با همکاری انجمن آبخیزداری ایران

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکتری، گروه مهندسی مرتع و آبخیزداری، دانشکده منابع طبیعی، دانشگاه لرستان، خرم آباد، ایران

2 دانشیار، گروه مهندسی مرتع و آبخیزداری، دانشکده منابع طبیعی، دانشگاه لرستان، خرم آباد، ایران

3 استادیار، بخش تحقیقات حفاظت خاک و آبخیزداری، مرکز تحقیقات و آموزش کشاورزی و منابع طبیعی، سازمان تحقیقات آموزش و ترویج کشاورزی کردستان، سنندج، ایران

10.22092/ijwmse.2026.371373.2139

چکیده

مقدمه
امروزه مطالعه فرسایش خندقی به‌‌دلیل تولید رسوب و خسارات متعدد در نتیجه فعالیت‌های انسانی از اهمیت بالایی برخوردار است. در مطالعات انجام شده عوامل طبیعی زیادی به‌عنوان عوامل کنترل کننده فرسایش آبکندی گزارش شده‌اند که ازجمله می‌‌توان به عوامل زمین-محیطی که شرایط بحرانی برای وقوع و توسعه فرسایش آبکندی را کنترل می‌کنند و در درجه اول با توپوگرافی، سنگ‌شناسی، بارندگی، خاک و کاربری اراضی مرتبط هستند اشاره کرد. شناسایی عوامل مؤثر در وقوع فرسایش آبکندی و پهنه‌بندی آن یکی از ابزارهای اساسی و مهم برای کنترل و مدیریت این پدیده است. فرسایش آبکندی یک خطر مهم برای وضعیت اکوسیستم‌ها در سراسر جهان است، در نتیجه توسعه نقشه‌های حساسیت فرسایش آبکندی ضروری است. بنابراین این پژوهش به‌منظور پهنه‌‌بندی حساسیت وقوع فرسایش آبکندی با استفاده از مدل‌‌های هوش مصنوعی از نوع شبکه عصبی مصنوعی (MLP)، حداکثرآنتروپی (MaxEnt)، تحلیل تفکیک‌کننده‌انعطاف‌پذیر (FDA)، در شهرستان الشتر انجام شد.
 
مواد و روش‌‌ها
منطقه مورد مطالعه از نظر ژئومورفولوژیکی در بخش مرکزی رشته‌کوه زاگرس در استان لرستان قرار دارد که خود بخشی از زیرحوضه کرخه است. شهرستان الشتر با مساحت 1523.55 کیلومتر مربع بین طول‌های جغرافیایی”38 ΄03 ْ48 تا ”52 ΄30 48 شرقی و عرض‌های ”37 ΄44 33 تا ”21΄01 34 شمالی قرار دارد. میانگین بارندگی حوضه حدود 570 میلی‌متر و دارای اقلیم نیمه‌خشک و سرد است. برای پهنه‌بندی حساسیت به وقوع فرسایش خندقی با استفاده از مدل‌های هوش مصنوعی و تعیین بهترین مدل، از مدل‌های شبکه عصبی مصنوعی (MLP) حداکثرآنتروپی (MaxEnt)، تحلیل تفکیک‌کننده‌انعطاف‌پذیر (FDA)، استفاده شد. در این تحقیق از 12 عامل شیب، جهت شیب، بارش، فاصله از جاده، فاصله از رودخانه، فاصله از گسل، خاک، کاربری اراضی، سازند زمین‌شناسی، شاخص رطوبت توپوگرافی (TWI)، شاخص موقعیت توپوگرافی TPI و شاخص پوشش گیاهی NDVI به عنوان پارامترهای ورودی و نقاط خندقی و غیرخندقی به‌عنوان پارامترهای خروجی برای مدلسازی و پهنه‌بندی حساسیت به وقوع خندق استفاده شد. سپس از مجموع 151 نقطه وقوع و عدم وقوع خندق (89 خندق و 62 غیر خندق)، 70 درصد به‌عنوان داده‌های آموزش و 30 درصد برای مرحله اعتبارسنجی استفاده شد. به‌منظور ارزیابی مدل‌ها، از منحنی تشخیص عملکرد نسبی (ROC) برای قدرت پیش‌بینی مدل‌ها استفاده شد.
 
