tools. The five RUSLE factors (R, K, LS, C, P) were calculated using digital analysis, and Sentinel-2 imagery was used to extract NDVI. The Random Forest algorithm was applied to improve the estimation of the cover factor (C) and to develop a predictive model for erosion density.
Results showed that Wadi Hamir is the most erosion-prone basin (333.69 tons/km²/year), while Wadi Abu Ghar recorded the lowest density. The predictive modeling experiment demonstrated that RUSLE accuracy improves significantly with the use of synthetically generated data and machine learning algorithms, reaching an R² value of 0.63.
The study recommends implementing effective soil conservation practices in high-risk watersheds and adopting routine NDVI monitoring via Sentinel-2 and Google Earth Engine. The findings confirm that integrating deterministic models with artificial intelligence enhances erosion assessment accuracy and supports environmental resource management planning.
References
2. Ali, M. K. (2022). Estimating the cover management factor using NDVI and artificial intelligence systems. Diyala Journal of Agricultural Sciences, 14(1), 77–95. https://www.iasj.net/iasj/article/253228
3. Al Obaidy, A. H., & Al-Maliky, S. K. (2019). Assessment of soil erosion in the western desert of Iraq using RUSLE and GIS. Journal of Geography and Regional Planning, 12(4), 66–75. https://doi.org/10.5897/JGRP2019.0734
4. Al-Rubaie, A. I., & Khalaf, R. S. (2023). Soil erosion assessment in Horan Valley, Iraq using RUSLE2 and GIS techniques. Arabian Journal of Geosciences, 16(3), 315. https://doi.org/10.1007/s12517-023-11221-9
5. Ameen, R. A., & Aljabry, A. H. (2016). Designing a form for the erosion gully map by using Bergsma equation that modified polygon via RS & GIS Zargata valley–Arbil–Iraq. Imperial Journal of Interdisciplinary Research (IJIR), 2(6).https://www.onlinejournal.in
6. Al, N. A. H. J. S., Al-Asadi, M. A., & Amin, R. A. M. (2024). Quantitative Assessment of Water Erosion Risk in the Sandi Plain Using the Jafarlovic EPM Model. Midad Al-Adab Refereed Journal, 1(34).https://midad-adab.com
7. Al-Ali, A. K., & Amin, R. M. (2025). Tectonic Evaluation by Using Morphotectonic Indices at Zurbatiyah Area, Eastern Iraq. The Iraqi Geological Journal, 18–39.https://igj-iraq.org
8. Abbas, A. M., Taher, M. A., Abbood, N. H., & Amin, R. M. (2024). Qualitative Assessment of Water Erosion in Zawita Town in Dohuk Governorate within Kurdistan Region in Iraq, Using the (PAP/CAR) Model. Kurdish Studies, 12(2), 5159–5171.https://kurdishstudies.net/index.php/KS/article/view/547
9. Khosravi, K., Pham, B. T., Chapi, K., Shirzadi, A., Shahabi, H., & Prakash, I. (2021). A comparative assessment of intelligent models for soil erosion prediction. Science of The Total Environment, 789, 148124. https://doi.org/10.1016/j.scitotenv.2021.148124
10. Kareem, I. J., Jasim, G. S., Ali, H. A., & Amin, R. M. (2024). Estimating the extent of water erosion in Darbandikhan Lake using a model Gavrilović Method (EPM) (Erosion Potential Method). International Journal of Religion, 5(9), 358–369 https://ijrjournal.com
11. Moore, I. D., & Burch, G. J. (1986). Physical basis of the length‐slope factor in the universal soil loss equation. Soil Science Society of America Journal, 50(5), 1294–1298. https://doi.org/10.2136/sssaj1986.03615995005000050042x
12. Panagos, P., Borrelli, P., Meusburger, K., Alewell, C., Lugato, E., & Montanarella, L. (2015). The new assessment of soil loss by water erosion in Europe. Environmental Science & Policy, 54, 438–447. https://doi.org/10.1016/j.envsci.2015.08.012
13. Rahman, M. M., Sadeghi, S. H. R., Karnon, J., & Smith, C. (2024). Integrating machine learning with RUSLE for enhanced soil erosion modeling under climate change scenarios. Environmental Modelling & Software, 170, 105578. https://doi.org/10.1016/j.envsoft.2023.105578
14. Renard, K. G., Foster, G. R., Weesies, G. A., McCool, D. K., & Yoder, D. C. (1997). Predicting soil erosion by water: A guide to conservation planning with the Revised Universal Soil Loss Equation (RUSLE). USDA Agricultural Handbook No. 703.
15. Sharma, H. S., Sehgal, V. K., & Sahoo, R. N. (2018). Soil erosion modeling using artificial neural network and RUSLE model in GIS. Environmental Earth Sciences, 77(1), 18. https://doi.org/10.1007/s12665-017-7170-7
16. Wischmeier, W. H., & Smith, D. D. (1978). Predicting rainfall erosion losses: A guide to conservation planning. USDA Agricultural Handbook No. 537.https://www.nrcs.usda.gov/Internet/FSE_DOCUMENTS/stelprdb1044171.pdf
17. Al-Maliki, N. H. J. Sh., Al-Asadi, M. A. W. H., & Amin, R. A. M. (2024). Quantitative assessment of water erosion risk in the Al-Sindi plain using the Gavrilovic EPM model. Midad Al-Adab Journal, 14(34), 1245–1276. https://www.midad-adab.com/index.php/midad/article/view/762.
Copyright (c) 2025 أ.د. رقية احمد محمد أمين , مصطفى عامر سهيل ممتاز , حارث عباس علي
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.
