مقایسه عملکرد الگوریتم‌های یادگیری ماشین در پهنه‌بندی حساسیت سیلاب حوضه ‏آبخیز دوست‌بیگلو

مقالات آماده انتشار

نوع مقاله : مقاله پژوهشی

نویسندگان

صیاد اصغری سراسکانرود

مهدی فروتن

گروه جغرافیای طبیعی، دانشکده علوم اجتماعی، دانشگاه محقق اردبیلی، اردبیل، ایران

10.22067/geoeh.2026.99615.1679

چکیده

این پژوهش با هدف مقایسه عملکرد الگوریتم‌های یادگیری ماشین شامل جنگل تصادفی (‏RF‏)، گرادیان تقویت درختی (‏GTB‏)، ‏‏‏ماشین بردار پشتیبان (‏SVM‏) و نزدیک‌ترین همسایه (‏KNN‏) در پهنه‌بندی حساسیت سیلاب حوضه آبخیز دوست‌بیگلو، انجام گرفت. مجموعه‌ای از عوامل مؤثر بر سیلاب، شامل ارتفاع، شیب، ‏‏‏رواناب، بارش، شاخص توان آبراهه (‏SPI‏)، شاخص رطوبت توپوگرافی (‏TWI‏)، تراکم آبراهه‌ها و جاده‌ها، پوشش گیاهی (‏NDVI‏)، ‏‏‏بافت خاک، سازند زمین و کاربری اراضی، تحلیل شدند ؛ سپس نقشه‌های ‏‏‏حساسیت سیلاب در پنج طبقه خطر تهیه و دقت آن‌ها ‏‏‏با منحنی ‏ROC‏ و شاخص ‏AUC‏ ارزیابی شد. نتایج نشان داد که عوامل شیب، کاربری اراضی و پوشش گیاهی درصد بیشترین تأثیر را در فرآیند یادگیری مدل‌ها داشته‌اند. مدل‌های ‏RF، ‏GTB، ‏SVM‏ و ‏KNN، نواحی شرقی، ‏‏‏شمالی و بخش‌هایی از دامنه‌های غربی سبلان را عمدتاً در طبقات خطر زیاد و خیلی زیاد طبقه‌بندی نمودند. در این میان، مدل ‏‏‏جنگل تصادفی با ‏AUC‏ برابر 98/0، بالاترین دقت را در تفکیک مناطق سیل‌خیز به ثبت رساند. این مدل، 42/21 درصد از مساحت منطقه را در طبقه پرخطر سیلاب قرار داد. سایر مدل‌ها ‏GTB، ‏SVM‏ و ‏KNN‏ نیز ‏‏‏به ترتیب با مقدار ‏AUC‏ برابر با 97/0‏‎، 95/0 و 94/0 در رتبه‌های بعدی قرار گرفتند و عملکرد قابل قبولی نشان دادند.‏

کلیدواژه‌ها

سیلاب

‏Random Forest ‏,SVM, GTB, ‎KNN شمال غرب ایران

موضوعات

• مخاطرات ژئومورفیک-هیدرولوژیک

---

©2026 The author(s). This is an open access article distributed under Creative Commons Attribution 4.0 International License (CC BY 4.0)

 

 مراجع

مراجع

Abdollahzadeh Bina, A., & Fard Moradinia, S. (2024). A novel approach to flood risk zonation: Integrating deep learning models with APG in the Aji Chay catchment. Aqua - Water Infrastructure, Ecosystems and Society, 73(7), 1333–1357. https://doi.org/10.2166/aqua.2024.023

Ait Naceur, H., Igmoullan, B., & Namous, M. (2025). Machine learning-based optimization of flood susceptibility mapping in semi-arid zone. DYSONA–Applied Science, 6(1), 145–159. http://dx.doi.org/10.30493/das.2024.483211

Arora, A., Durga, P. G., Pandey, M., & Arabameri, A. (2025). Machine learning model optimization for flood susceptibility zonation over the Kosi megafan, Himalayan foreland basin, India. Scientific Reports, 15, 32757. https://doi.org/10.1038/s41598-025-07403-w

Asghari Saraskanrood, S., & Frotan, M. (2025). Assessing the flood potential of the Khiaochay watershed using the MFFPI model and spectral indices. Journal of Natural Environmental Hazards, 15(2), 1–1. [In Persian] https://doi.org/10.22111/jneh.2025.51600.2109

Ashkriz, O., Falahati, F., & Garakani, A. (2024). Detection of flood zones using machine learning algorithms and remote sensing to determine the area of land under flood damage (Case study: March 2019 flood in Aqqla city). Journal of Spatial Analysis Environmental Hazards, 11(3), 21–34. [In Persian] http://dx.doi.org/10.61186/jsaeh.11.3.1