نتایج و بحث
نتایج نشان داد که مدل MLP با مقادیر AUC برابر با 0.98 در مرحله آموزش و 0.92 در مرحله اعتبارسنجی، بهترین عملکرد را در پیش‌بینی حساسیت وقوع فرسایش آبکندی دارد. پس از آن به‌ترتیب مدل‌های ( 0.87=AUC) FDA و (0.5=AUC) MaxEnt قرار دارند. تحلیل عوامل مؤثر نشان داد که بیشترین آبکندها در طبقات بارشی ۷۰۰-۶۰۰ میلی‌متر، فواصل بیش از ۳۰۰ متر از گسل، جاده و رودخانه، شیب‌های ۰-۵ و ۵-۱۵ درصد، جهت‌های شمالی، کاربری کشاورزی دیم و سازندهای آبرفت قدیم و مارن‌ها واقع شده‌اند. همچنین بین شاخص‌های TWI و NDVI به‌ترتیب رابطه مستقیم و معکوس با وقوع آبکند مشاهده شد. در نهایت، نقشه نهایی پهنه‌بندی حساسیت فرسایش آبکندی با استفاده از مدل برتر MLP تهیه شد.
 
نتیجه‌‌گیری
با توجه به اینکه فرسایش آبکندی یکی از شکل‌های پیشرفته فرسایش آبی است، شناسایی عوامل مؤثر و پهنه‌بندی آن برای کنترل و مدیریت این پدیده حائز اهمیت است. این مطالعه با هدف شناسایی عوامل مهم و تأثیرگذار در فرسایش آبکندی و ایجاد مدل‌های یادگیری ماشین برای پهنه‌بندی حساسیت وقوع به فرسایش آبکندی در شهرستان الشتر انجام شد. نتایج نشان داد که مدل شبکه عصبی مصنوعی (MLP) بهترین عملکرد را با توجه به معیار ارزیابی مدل (0.92=AUC) کسب کرده است و پس از آن به‌ترتیب مدل‌های ( 0.87=AUC) FDA و ( 0.5=AUC)  MaxEnt قرار دارند. نتایج به‌دست‌آمده از این پژوهش، دیدگاه مناسبی را در مورد تأثیر عوامل مؤثر در ایجاد فرسایش خندقی در اختیار برنامه‌ریزان و محققان قرار می‌دهد. در نتیجه با انجام تحقیقات بیشتر می‌توان استفاده از سایر تکنیک‌های یادگیری ماشین را بررسی نمود و دیگر عوامل مؤثر را برای بهبود دقت مدل‌های پیش‌بینی فرسایش خندقی در نظر گرفت.

کلیدواژه‌ها

عنوان مقاله [English]

Application of artificial intelligence in preparing gully erosion susceptibility maps in the Alshater County, Lorestan Province

نویسندگان [English]

  • Negar Arjmand 1
  • Alireza Sepahvand 2
  • Omid Rahmati 3

1 Ph.D. Student, Department of Range and Watershed Management, Faculty of Natural Resources, Lorestan University, Khorramabad, Lorestan Province, Iran

2 Associate Professor, Department of Range and Watershed Management Engineering, Faculty of Natural Resources, Lorestan University, Khorramabad, Lorestan Province, Iran

3 Assistant Professor, Soil Conservation and Watershed Management Research Department, Agricultural and Natural Resources Research and Education Center, Kurdistan Agricultural Research, Education and Extension Organization, Kurdistan, Iran

چکیده [English]

Introduction
Today, the study of gully erosion is of great importance due to sediment production and numerous damages resulting from human activities. Many natural factors have been reported as controlling factors of gully erosion. Among the geo-environmental factors that control the critical conditions for the occurrence and development of gully erosion, primarily related to topography, lithology, rainfall, soil, and land use, other studies have stated that surface runoff is one of the main factors affecting the occurrence of gully erosion. Identifying the factors affecting the occurrence of gully erosion and its zoning is one of the essential and important tools for controlling and managing this phenomenon. Gully erosion is a significant threat to the state of ecosystems worldwide; consequently, developing gully erosion susceptibility maps is essential. Therefore, this research was conducted to mapping the susceptibility of gully erosion occurrence using artificial intelligence models of the Multilayer Perceptron (MLP) neural network, Maximum Entropy (MaxEnt), and Flexible Discriminant Analysis (FDA) in Al-Shatr city.
 
