Spatial Prediction of Gully Erosion Susceptibility in the Talwar Watershed of Kurdistan Province Using Random Forest and Boosted Regression Trees Models and Evaluating their Accuracy

Document Type : Research Article

Authors

• O. Rahmati ¹
• S.M. Soleimanpour ²
• S. Shadfar ³
• S. Zahedi ¹

¹ - Soil Conservation and Watershed Management Research Department, Kurdistan Agricultural and Natural Resources Research and Education Center, Agricultural Research, Education and Extension Organization (AREEO), Sanandaj, Iran

² Soil Conservation and Watershed Management Research Department, Fars Agricultural and Natural Resources Research and Education Center, Agricultural Research, Education and Extension Organization (AREEO), Shiraz, Iran

³ Soil Conservation and Watershed Management Research Institute, Agricultural Research, Education and Extension Organization (AREEO), Tehran, Iran

10.22067/jsw.2025.92149.1465

Abstract

Introduction
Gully erosion is one of the most important factors affecting sediment production and land degradation, and predicting its occurrence is one of the practical solutions to prevent gully erosion. Since the occurrence of gully erosion is directly related to environmental factors and human activities, it is possible to identify areas prone to gully erosion using models based on artificial intelligence and data mining. Modeling helps to save time and cost of measuring gutters. Also, because artificial intelligence and data mining models have a high ability to analyze environmental information; they are able to identify nonlinear and complex relationships between variables, and for this reason, they have been widely accepted by researchers in various sciences worldwide. For this purpose, this study aimed to predict gully erosion susceptibility using random forest models and boosted regression trees in the Talwar watershed located in the southeast of Kurdistan province.
 
Materials and Methods
Initially, 99 gullies were identified during field visits, the location of the gully head-cut was recorded, and a map of the spatial distribution of the gullies was prepared. The recorded gullies were randomly divided into two groups: training and validation in a ratio of 70:30, such that 70% of the gullies were in the training group and the rest in the validation group. In addition, maps of factors affecting gully erosion including elevation, slope gradient, slope aspect, lithology, distance from the stream, topographic wetness index, land use, plan curvature, profile curvature, average annual rainfall, relative slope position, stream power index, distance from the road, soil order, and soil texture were prepared in geographic information system. Subsequently, in the modeling process, environmental factors were considered as independent variables and the creation of gullies as a dependent variable. In order to model gully erosion, the training group gullies were used in this stage to calibrate the models. In this study, Random Forest (RF) and Boosted Regression Trees (BRT) machine learning models were used to predict gully erosion. In these models, raster layers related to environmental factors affecting gully erosion were introduced as independent variables to the model. Also, the layer of gully front points, which were previously named after the training group, was introduced as a dependent variable to the model. The process of running the models was carried out in the R software environment. The prediction accuracy of the models was also evaluated using the area under the receiver operating characteristic curve (AUC) method.
 
Results and Discussion
The spatial pattern of gully erosion by these two models showed that in this basin, generally the middle, eastern and northern parts, which are adjacent to waterways and rivers, had a higher tendency to cause gully erosion. Since the prediction interval of gully erosion in artificial intelligence models varied between zero and one, it can be considered as the probability of gully erosion. The lowest and highest values of the probability of gully erosion by the random forest model were obtained as 0.006 and 0.996, respectively. The median value of the prediction of gully erosion in the prediction of the random forest model was also calculated as 0.322. Therefore, 50% of the pixels in this basin had a tendency to cause gully erosion greater than 0.322 and the other half of its tendency was less than 0.322. The spatial pattern of gully erosion prediction from the boosted regression tree model also varied from 0.011 to 0.799. This model generally introduced the adjacent sections of the drainage network in the middle, eastern, and northern parts as the most favorable lands for the creation and formation of gully erosion. The median predicted value from this model was 0.387. Prediction accuracy, measured by the area under the receiver operating characteristic curve, was 0.952 for the random forest model and 0.891 for the boosted regression tree model.
 
Conclusion
The findings showed that the random forest model had more accuracy in spatial prediction of gully erosion in the Talwar watershed. Also, based on the AUC criterion, the random forest model was placed in the excellent group (AUC>0.9) and the boosted regression tree model was placed in the very good group (AUC<0.8). According to the findings of this study, executive agencies can use artificial intelligence and data mining models, such as the random forest model, to prepare a gully erosion map and plan and prioritize areas for implementing soil conservation measures. Certainly, focusing soil conservation executive measures and management programs in areas prone to gully erosion in the country's watersheds will improve the performance and optimize the financial resources of natural resources and watershed management departments.
 
 

Keywords

• Artificial intelligence
• Modeling
• Soil conservation
• Spatial pattern

Main Subjects

• Soil science

©2025 The author(s). This is an open access article distributed under Creative Commons Attribution 4.0 International License (CC BY 4.0).