Asrade, T. M., Abebe, S. A., Tadesse, K. B., Kerebih, M. S., & Meshesha, T. M. (2026). Flood susceptibility assessment using three machine learning techniques and comparison of their performance. Scientific Reports. https://doi.org/10.1038/s41598-026-38391-0

Avand, M., Janizadeh, S., & Jafari, F. (2020). Evaluating the efficiency of machine learning models in preparing flood probability mapping. Degradation and Rehabilitation of Natural Land, 1(1), 19–32. [In Persian] https://dor.isc.ac/dor/20.1001.1.27174425.1399.1.1.4.3

Beven, K. J., & Kirkby, M. J. (1979). A physically based, variable contributing area model of basin hydrology. Hydrological Sciences Bulletin, 24(1), 43–69. https://doi.org/10.1080/02626667909491834

Breiman, L. (2001). Random forests. Machine Learning, 45(1), 5–32. https://doi.org/10.1023/A:1010933404324

Choubin, B., Moradi, E., Golshan, M., Adamowski, J., Sajedi-Hosseini, F., & Mosavi, A. (2019). An ensemble prediction of flood susceptibility using multivariate discriminant analysis, classification and regression trees, and support vector machines. Science of The Total Environment, 651(2), 2087–2096. https://doi.org/10.1016/j.scitotenv.2018.10.064

Cortes, C., & Vapnik, V. (1995). Support-vector networks. Machine Learning, 20(3), 273–297. https://doi.org/10.1007/BF00994018

Cover, T. M., & Hart, P. E. (1967). Nearest neighbor pattern classification. IEEE Transactions on Information Theory, 13(1), 21–27. https://doi.org/10.1109/TIT.1967.1053964

Esmali Ouri, A., Golshan, M., & Khorrami, K. (2016). Prioritization of suitable axes for construction of underground dam in the Doostbeiglou watershed. Physical Geography Research, 48(4), 645–659. [In Persian] https://doi.org/10.22059/jphgr.2016.60834

Feizbahr, M., Brake, N., Arbabkhah, H., Hariri Asli, H., & Woods, K. (2025). Flood susceptibility mapping using machine learning and geospatial-Sentinel-1 SAR integration for enhanced early warning systems. Remote Sensing, 17(20), 3471. https://doi.org/10.3390/rs17203471

Friedman, J. H. (2001). Greedy function approximation: A gradient boosting machine. The Annals of Statistics, 29(5), 1189–1232. https://doi.org/10.1214/aos/1013203451

Ghosh, S., Saha, S., & Bera, B. (2022). Flood susceptibility zonation using advanced ensemble machine learning models within Himalayan foreland basin. Natural Hazards Research. https://doi.org/10.1016/j.nhres.2022.06.003

Hajji, S., Krimissa, S., Abdelrahman, K., Boudhar, A., Elaloui, A., Ismaili, M., … & Namous, M. (2025). Enhancing flood prediction through remote sensing, machine learning, and Google Earth Engine. Frontiers in Water, 7, 1514047. https://doi.org/10.3389/frwa.2025.1514047

Hanifinia, A., & Abghari, H. (2025). Predicting flood-prone areas using generalized linear and maximum entropy machine learning models. Journal of Natural Environmental Hazards, 14(43), 19–34. [In Persian] https://doi.org/10.22111/jneh.2024.47730.2021

Hassan, S., Samantaray, S., Annayat, W., & Satapathy, D. P. (2026). Flood Susceptibility Assessment in the Jhelum Basin Using Machine Learning and GIS Techniques. Natural Hazards Review, 27(3). https://doi.org/10.1061/NHREFO.NHENG-2672

Janizadeh, S., Avand, M., Jaafari, A., Phong, T. V., Bayat, M., Ahmadisharaf, E., … & Lee, S. (2019). Prediction success of machine learning methods for flash flood susceptibility mapping in the Tafresh watershed, Iran. Sustainability, 11(19), 5426. https://doi.org/10.3390/su11195426

Javan, F., Jamini, D., & Atashbahar, R. (2026). Application of machine learning algorithms in flood risk management with emphasis on tourist-oriented rural settlements (Case study: the Bisotun tourist sample area, Kermanshah Province). Journal of Geography and Environmental Hazards, 15(1), 226–250. [In Persian] https://doi.org/10.22067/geoeh.2025.95982.1616