Materials and methods
The study area is located in the central part of the Zagros mountain range in Lorestan Province, Iran, within the Karkheh sub-basin. Alashtar County covers an area of 1,523.55 km², situated between longitudes 48°30′52″E to 48°03′38″E and latitudes 34°01′21″N to 33°44′37″N. The basin has an average annual precipitation of approximately 570 mm and features a semi-arid, cold climate. To map gully erosion susceptibility and identify the most effective model, three artificial intelligence models were employed: Multi-Layer Perceptron (MLP), Maximum Entropy (MaxEnt), and Flexible Discriminant Analysis (FDA). Twelve environmental factors were used as input variables: slope, aspect, precipitation, distance from roads, distance from rivers, distance from faults, soil type, land use, geological formation, Topographic Wetness Index (TWI), Topographic Position Index (TPI), and Normalized Difference Vegetation Index (NDVI). The output variables consisted of gully and non-gully points. A total of 151 points (89 gully and 62 non-gully locations) were collected. Seventy percent of the data were used for model training, while the remaining 30% were reserved for validation. Model performance was evaluated using the Relative Operating Characteristic (ROC) curve to assess predictive accuracy.
 
Results and discussion
The results showed that the MLP model, with AUC values of 0.98 in the training phase and 0.92 in the validation phase, had the best performance in predicting gully erosion susceptibility. This was followed by the FDA (AUC = 0.87) and MaxEnt (AUC = 0.5) models, respectively. Analysis of the influencing factors revealed that most gullies were located in precipitation classes of 600-700 mm, distances greater than 300 meters from faults, roads, and rivers, slope classes of 0-5% and 5-15%, northern aspects, dry farming land use, and geological formations of old alluvium and marls. Furthermore, a direct relationship was observed between the TWI index and gully occurrence, while an inverse relationship was found for the NDVI index. Finally, the gully erosion map was prepared using the MLP model.
 
Conclusions
Given that gully erosion is an advanced form of water erosion, identifying its driving factors and mapping its susceptibility are crucial for effective control and management. This study aimed to identify key factors influencing gully erosion and develop machine learning models to map susceptibility in Shastar County. Results indicate that the Artificial Neural Network (MLP) model performed best, achieving an AUC of 0.92, followed by FDA (AUC = 0.87) and MaxEnt (AUC = 0.50). These findings provide valuable insights for planners and researchers regarding the factors driving gully erosion. Future research should explore additional machine learning techniques and incorporate other influential factors to further improve prediction accuracy.

کلیدواژه‌ها [English]

