نشریه علمی - پژوهشی مرتع و آبخیزداری

نوع مقاله : مقاله پژوهشی

نویسندگان

1 گروه احیاء مناطق خشک و کوهستانی، دانشکده منابع طبیعی دانشگاه تهران، کرج، ایران

2 دانشکده مهندسی انرژی و منابع پایدار، دانشکدگان علوم و فناوری‌های میان رشته‌ای دانشگاه تهران، تهران، ایران

10.22059/jrwm.2021.301588.1491

چکیده

سیل یکی از مخرب ترین بلایای طبیعی است که هر ساله باعث تلفات مالی و جانی می شود. تخمین دبی سیلاب یکی از مهم‌ترین عوامل لازم جهت طراحی و اجرای سازه‌های آبی است. در چنین مواردی یکی از راه حل‌های مناسب برای برآورد دبی‌های حداکثر لحظه‌ای با دوره بازگشت‌ های مختلف آنالیز منطقه‌ای سیلاب می‌باشد. به ‌منظور انجام پژوهش حاضر، تعداد 55 ایستگاه آب‌سنجی با دوره مشترک آماری 20 ساله پس از رفع نواقص آماری برای انجام کار در نظر گرفته شدند. سپس بر اساس توزیع لوگ پیرسون نوع سوم با کمترین میزان خطا و بیشترین تعداد رتبه اول به عنوان مناسب ترین تابع برازش، مقدار دبی در دوره بازگشت‌های مختلف برآورد گردید. در ادامه اطلاعات مربوط به انواع متغیرهای فیزیوگرافی، کاربری اراضی، اقلیمی و زمین‌شناسی جمع‌آوری شد. پس از جمع‌آوری اطلاعات مربوط به کلیه متغیرهای مستقل با استفاده از آزمون گاما مهم‌ترین متغیرهای موثر بر دبی‌های حداکثر لحظه‌ای شامل مساحت، تراکم زهکشی، حداکثر بارندگی 24 ساعته و محیط حوزه آبخیز انتخاب و مدل‌سازی با استفاده از روش‌های مدل‌سازی جنگل تصادفی ‌و ماشین بردار پشتیبان در نرم‌افزار R انجام پذیرفت و میزان کارایی این دو روش بر اساس نمایه‌های آماری ضریب تبیین (R2)، ریشه میانگین مربعات خطا (RMSE) و ضریب کارایی ناش و ساتکلیف (CE) مشخص شد. با ضریب کارایی 74 تا 83 درصد، خطای 05/3 تا 11/32 متر مکعب و ضریب تبیین 76 تا 91 نسبت به نسبت به مدل جنگل تصادفی از دقت بالاتری برخوردار می‌باشند.

کلیدواژه‌ها

عنوان مقاله [English]

Regional flood analysis by random forest method in the Namak Lake basin

نویسندگان [English]

  • Saeid Khosrobeigi Bozchelui 1
  • Arash Malekian 1
  • Alireza Moghaddam Nia 1 2
  • Shahra,m Khalighi 1

1 Faculty of Natural Resources, University of Tehran, Karaj, Iran

2 Faculty of Renewable Energies and Environment, University of Tehran, Tehran, Iran

چکیده [English]

Flood is one of the most devastating natural disasters, causing financial and human losses each year. At the same time, many rivers in Iran's watersheds lack complete and accurate statistics and information. On the other hand, estimating the flow of floods is one of the most important factors for the design and implementation of water structures. In such cases, one of the appropriate solutions to estimate the maximum flow rate with different return periods is flood analysis. In order to conduct the present study, 55 hydrometric stations with a common statistical period of 20 years were considered to perform the work after the statistical deficiencies were eliminated. Then, based on the distribution of the third type of Pearson logo with the lowest error rate and the highest number of first rank as the most suitable fit function, the amount of discharge in different return periods was estimated. The following information was collected on the types of physiography, land use, climate and geology variables. After collecting information about all independent variables using Gamma test, the most important variables affecting the maximum instantaneous flow, including area, drainage density, maximum 24-hour rainfall and watershed environment, were selected and modeled using methods. Random forest modeling and support vector modeling were performed and their efficiency was determined based on statistical indicators With an efficiency coefficient of 74 to 83%, the error of 3.05 to 32.11 m3 and the coefficient of explanation of 76 to 91 are more accurate than the random forest model.