References

1. Amiri, M., Pourghasemi, H.R., Ghanbarian, Gh.A., & Afzali, S.F. (2020). Spatial modeling of gully erosion in Maharlou Watershed using different scenarios and Weights-of-evidence algorithm. Journal of Watershed Engineering and Management, 11(4), 1016-1032. (In Persian with English abstract). https://doi.org/10.1007/ 978-3-030-01440-7_59
2. Asadi Nalivan, O., Rabet, A., Vakili tajareh, F., Ramezani, M., Momeni, M., & Heydari, K. (2023). Zoning gully erosion susceptibility using ANN, CART and RF models. Watershed Engineering and Management, 15(2), 155-171. (In Persian with English abstract). https://doi.org/10.22092/ijwmse.2022.356379.1920
3. Bammou, Y., Benzougagh, B., Abdessalam, O., Brahim, I., Kader, Sh., Spalevic, V., Sestras, P., & Ercişli, S. (2024). Machine learning models for gully erosion susceptibility assessment in the Tensift catchment, Haouz Plain, Morocco for sustainable development. Journal of African Earth Sciences, 213(1), 105229. https://doi.org/1016/ j.jafrearsci.2024.105229
4. Conoscenti, C., Agnesi, V., Cama, M., Caraballo‐Arias, N.A., & Rotigliano, E. (2018). Assessment of gully erosion susceptibility using multivariate adaptive regression splines and accounting for terrain connectivity. Land Degradation & Development, 29(3), 724-736. https://doi.org/10.1002/ldr.2772
5. Conoscenti, C., Angileri, S., Cappadonia, C., Rotigliano, E., Agnesi, V., & Märker, M. (2014). Gully erosion susceptibility assessment by means of GIS-based logistic regression: A case of Sicily (Italy). Geomorphology, 204(1), 399-411. https://doi.org/10.1016/j.geomorph.2013.08.021
6. Emadodin, S., Omidi, M., Arekhi, S., & Karam, A. (2021). Assessment the Gully Erosion Risk in Quyjoq watershed. Journal of Natural Environmental Hazards, 10(30), 17-34. (In Persian with English abstract). https://doi.org/ 10.22111/jneh.2020.34212.1662
7. Garosi, Y., Sheklabadi, M., Conoscenti, C., Pourghasemi, H.R., & Van Oost, K. (2019). Assessing the performance of GIS-based machine learning models with different accuracy measures for determining susceptibility to gully erosion. Science of the Total Environment, 664(1), 1117-1132. https://doi.org/10.1016/j.scitotenv.2019.02.093
8. Garosi, Y., Sheklabadi, M., Pourghasemi, H.R., Besalatpour, A.A., Conoscenti, C., & Van Oost, K. (2018). Comparison of differences in resolution and sources of controlling factors for gully erosion susceptibility mapping. Geoderma, 330(1), 65-78. https://doi.org/10.1016/j.geoderma.2018.05.027
9. Gayen, A., Pourghasemi, H.R., Saha, S., Keesstra, S., & Bai, S. (2019). Gully erosion susceptibility assessment and management of hazard-prone areas in India using different machine learning algorithms. Science of the Total Environment, 668(1), 124-138. https://doi.org/10.1016/j.scitotenv.2019.02.436
10. Ghaderi, N., Ghodosi, J., Tabatabai, M.R., & Khaledian, H. (2000). Zoning of gully erosion risk in the Talwar Chay watershed of Kurdistan province using GIS. Report of a Research Project in Soil Conservation and Watershed Management Research Institute. Identical Code 18781476, p. 139. (In Persian with English abstract). http:// fipak.areeo.ac.ir/site/catalogue/18781476
11. Ghorbanzadeh, O., Shahabi, H., Mirchooli, F., Valizadeh Kamran, K., Lim, S., Aryal, J., Jarihani, B., & Blaschke, T. (2020). Gully erosion susceptibility mapping (GESM) using machine learning methods optimized by the multi‑collinearity analysis and K-fold cross-validation. Geomatics, Natural Hazards and Risk, 11(1), pp.1653-1678. https://doi.org/10.52547/jwmr.12.24.298
12. Igwe, P.U., Chinedu, O.C., Nlem E.U., Nwezi, C.C., & Ezekwu, J.C. (2018). A review of landscape design as a means of controlling gully erosion. International Journal of Environment Agriculture and Biotechnology, 3(1), 103-111. https://doi.org/22161/ijeab/3.1.13
13. Javidan, N., Kavian, A., Rajabi, S., Pourghasemi, H.R., & Jafarian, Z. (2023). Identification the areas prone to gully erosion and landslides in the form of two-hazards map using machine learning models in Gorganrood watershed. Iranian Journal of Watershed Management Science, 17(62), 75-85. (In Persian with English abstract). https://doi.org/10.1007/978-3-030-23243-6_29
14. Jurchescu, M., & Grecu, F. (2015). Modelling the occurrence of gullies at two spatial scales in the Olteţ Drainage Basin (Romania). Natural Hazards, 79(1), 255-289. https://doi.org/1007/s11069-015-1981-6