  • FDA Model
  • Lorestan province
  • Machine Learning
  • Mapping of gully erosion
  • Modeling
Abedini, M. 2005. A Study on Gully Erosion of the Highlands in Southwest of Hadishahr Plain, Northwest of East Azerbaijan through New Methods and Techniques. Geography and Development Journal, 3(6), 113-134 (in Persian).
Ahmadpour, H., Bazrafshan, O., Rafiei-Sardooi, E., Zamani, H., Panagopoulos, T., 2021. Gully erosion susceptibility assessment in the Kondoran watershed using machine.2-23.
Arabameri, A., Blaschke, T., Pradhan, B., Pourghasemi, H.R., Tiefen bacher, J.P., Bui, D.T., 2020c. Evaluation of recent advanced soft computing techniques for gully erosion susceptibility mapping: A comparative study. Sensors 20 (2), 335.
Arabameri, A., Chen, W., Loche, M., Zhao, X., Li, Y., Lombardo, L., Cerda, A., Pradhan, B., Bui, D.T., 2020a. Comparison of machine learning models for gully erosion susceptibilit y mapping. Geoscience Frontiers. 11 (5), 1609–1620.
Arabameri, A., Pradhan, B., Rezaei, K., Conoscenti, C., 2019. Gully erosion susceptibility mapping using GIS-based multi-criteria decision analysis techniques. Catena 180, 282–297. https://doi.org/10.1016/ j.catena.2019.04.032.
Asadi Nalivan, O., Rabet, A., Vakili Tajareh, F., Ramezani, M., Momeni, M., Heidari, K., 2023. Zoning of gully erosion susceptibility using Ann, CART, and RF models, Watershed Engineering and Management, 15(2): 155-171 (in Persian).
Azareh, A., O. Rahmati, E. Rafiei, J. Sankey, S. Lee, H. Shahabi and B. Ahmad. 2019. Modelling gully erosion susceptibility in a semi-arid region, Iran: investigation of applicability of certainty factor and maximum entropy models. Science of the Total Environment, 655: 684–696.
Borrelli, P., Robinson, D.A., Panagos, P., Lugato, E., Yang, J.E., Alewell, C., Wuepper, D., Montanarella, L., Ballabio, C., 2020. Land use and climate change impacts on global soil erosion by water (2015-2070). Proceedings of the National Academy of Sciences of the United States America. 117 (36), 21994–22001.
Breiman, L., 2001. Random forests. Mach. Learn. 45 (1), 5–32.
Chen, W., Lei, X., Chakrabortty, R., Pal, S.C., Sahana, M., Janizadeh, S., 2021. Evaluation of different boosting ensemble machine learning models and novel deep learning and boosting framework for head-cut gully erosion susceptibility. Journal of Environmental Management. 284. 112015.
Chenari K, Bahremand A, Bordi Sh, Komaki Ch, 2016. Zoning the Risk of Erosion Occurrence Potential Using Statistical Methods in the Gernaveh Watershed, Golestan Province, Ecohydrology Journal, 3(2): 219-231 (in Persian).
Chowdhuri, I., Pal, S.C., Saha, A., Chakra bortty, R., Roy, P., 2021. Evaluation of different DEMs for gully erosion susceptibility mapping using in-situ field measurement and validation. Ecological Informatics. 65. 101425.
Chuma, G., Mugumaarhahama, Y., Mond, J., Bagula. E., Ndeko, A., Lucungu, P., Karume, K., Mushagalusa, G., Schmitz, S., 2023. Gully erosion susceptibility mapping using four machine learning methods in Luzinzi watershed, eastern Democratic Republic of Congo. Physics and Chemistry of the Earth 129 (2023) 103295.
Conforti, M., Aucelli, P.P.C., Robustelli, G. and Scarciglia, F. 2011. Geomorphology and GIS analysis for mapping gully erosion susceptibility in the Turbolo stream catchment (Northern Calabria, Italy). Natural Hazards, 56, 881–898.
Dixon, B., Candade, N., 2008. Multispectral land use classification using neural networks and support vector machines: one or the other, or both? International Journal of Remote Sensing. 29 (4), 1185–1206.
Domazetovic, F., Siljeg, A., Loncar, N., Maric, I., 2019. Development of automated multicriteria GIS analysis of gully erosion susceptibility. Appl. Geogr. apgeog.2019.102083. 112 102083. https://doi.org/10.1016/j.