Kahrizi, A., Izadbakhsh, M. A., Shabanlou, S., & Yosefvand, F. (2023). Investigation the effect of different number of presence points, raster resolution and sample size scenarios on the groundwater potential map prediction using data mining model in Namroud catchment, Tehran. Iranian Journal of Soil and Water Research, 54(5), 713–736. [In Persian] https://doi.org/10.22059/ijswr.2023.325058.668989

 Karami, P., Eslamnezhad, S. A., Eftekhari, M., Akbari, M., & Rastgoo, M. (2023). Flood susceptibility zoning using machine learning improved by genetic algorithm. Journal of Natural Environment, 76(1), 43–60. [In Persian] https://doi.org/10.22059/jne.2022.350170.2485

Kazemi, H., Mansouri, N., & Jozi, S. A. (2021). Flood risk zoning in Nowshahr city using machine learning models. JHRE, 40(176), 71–86. [In Persian] https://doi.org/10.22034/40.176.71

Kazemi, M., & Jafarpoor, A. (2024). Identifying the threshold of variables affecting flood zones using machine learning technique (Case study: the downstream region of the Karun River). Water and Soil Management and Modelling, 4(1), 214–232. [In Persian] https://doi.org/10.22098/mmws.2023.12285.1220

Khosravi, K., Pham, B. T., Chapi, K., Shirzadi, A., Shahabi, H., Revhaug, I., … & Bui, D. T. (2018). A comparative assessment of decision trees algorithms for flash flood susceptibility modeling at Haraz watershed, northern Iran. Science of the Total Environment, 627, 744–755. https://doi.org/10.1016/j.scitotenv.2018.01.266

Kordi, A., Sadoddin, A., Mohammadi, G., Sheikh, V., & Asadi Nalivan, O. (2025). Zoning of flash flood generation probability using machine learning techniques (A case study: Karaj Dam Watershed, Iran). Desert Ecosystem Engineering, 14(46), 91–107. [In Persian] https://doi.org/10.22052/deej.2025.256422.1098

Liu, Y., Liu, L., Sun, H., Chen, B., Ma, X., Ning, Y., & Qi, S. (2025). Flood risk assessment combining machine learning with multi-criteria decision analysis in Jiangxi Province, China. International Journal of Disaster Risk Science, 16, 858–869. https://doi.org/10.1007/s13753-025-00423-1

Martinis, S., Plank, S., & Ćwik, K. (2018). The use of Sentinel-1 time-series data to improve flood monitoring in arid areas. Remote Sensing, 10(4), 583. https://doi.org/10.3390/rs10040583

Mukomberanwa, N. T., & Madamombe, H. K. (2025). Next generation data-driven flood susceptibility modelling with spatial machine learning. Scientific African, 30, e03082. https://doi.org/10.1016/j.sciaf.2025.e03082

Naemitabar, M., Zanganeh Asadi, M. A., & Boroughani, M. (2025). Flood susceptibility mapping in the semi-arid region of Tabas using machine learning algorithms. Journal of Arid Regions Geographic Studies, 16(61), 46–67. [In Persian] https://doi.org/10.22034/jargs.2025.509539.1182

Rahmati, M., Balenzano, A., Bechtold, M., Brocca, L., Fluhrer, A., Jagdhuber, T., … & Montzka, C. (2026). Soil moisture retrieval from Sentinel-1: Lessons learned after more than a decade in orbit. Remote Sensing of Environment, 333, 115146. https://doi.org/10.1016/j.rse.2025.115146

Rezaei Moghaddam, M. H., Karami, F., & Abazari, K. (2023). Assessment and zoning of flash flood risk in Ojan Chai basin by MFFPI model. Journal of Hydrogeomorphology, 10(36), 138–157. [In Persian] https://doi.org/10.22034/hyd.2023.57462.1701

Shirzadi, A., Salvati, A., Hajizadeh Tahan, M., Shahabi, H., Jafari Nodoushan, E., Ramezani, M., … & Clague, J. J. (2025). Urban flood susceptibility mapping using deep and machine learning algorithms as a management tool: A case study of Sanandaj city, Iran. Ecological Indicators, 178, 113886. https://doi.org/10.1016/j.ecolind.2025.113886

Siddiquie, K. T., & Nafi, A. M. (2025). Flood hazard zonation using 2D HEC-RAS and explainable machine learning in urban watersheds. Research Journal in Civil, Industrial and Mechanical Engineering, 2(2), 112–130. https://doi.org/10.61424/rjcime.v2i2.631

Yousefi, H., Yonesi, H. A., Davoudimoghadam, D., Azadeh, A., & Shamsi, Z. (2022). Determination of Flood potential Using CART, GLM and GAM Machine learning Models. Journal of Irrigation and Water Engineering, 12(48), 84–105. [In Persian] https://doi.org/10.22125/IWE.2022.150684