تهیه نقشه مدیریت سیلاب با استفاده از الگوریتم نوین جنگل تصادفی و سیستم اطلاعات جغرافیایی، نمونه موردی: محور کندوان - چالوس

نوع مقاله : پژوهشی

نویسندگان

1 استاد گروه ژئومورفولوژی، گروه جغرافیا، دانشکده علوم اجتماعی،دانشگاه محقق اردبیلی، اردبیل،

2 2- دانشجوی دکتری گروه جغرافیای طبیعی( گرایش ژئومورفولوژی ، دانشکده علوم اجتماعی، دانشگاه محقق اردبیلی

چکیده

در طی سال‌های اخیر محور کندوان - چالوس در شمال کشور (در استان مازندران ) سیلاب‌های متعدد مخاطره‌آمیز رخ داده است. ویژگی‌های زمین‌شناسی و توپوگرافی، شرایط بارندگی و دخالت انسانها، محور کندوان -چالوس را برای پتانسیل خطر وقوع سیل مستعد کرده است. علاوه بر نقش عوامل طبیعی؛ عدم لایروبی، نبود آبخیزداری مناسب و دخالتهای غیر اصولی انسانی منجر به تشدید مخاطرات سیلاب در منطقه مورد تحقیق شده است. بررسی و تهیه نقشه‌های مدیریت سیلاب, با تکیه بر اصول کارشناسی یکی از ضروریات اساسی در مدیریت بحران سیل این منطقه محسوب می‌باشد. هدف از این پژوهش، پهنه‌بندی مناطق مستعد سیل‌ و تعیین اولویت عوامل مؤثر در وقوع آن با استفاده از الگوریتم جنگل تصادفی در محور کندوان چالوس است. بدین منظور ۹ شاخص کاربری اراضی، فاصله از رودخانه، شیب، ارتفاع، عدم رعایت حریم رودخانه، دبی رودخانه، شبکه آبراهه، بارش، و عدم لایروبی رودخانه انتخاب شدند. پس از تعیین عامل تورم واریانس و ضریب تحمل، در مرحله بعد با واردکردن داده‌های مربوط به عوامل مؤثر به نرم‌افزار ARC/MAP10.2، مدل‌سازی گردید. سپس با استفاده از الگوریتم جنگل تصادفی انجام و نقش عوامل مؤثر در وقوع سیلاب در منطقه تعیین شد. در نهایت نقشه پهنه‌بندی خطر وقوع سیلاب در سه پهنه خیلی خطرناک ، با خطر متوسط و کم‌خطر در محیط ARC/MAP10.2 تهیه شد. نتایج نشان می‌دهد بر اساس نقشه پتانسیل‌‌‌وقوع سیل، خطر وقوع سیلاب منطقه در حدود۲۶۱.۴۳ کیلومترمربع منطقه جزء مناطق کم‌خطر ۱۵۱.۱ کیلومترمربع جزء مناطق با خطر متوسط و در حدود ۱۱۸.۳کیلومترمربع جزء مناطق پرخطر محسوب می‌شوند.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Flood Management Map Using New Random Forest Algorithm and Geographic Information System: Case Study: Kandovan-Chalus Axis

نویسندگان [English]

  • Mousa Abedini 1
  • Mahrokh sardashti 2
1 Professor in Geomorphology Faculty social science University of Mohaghegh Ardabili Ardabil
2 2- PhD Student of Geomorphology, Dept. of Physical Geography, University of Mohaghegh Ardabili
چکیده [English]

In recent years, the Kandovan-Chalus axis in the north of the country (in Mazandaran province) has experienced numerous dangerous floods. Geological and topographic features, precipitation and human intervention have made the Kandovan-Chalus axis susceptible to potential flood risks. In addition to natural factors; lack of dredging, lack of proper watershed management and unprincipled human interventions have led to an increase in flood risks in the researched area. The aim of this research is to zone flood-prone areas and determine the priority of factors affecting their occurrence using the random forest algorithm in the Kandovan-Chalus axis. For this purpose, 9 land use indicators were selected: distance from the river, slope, height, failure to observe the river boundary, river discharge, waterway network, rainfall, and lack of river dredging. After determining the variance inflation factor and tolerance coefficient, in the next stage, modeling was carried out by entering the data related to the effective factors into the ARC/MAP10.2 software. Then, the random forest algorithm was used to determine the role of the effective factors in the occurrence of floods in the region. Finally, a flood risk zoning map was prepared in three very dangerous, medium-risk, and low-risk zones in the ARC/MAP10.2 environment. The results show that based on the flood potential map, the risk of flooding in the region is about 261.43 square kilometers of the region, 151.1 square kilometers of the region are considered low-risk areas, 118.3 square kilometers of the region are considered medium-risk areas, and about 118.3 square kilometers