Davoudi, A., Karam, A., Zeaiean Firouzabadi, P., Ahmadabadi, A., 2025. Assessment of gully erosionprone areas in the Aleshtar basin using machine learning models. Natural Disasters, 1 (1), 63-82.
Emadodin, S., Omidi, M., Arkhi, S., & Karam, A. 2021. Risk assessment of gully erosion occurrence in Ghoojegh watershed. Scientific-Research Journal of Natural Environmental Hazards, 10 (4, Serial No. 30), 17-34 (in Persian).
Fu, L., Guo, J., Shen, W., Wang, X., et al., 2024. Geophysical Evidence of the Collisional Suture Zone in the Prydz Bay, East Antarctica. Geophysical Research Letters 51 (2). https://doi.org/ 10.1029/2023GL106229.
Gao, R., Gao, M., Yao, Sh., Wen, Y., 2025. Gully erosion susceptibility mapping considering seasonal variations of NDVI using a machine learning approach in the Mollisol region of China. Soil & Tillage Research 245 (2025) 106322.
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, 65–78. https://doi.org/ 10.1016/j.geoderma.2018.05.027.
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, 65–78.
Gornami, R. and S. Shadfar. 2019. Application of the GIS in the determination of susceptible areas to gully erosion using the ANP. Watershed Management Research, 31(4): 58-68 (in Persian).
Gornami, R. and S. Shadfar. 2019. Application of the GIS in the determination of susceptible areas to gully erosion using the ANP. Watershed Management Research, 31(4): 58-68 (in Persian).
Hallgren, W., Santana, F., Low-Choy, S., Zhao, Y., , & Mackey, B. 2019: Species distribution models can be highly sensitive to algorithm configuration. Ecological Modelling, 408, 108719.
Hasanuzzaman, M., Adhikary, P., Shit, P., 2024. Gully erosion susceptibility mapping and prioritization of gully-dominant sub-watersheds using machine learning algorithms: Evidence from the Silabati River (tropical river, India). Advances in Space Research 73 (2024) 1653–1666.
Hastie, T., Tibshirani, R., Friedman, J.H., & Friedman, J.H. 2009: The elements of statistical learning: data mining, inference, and prediction. 2, 1-758. doi:10.1007/978-0-387-21606-5.
Hitouri, S., Meriame, M., Ajim, A., Pacheco, Q., Nguyen-Huy, T., Bao, P., ElKhrachy, I., Varasano, A., 2024. Gully erosion mapping susceptibility in a Mediterranean environment: A hybrid decision-making model. International Soil and Water Conservation Research. 12(2), 279-297. doi: 10.1016/j.iswcr.2023.09.008.
Hu, M., Niu, Q., Yuan, W., Wang, W., et al., 2024. Evolution characteristic and mechanism of microstructure, hydraulic and mechanical behaviors of sandstone treated by acid-rock reaction: Application of in-situ leaching of uranium deposits. Journal of Hydrology 643. 131948. https://doi.org/10.1016/j.jhydrol.2024.131948.
Igwe, O., John, U.I., Solomon, O., Obinna, O., 2020. GIS-based gully erosion susceptibility modeling, adapting bivariate statistical method and AHP approach in Gombe town and environs Northeast Nigeria. Geoenvironmental Disasters 7, 1–16.
Khazaei M., Shirani K., Saleh A., 2024. Investigation of Factors Affecting Gully Erosion and Preparation of Zoning Map in Takht-e Deraz Watershed. Environmental Erosion Research, 3(14), 123-141(in Persian).
Kheir, R.B., Wilson, J., Deng, Y., 2007. Use of terrain variables for mapping gully erosion susceptibility in Lebanon. Earth Surface Processes and Landforms: the Journal of the British Geomorphological Research Group 32 (12), 1770–1782.
Kuhnert, P.M., Henderson, A.-K., Bartley, R., Herr, A., 2010. Incorporating uncertainty in gully erosion calculations using the random forests modelling approach. Environmetrics 21, 493–509. https://doi.org/10.1002/env.999.
Lei, X., Chen, W., Avand, M., Janizadeh, S., Kariminejad, N., Shahabi, H., Costache, R., Shahabi, H., Shirzadi, A., Mosavi, A., 2020. GIS based machine learning algorithms for gully erosion susceptibility mapping in a semi-arid region of Iran. Remote Sensing. 12 (15), 2478.