کلیدواژه‌ها [English]

  • Gamma test
  • Lo Pearson III distribution
  • Return period
  • Maximum instantaneous discharge
  • Support vector machine
Aziz, K., Haque, M. M., Rahman, A., Shamseldin, A. Y., & Shoaib, M. (2017). Flood estimation in ungauged catchments: application of artificial intelligence-based methods for Eastern Australia. Stochastic Environmental Research and Risk Assessment, 31(6), 1499–1514.
Aziz, K., Rahman, A., Shamseldin, A.Y., & Shoaib, M. (2014). Co-Active Neuro Fuzzy Inference System for Regional Flood Estimation in Australia. Journal of Hydrology and Environment Research, 1(1): 11-20.
Besalatpour, A., Haj Abbasi, M. A., & Ayoubi S. A. (2013). Using gamma test to select the optimal inputs in soil shear strength modeling using artificial neural networks. Journal of Research Water and Soil Protection, 20 (1): 97-114. (In Persian).
Chua, K.W., Wu, C.L., & Li, Y.S. (2005). Comparison of several flood forecasting models in Yangtze River. Journal of Hydrologic Engineering, 10, 485–491.
Du, J., Fang, J., Xu, W., & Shi, P. (2013). Analysis of dry/wet conditions using the standardized precipitation index and its potential usefulness for drought/flood monitoring in Hunan Province, China. Stochastic Environmental Research and Risk Assessment, 27, 377–387.
Durocher, M., Chebana, F., & Ouarda, T. B. M. J. (2015). A Nonlinear Approach to Regional Flood Frequency Analysis Using Projection Pursuit Regression. Journal of Hydrometeorology, 16(4), 1561– 1574.
Echogdali, F. Z., Boutaleb, S., Elmouden, A., & Ouchchen, M. (2018). Assessing Flood Hazard at River Basin Scale: Comparison between HECRAS-WMS and Flood Hazard Index (FHI) Methods Applied to El Maleh Basin, Morocco. Journal of Water Resource and Protection10(9), 957-977.‏
Hailegeorgis, T. T., & Alfredsen, K. (2017). Regional flood frequency analysis and prediction in ungauged basins including estimation of major uncertainties for mid-Norway. Journal of Hydrology, 27, 377–387.
Kisi, O., Shiri, J., & Tombul M. (2013). Modeling Rainfall-Runoff Process Using Soft Computing Techniques. Computers & Geosciences, 51, 108-117.
Kornejady, A., Heidary, K., Sarparast, M., Khosravi, G., & Mombeini, M. (2014). Performance Assessment of Two “LNRF” and “AHP-Area Density” Models in landslide Susceptibility Zonation. American Journal of Biomedical and Life Sciences, 4, 169–176.
Negaresh, H., Ajdari Moghaddam, M., & Armesh M. (2013). Application of artificial neural network in simulation and flood prediction in Sarbaz Watershed. Journal of Geography and Development, 31: 15-28.
Nikoo, M., Ramezani, F., Hadzima-Nyarko, M., Nyarko, E.K., & Nikoo, M. (2016). Flood-routing modeling with neural network optimized by social-based algorithm. Natural Hazards, 128-152
Panahi, A., & Alijani, B. (2013). Predicting Dubai Peak Flood Using Artificial Neural Network Modeling and Multivariate Regression (Madarsoo Watershed of Golestan Province). Geography (International Quarterly of the Geographical Society of Iran), 11 (38): 113-132. (In Persian).
Pierdicca, N., Pulvirenti, L., Chini, M., Guerriero, L., & Ferrazzoli, P. (2010). A fuzzy-logic-based approach for flood detection from cosmo- skymed data Dept. Information, Electronic and Telecommunications Engineering, Sapienza University of Rome.
Pourghasemi, H.R., & Kerle, N., (2016). Random forests and evidential belief function-based landslide susceptibility assessment in Western Mazandaran Province, Iran. Environmental Earth Sciences, 75, 1–17.
Rahman, A., Charron, C., Ouarda, T. B., & Chebana, F. (2018). Development of regional flood frequency analysis techniques using generalized additive models for Australia. Stochastic Environmental Research and Risk Assessment, 32(1), 123-139.
Sahoo, G.B., Schladow, S.G., & Reuter, J.E. (2009). Forecasting stream water temperature using regression analysis, artificial neural network, and chaotic non-linear dynamic models. Journal of Hydrology, 378, 325–342.
Sivapalan, M., & Bloschi G. (1997). Transformation of point rainfall to areal rainfall: intensity-duration-frequency curves. Journal of Hydrology, 98(240): 150-167.
Vafkhah, M. (1998). Estimation of the abundance of regional currents of the minimum seasonal rivers (study in the arid regions of central Iran), Bachelor's degree in watershed management. Tarbiat Modares University, 145 p. (In Persian).
Xiong, F., Guo, S., Chen, L., Yin, J., & Liu, P. (2018). Flood Frequency Analysis Using Halphen Distribution and Maximum Entropy. Journal of Hydrologic Engineering, 23(5),
Youssef, A.M., Pradhan, B., & Hassan, A.M. (2011). Flash flood risk estimation along the St. Katherine Road, southern Sinai, Egypt using GIS based morphometry and satellite imagery. Environmental Earth Sciences, 62, 611–623.
Zakaria, A.Z., & Shabri A. (2012). Streamflow Forecasting at Ungaged Sites using Support Vector Machines. Applied Mathematical Sciences, 60(6), 3003-3014.