کلیدواژه‌ها [English]

  • Random Forest Algorithm
  • Precipitation
  • Flood
  • Slope
  • Land Use
Abdelkarim, A & Gaber, A.F.D. (2019). Flood risk assessment of the Wadi Nu’man basin, Mecca, Saudi Arabia (during the period,1988–2019) based on the integration of geomatics and hydraulic modeling: a case study, Water11(9): pp.1887. (In Persian)
Abedini, M., Faal Naziri, M., Piroozi, Elnaz. (2023). Flood risk assessment and zoning using multi-criteria ARAs and unit hydrograph techniques. Case study: upstream basin of Hydrometer Station Pol Sultan Meshkinshahr. Journal of Natural Environmental Hazards, 12 (35): pp. 115-137. (In Persian)
Abedini, M., Piroozi, E., Aghayari, L. (2022), Zoning of flood risk in the Razi Chay watershed using the VIKOR model, Crisis Management, No. 22:  pp. 186-197. (In Persian)
Abedini, M., Sabouri, H and Pasban, A.H. (2015). Zoning of flood risk and its relationship with land use using the network analysis process model (Case study: Razichai watershed, Ardabil province). Quarterly Journal of Sustainable Urban and Regional Development Studies, 6(2): pp.68-84. (In Persian)
Avand, M., Janizadeh, S., &Jaafari, F. (2018). Evaluating the efficiency of machine learning models in preparing a possible flood risk map, Journal of Natural Lands Destruction and Restoration, 1(1): pp.1-32(In Persian)
Beheshti, M., Feiznia, S & Ahmadi, H. (2009). Investigation of Landslide Zoning Efficiency of Safety Factor: A Case Study of Moallem Kalayeh Watershed, Physical Geography Quarterly2 (5): pp. 20-32. (In Persian)
Chen, W., Xiaoshen, X., Jianbing, P., Himan, Sh., Haoyuan, H; Dieu, T. B., Zhao, D., Shaojun, L., & A-Xing, Z. (2018). GIS-based landslide susceptibility evaluation using a novel hybrid integration approach of bivariate statistical based random forest method, Journal Catena, No 164: PP.135–149.
Chen, W., Li, Y., Xue,W.,Shahabi,H.,Li,S.,Hong, H.,& Ahmad, B.B.(2020). Modeling Flood Susceptibility Using Data Driven Approaches of Naïve Bayes tree, Alternating Decision Tree, and Random Forest Methods.Science of The Total Environment ,701: pp.134979.
Demisi, Z., imal, P., Seyoum M.W., Dutta, A.& Rimmington, G. (2024). Flood susceptibility mapping: ntegrating machine learning and GIS for enhanced risk assessment, Applied Computing and Geosciences,23 pp. 100183.
Ebrahimi, L. (2020). Preparation of Flood Hazards Management Map Using a New Random Forest Algorithm (Case Study: Lavasanat Watershed), Natural Hazards,7(2), Summer: pp.188-196.
Ebadati, B., Attarzadeh, R, Alikhani, M., Youssefi, F., Pirasteh, S. (2024). Efficient Flood Detection through Hybrid Machine Learning and Metaheuristic Methods using Sentinel-1, Int. Arch. Photogramm. Remote Sens. Spatial Inf. Sci., XLVIII-3/W3: pp.35–43. (In Persian)
 Esmaeili, R; Nourizadeh Nashli, N. (2024). Evaluation of morphological changes in the Haraz River due to human pressures in the area of Amol city, Mazandaran. Hydrogeomorphology, Volume 11, Number 40: pp. 43-57. (In Persian)
Fenicia, F., Kavetski, D., Savenije, H.H. G., Clark, M. P., Schoups, G., Pfister, L., & Freer, J. (2014). Catchment properties, function, and conceptual model representation: Is there a correspondence? Hydrological Processes, 28(4): pp. 2451-2467.
Hagen, E.J.F., Shrodr Jr., Lu, John, X.X., &. Teufert, F. (2010). Reverse engineered flood hazard mapping in fghanistan: A parsimonious flood map model for developing Countries.Quaternary International: PP. 1-10.