Liou, Y.-A., Liu, S.-F., Wang, W.J., 2001. Retrieving soil moisture from simulated brightness temperatures by a neural network. IEEE Transactions on Geoscience and Remote Sensing. 39, 1662–1673.
Liu, J., Araba meri, A., Surabh i Das, CH., Sarkar, P., 2025.An integrated approach for gully erosion susceptibility mapping and factor effect analysis. Advances in Space Research 75 (2025) 3451–3470
Lombardo, L., Cama, M., Conoscenti, C., M¨arker, M., Rotigliano, E.J., 2015. Binary logistic regression versus stochastic gradient boosted decision trees in assessing landslide susceptibility for multiple-occurring landslide events: application to the 2009 storm event in Messina (Sicily, southern Italy). Natural Hazards 79 (3), 1621–1648. https://doi.org/10.1007/s11069-015-1915-3.
Lu, D., Weng, Q.A., 2007. Survey of image classification methods and techniques for improving classification performance. International Journal of Remote Sensing. 28 (5), 823–870.
Madadi A., Saraskanroud P., Marhamat M., 2022. The Role of Soil Characteristics and Topographic Threshold in Gully Erosion in the Shour River Watershed (Mohr County). Quantitative Geomorphological Research, 10(4): 75-95 (in Persian).
Mehraban, M., Golkarian, A. and Khosravi, K. 2018. Evaluation of susceptibility to gully erosion using maximum entropy model )Case study: Shorlouq region of Khorasan Razavi province). Third National Conference on Soil Conservation and Watershed Management, Soil Conservation and Watershed Management Institute, Tehran, Iran.
Moreno, R., Zamora, R., Molina, J.R., Vasquez, A., Herrera, M.A., 2011. Predictive modeling of microhabitats for endemic birds in South Chilean temperate forests using Maximum entropy (Maxent). Ecological Informatics. 6 (6), 364–370. https://doi.org/10.1016/j. ecoinf.2011.07.003.
Nohegar, A and Heidarzadeh, M. 2011. Study of Physico-Chemical Characteristics and Morphometry of Trench Areas Case Study, Gozir, Hormozgan Province, Erosion Research Environmental, No1. (In Persian).
Poesen, J., 2011. Challenges in gully erosion research. Landform Analysis 17, 5–9.
Poesen, J., Nachtergaele, J., Verstraeten, G., Valentin, C., 2003. Gully erosion and environmental change: importance and research needs. Catena 50 (2–4), 91–133.
Poesen, J., Vandaele, K., van Wesemael, B., 1998. Gully erosion: importance and model implications. In: Modelling Soil Erosion by Water. Springer, Berlin, Heidelberg, pp. 285–311.
Qashqaei, A., Nik-Kami, D., Shadfar, S., & Moeini, A. 2011. Zoning of gully erosion in the Taroud Firuzkuh watershed. Geographical Territory Quarterly Journal, 8 (31), 107-119 (in Persian).
Rahmati A., Karnejadi A., Chobin B., Jafari A., Amini A., 2024. Evaluation of the Capability of the Flexible Discriminant Analysis Model in Predicting Flood Susceptibility of the Zarrineh River Watershed. Water and Soil Management Modeling, 4(3): 269-284 (in Persian).
Rahmati o., Kornejady A., Samadi M., C. Deo R., Conoscenti C., Lombardo L., Dayal K., Taghizadeh-Mehrjardi R., Pourghasemi H., Kumar S., Tien Bui D. 2019: PMT: New analytical framework for automated evaluation of geo-environmental modelling approaches. Science of the Total Environment 664 (2019) 296–311.
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, 118–137.
Saeidian H., Shirani K., Salajegheh A., Ahmadi R.; 2023.Performance of the Maximum Entropy Model in Determining the Importance of Environmental Factors in Gully Erosion Initiation in Semi-Arid Regions. Journal of Novel Approaches in Water Engineering and Environment, 2 (1): 129-144 (in Persian).
Schuman, C.D., Birdwell, J.D., 2013. Dynamic artificial neural networks with affective systems. PLoS One 8, e80455.
Servati, M.R. Qudusi, J. Dadkhah, M. 2008. Factors affecting formation and spread of gully erosion in loesses, 21(1): 20 - 33. (In Persian).