15. Nyssen, J., Poesen, J., Moeyersons, J., Luyten, E., Veyret‐Picot, M., Deckers, J., Haile, M., & Govers, G. (2002). Impact of road building on gully erosion risk: a case study from the northern Ethiopian highlands. Earth Surface Processes and Landforms: The Journal of the British Geomorphological Research Group, 27(12), 1267-1283. https://doi.org/10.1002/esp.404
16. Rahmati, , Soleimanpour, S.M., Shadfar, S., & Zahedi, S. (2023). Modeling gully erosion susceptibility in Talwar watershed, Kurdistan province and evaluating the model transferability to Baba-arab watershed. Final Report of Research Project, Soil Conservation and Watershed Management Research Institute, 76pp. Project code: 2-53-29-013-000301. (In Persian with English abstract). https://doi.org/10.52547/jwmr.12.24.298
17. Rahmati, O., Tahmasebipour, N., Haghizadeh, A., Pourghasemi, H.R., & Feizizadeh, B. (2017). Evaluation of different machine learning models for predicting and mapping the susceptibility of gully erosion. Geomorphology, 298(1), 118-137. https://doi.org/10.1016/j.geomorph.2017.09.006
18. Rahmati, O., Tahmasebipour, N., Haghizadeh, A., Pourghasemi, H.R., & Feizizadeh, B. (2019). Assessing the effectiveness of the maximum entropy model to gully erosion susceptibility prediction in the Kashkan-Poldokhtar Watershed. Journal of Watershed Engineering and Management, 10(4), 727-738. (In Persian with English abstract). https://doi.org/10.1016/j.geomorph.2017.09.006
19. Rahmati, O., Soleimanpour, S.M., & Shadfar, S. (2024). Principles of spatial modeling of gully erosion using artificial intelligence models. Soil Conservation and Watershed Management Research Institute Press, P. 158. (In Persian with English abstract).
20. Rangzan, K., Zaheri Abdehvand, Z., & Mokarram, M. (2022). Determining areas prone to gully erosion using fuzzy membership function (Case study: Mohr City in the south of Fars province). Quantitative Geomorphological Researches, 10(4), 56-74. (In Persian with English abstract). DOR: 1001.1.22519424.1401.10.4.4.9
21. Refahi, H.Gh. (2017). Water Erosion and Its Control. Tehran University Press, 7th edition, 672 pages. (In Persian)
22. Saha, S., Roy, J., Arabameri, A., Blaschke, T., & Tien Bui, D. (2020). Machine learning-based gully erosion susceptibility mapping: A case study of Eastern India. Sensors, 20(5), p.1313. https://doi.org/10.3390/s20051313
23. Servati, M.R., Ghodosi, J., & Dadkhah, M. (2008). Factors affecting the formation and spread of gully erosion in loess. Research and Construction, 21(1), 20-33. (In Persian with English abstract).
24. Shahabi, H., Amiri, Z., & Shirzadi, A. (2022). Prediction of Gully Erosion Susceptibility and Its Hazards in Kloche Bijar Watershed Using Spatial Predictive Models. Environmental Management Hazards, 9(2), 89-107. (In Persian with English abstract). https://doi.org/10.22059/jhsci.2022.348010.742
25. Soleimani, F., Soufi, M., & Arsham, A. (2017). Determination of Effective Factors in Gullies Development in Modares Watershed of Shushtar. Water and Soil, 31(5), 1432-1446. (In Persian with English abstract). https://doi.org/10.22067/jsw.v31i5.63329
26. Soleimanpour, S., Soufi, M., & Ahmadi, H. (2009). Determining Effective Factors on Gully Development in Konartakhte Region, Fars Province. Water and Soil, 23(1), 131-141. (In Persian with English abstract). https://doi.org/10.22067/jsw.v0i0.1545
27. Vosoghi, S., Zakerinejad, R., & Entezari, M. (2025). Prediction of Gully Erosion and identifying factors affecting it using the Maximum Entropy Model and BCC-CSM2-MR climate change models for the years 2020-2040 (case study: Alamarvdasht watershed). Journal of Geography and Planning, 28(90), 163-141. (In Persian with English abstract). https://doi.org/10.22034/gp.2023.57572.3169
28. Wei, Y., Liu, Z., Zhang, Y., Cui, T., Guo, Z., Cai, C., & Li, Z. (2022). Analysis of gully erosion susceptibility and spatial modelling using a GIS-based approach. Geoderma, 420(1), 115869. https://doi.org/10.1016/j.geoderma. 2022.115869
29. Were, K., Kebeney, S., Churu, H., Mumo Mutio, J., Njoroge, R., Mugaa, D., Alkamoi, B., Ng’etich, W., & Ram Singh, B. (2023). Spatial prediction and mapping of gully erosion susceptibility using machine learning techniques in a degraded semi-arid region of Kenya. Land, 12(4), 1-19. https://doi.org/3390/land12040890
30. Zakerinejad, R., & Alvandi, P. (2023). Spatial prediction of gully erosion using TanDEM-X data and maximum entropy model (A case study: Khasoyeh watershed, in Southeast of Fars Province). Environmental Erosion Research, 13(1), 96-113. (In Persian with English abstract). http://magazine.hormozgan.ac.ir/article-1-705-en.html