Huang, Y., Bardossy, A., & Zhang, K. (2019). Sensitivity of hydrological models to temporal and spatial resolutions of rainfall data, Hydrol. Earth Syst. Sci. 23: PP.2647–2663.
Islaminejad, S.A., Aftakhari, M., Akbari, M., Haji Eliasi, A. & Farhadian, Hadi. (2021). Prediction of flood prone areas using advanced machine learning models (Dasht Birjand), Journal of Water Resources and Irrigation Management 11(4): pp. 885-904. (In Persian)
Kakavand, M; Haghzadeh, A; Seimani Motlagh, M. (2024). Natural Environment Hazards, Volume 13 - Issue 40: pp.59 – 41.
Kazemi, H., Mansouri, N., & Jozi, S. A. (2022). Flood Risk Zoning in Nowshahr City Using Machine Learning Models.JHRE,40(176): pp.71-86. (In Persian)
Khodai, A., & Zandi, R. (2022). Zoning of flood risk based on multi-criteria decision making and neural network model, case study: Khodaafrin watershed, Watershed Engineering and Management, 14(4): pp. 562-549. (In Persian)
Liu, M., Chen, N., Zhang, Y., & Deng, M. (2020). Glacial Lake inventory and lake outburst flood/debris flow hazard assessment after the Gorkha earthquake in the Bhote Koshi basin, Water 12: pp. 464.
Milanesi, L., M. Pilotti & R. Ranzi.) 2015(. A conceptual model of people's vulnerability to floods. Water Resources Research, 51(1): pp. 182-197
Mugagga F., Kakembo, V., & Buyinza, M. (2012). Land use changes on the slopes of Mount Elgon and the implications for the occurrence of landslides. Catena 90: pp.39–46.
Parvin, M. (2018). Evaluation and Zoning of Flash Flood Risk Based on MFFPI Model (Case Study: West Islamabad Basin), Journal of Environmental Hazards (Former Risk Knowledge), 6(2): pp. 169-184. (In Persian)
Pregnolato, M., Ford, A., Wilkinson, S.M., & Dawson, R.J. (2017). The impact of flooding on road transport: a depth-disruption function, Transp. Res. D Transp. Environ. 55: pp.67–81.
Rahimpour, T., Rezaei Moghadam, M. H., Hijazi, S.A., & Valizadeh Kamran, K. (2023). Flood Susceptibility Modeling in the Aland Chai Basin based on a new ensemble classification approach (FURIA-GA-LogitBoost). Journal of Geography and Environmental Hazards, 12(1): pp.1-24. (In Persian)
Rezaei Moghaddam, M. H., Yasi, M., Nikjoo, M. R, & Rahimi, M. (2018). Zoning and Morphological Analysis of Gharesou River Flood Using HEC-RAS Hydrodynamic Model (From Pirazmian Village to Aharchay River Confluence). Journal of Geography and Environmental Hazards,7(25): PP.1-15. (In Persian)
Soleimani, K., Ali Dadganfard, F., & Pourqasmi, H. (2018). Comparison of Shannon Entropy Data Mining Techniques and Random Forest Algorithm in Preparing Jahrom Groundwater Potential Map", Journal of Desert Ecosystem Engineering, 8(24): pp.37-48. (In Persian)
Talebi, A; Godarzi, S., & Pourqasmi, H. (2017). Evaluation of the possibility of preparing a landslide risk map using random forest algorithm (study area: Sardar Abad watershed, Lorestan province), Journal of Natural Environment Hazards,7 (16): pp.45-64. (In Persian)
Valizadeh Kamran, Kh.)2007(. Application of GIS in flood risk zoning. Journal of Geographical Space, 20: pp.170-153. (In Persian)
 Yousefi, H., Younisi, H., Davoudi, D., Arshiya, Azadeh, & Shamsi, Z. (2021). Determining flood potential using CART, GLM and GAM machine learning models (case study, Kashkan Basin) Journal Scientific and research journal of irrigation and water engineering in Iran, 12(4): pp.84-105. (In Persian)
Wang, Y., Fang, Z., Hong, H., & Peng, L. (2022). Flood Susceptibility Mapping Using Convolution Neural Network Frameworks. Jornal of Clinical Epidemiology, 63(8): pp.826-833.