Shahbazi,k., Vakili Tajareh, f., 2021. Prioritization of Factors Affecting Gully Erosion and Determination of Sensitive Areas in Kermanshah Province Using the MaxEnt Model, Iranian Journal of Watershed Management Science and Engineering, 15(54): 48-58 (in Persian).
Soleimanpour, S.M., Pourghasemi, H.R., Zare, M., 2021. A comparative assessment of gully erosion spatial predictive modeling using statistical and machine learning models. Catena 207 105679. https://doi.org/ 10.1016/j.catena.2021.105679.
Swets, J.A., 2014: Signal Detection Theory and ROC Analysis in Psychology and Diagnostics: Collected Papers. Psychology Press.
Tajvosi M., Fathollahzadeh T., 2003. A Study of Erosion Types in the Masuleh River Watershed (Gilan Province), Journal of Natural Resources of Iran, 56(3(Serial 1430)): 15-164(in Persian).
Therneau, T.M., Atkinson, B., Ripley, B., 2014. Recursive Partitioning and Regression Trees. R package version. http://CRAN.R-project.org/package=rpart.
Tien Bui, D., Shirzadi, A., Shahabi, H., Chapi, K., Omidvar, E., Thai Pham, B., Talebpour, D., Khaledian, H., Pradhan, B., Panahi, M., Ahmad, B., Rahmani, H, Grof, G. and Lee, S. 2019. A Novel Ensemble Artificial Intelligence Approach for Gully Erosion Mapping in a Semi-Arid Watershed (Iran). Sensors, 19, 2444.
Townsend Peterson, A., Papes¸, M., Eaton, M., 2007. Transferability and model evaluation in ecological niche modeling: a comparison of GARP and Maxent. Ecography 30, 550–560. https://doi.org/10.1111/j.0906-7590.2007.05102.x.
Townsend Peterson, A., Papes¸, M., Eaton, M., 2007. Transferability and model evaluation in ecological niche modeling: a comparison of GARP and Maxent. Ecography 30, 550–560. https://doi.org/10.1111/j.0906-7590.2007.05102.x.
Valentin, C., Poesen, J., Li, Y., 2005. Gully erosion: impacts, factors and control. Catena 63 (2–3), 132–153.
Wang, F., Sahana, M., Pahlevanzadeh, B., Pal, S. C., Shit, P. K., Piran, M. J., Mosavi, A., 2021. Applying different resampling strategies in machine learning models to predict head cut gully erosion susceptibility. Alexandria Engineering Journal, 60(6), 5813-5829. https://doi.org/10.1016/j.aej.2021.04.026.
Wang, Q., Tang, B., Wang, K., Shi, J., Li, M., 2024. Evaluation of the gully erosion susceptibility by using UAV and hybrid models based on machine learning. Soil and Tillage Research. 224 (2), 106218.
Warren, D.L., Seifert, S.N., 2011. Ecological niche modeling in Maxent: the importance of model complexity and the performance of model selection criteria. Ecological Applications. 21(2), 335–342. https://doi.org/10.1890/10-1171.1.
Woodbury, A.D., Render, F.W., Ulrych, T.J., 1995. Practical probabilistic groundwater modeling. Groundwater 33 (4), 532–538.
Yamani, S., M. Zamanzadeh and M. Ahmadi. 2013. Analysis of factors affecting the formation and development of gully erosion: a case study of Kahoor Plain in Fars Province. Geographical Exploration Desert, 1: 53-84 (in Persian).
Zabihi, M., Mirchooli, F., Motevalli, A., Darvishan, A.K., Pourghasemi, H.R., Zakeri, M.A., Sadighi, F., 2018. Spatial modelling of gully erosion in Mazandaran Province, northern Iran. Catena 161, 1–13.
Zhou, G., Li, H., Song, R., Wang, Q., et al., 2022. Orthorectification of Fisheye Image under Equidistant Projection Model. Remote Sensing 14 (17), 4175. https://doi.org/10.3390/rs14174175.
Zhou, G., Tang, Y., Zhang, W., Liu, W., Jiang, Y., Gao, E. Bai, Y., 2023. Shadow Detection on High-Reso lution Digital Orthophoto Map Using Semantic Matching. IEEE Transactions on Geoscience and Remote Sensing, 61. https://doi.org/10.1109/TGRS.2023.3294531.
 Zhou, G., Zhou, X., Chen, J., Jia, G., Zhu, Q., 2022. LiDAR Echo Gaussi an Decomposition Algorithm for FPGA Implementation. Sensors 22 (12), 4628. https://doi.org/10.3390/s22124628.