پیش بینی رسوب معلق با استفاده از داده های هیدرولوژیک و هیدروژئومورفیک در مدل های هوشمند

نوع مقاله : مقاله پژوهشی

نویسندگان

1 دانشجوی دکترای گروه مهندسی آبخیزداری/ دانشگاه علوم کشاورزی و منابع طبیعی ساری، ایران.

2 دانشیار / گروه مهندسی آبخیزداری، دانشگاه علوم کشاورزی و منابع طبیعی ساری، ایران.

3 استاد / علوم زمین و محیط زیست، دانشگاه آسیای میانه، تاجیکستان.

4 دانش آموخته دکترای گروه مهندسی برق/دانشگاه صنعتی خواجه نصیرالدین طوسی، ایران.

چکیده

برآورد دقیق مقدار رسوبات حمل شده توسط رودخانه ها، در مدیریت منابع آب از اهمیت بسیاری برخوردار است. بنابراین شناسایی و پیشنهاد مدلهای مناسب جهت برآورد رسوب معلق از اهداف مهم تلقی میشود که استفاده از روش نوین مدلهای هوشمند از جمله شبکه عصبی مصنوعی و رگرسیون بردار پشتیبان در این زمینه تحول عظیمی وجود آورده است. یک گام مهم در مدلسازی رسوب معلق با استفاده از این مدلها، انتخاب ورودیهای مناسب میباشد، زیرا ساختار و نتایج مدل را تحت تاثیر قرار میدهند. با توجه به اینکه در اکثر مطالعات در زمینه برآورد رسوب معلق با استفاده از مدلهای داده محور، تنها از متغیرهای اقلیمی و هیدرولوژیکی به عنوان متغیرهای تخمینگر استفاده گردیده است. بنابراین پژوهش حاضر به منظور تعیین متغیرهای ژئومورفولوژیکی اثرگذار و قابل دسترس در تخمین رسوب معلق در حوضه آبخیز تمر طراحی گردید. برای دستیابی به این هدف، نقش شاخص اتصال رسوبی به عنوان یک ورودی هیدروژئومورفیک علاوه بر ورودیهای هیدرولوژیکی با استفاده از مدلهای مذکور در تخمین رسوب معلق مورد ارزیابی قرار گرفت. مقایسه نتایج الگوهای ورودی مختلف نشان داد که شاخص اتصال رسوبی به همراه متغیرهای هیدرولوژیکی کارایی مدلها را بهبود میدهد و این بهبود به صورت کاهش (9/63% و 26/36%) در مجذور میانگین مربعات خطا و افزایش قابل توجه (25/80% و 21/85%) در ضریب کارایی ناش_ساتکلیف و (13/20% و 45/94%) در ضریب تبیین به ترتیب در مدلهای شبکه عصبی مصنوعی و رگرسیون بردار پشتیبان میباشد. نتایج این پژوهش با توجه به برآورد دقیقتر رسوب معلق در طراحی و مدیریت منابع آب با ارزش میباشد.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Prediction of Suspended Sediment Using Hydrologic and Hydrogeomorphic Data within Intelligence Models

نویسندگان [English]

  • Haniyeh Asadi 1
  • Kaka Shahedi 2
  • Roy C. Sidle 3
  • Seyed Mostapha Kalami Heris 4
1 PhD Student, Department of Watershed Management Engineering, Sari Agricultural Sciences and Natural Resources University, Iran.
2 Associate Professor, Department of Watershed Management Engineering, Sari Agricultural Sciences and Natural Resources University, Iran.
3 Director of Mountain Societies Research Institute and Professor of Earth and Environmental Sciences, University of Central Asia, Tajikistan.
4 PhD Graduate, Faculty of Electrical Engineering, K.N.Toosi University of Technology, Iran.
چکیده [English]

Accurate estimation of transported sediment by rivers plays an important role in water resources management. So the selection of proper methods for estimation of suspended sediment is an important objective. In this regard, application of intelligence models (e.g., ANN, SVR) have substantially improved the prediction of suspended sediment. An important step in suspended sediment modeling using these models is, the proper input selection because input vectors determine the structure of the model and, hence, can influence model results. In the most studies, only climatic and hydrological variables have been used as suspended sediment estimators using data-driven models. Therefore, this study was designed to determine effective and accessible geomorpholigical variables based on hydrologic understanding in suspended sediment estimation for the Tamar catchment. To accomplish this goal, the effect of an Index of Connectivity (IC) as a hydrogeomorphic input, in addition to the hydrologic inputs, using ANN and SVR models was investigated. Comparison of results indicated that using IC along with hydrological inputs improve models efficiency and this improvement is indicated by decrease in the root mean squared error (9.63% and 26.36%) and a noticeable increase in the Nash–Sutcliffe efficiency (25.80% and 21.85%) and in the coefficient of determination (13.20% and 45.94%) for ANN and SVR models, respectively. These results are valuable for water resources planning and management.

کلیدواژه‌ها [English]

  • Suspended sediment modeling
  • Artificial Neural Network
  • Support vector regression
  • Index of Sediment Connectivity
Araghinejad Sh, Karamouz M (2005) Long-lead streamflow forecasting using artificial neural networks and fuzzy inference system. Iran-Water Resources Research 1(2):29-41 (In Persian)
Asadi H, Shahedi K, Jarihani B, Sidle RC (2019) Rainfall-runoff modelling using hydrological connectivity index and artificial neural network approach. Water 11(2):212
Borselli L, Cassi P, Torri D (2008) Prolegomena to sediment and flow connectivity in the landscape: A GIS and field numerical assessment. Catena 75(3):268-277
Bracken LJ, Wainwright J, Ali GA, Tetzlaff D, Smith MW, Reaney SM, Roy AG (2013) Concepts of hydrological connectivity: Research approaches, Pathways and future agendas. Earth-Science Reviews 119:17-34
Cavalli M, Trevisani S, Comiti F, Marchi L (2013) Geomorphometric assessment of spatial sediment connectivity in small Alpine catchments. Geomorphology 188:31-41
Chen ST and Yu PS (2007) Pruning of support vector networks on flood forecasting. Journal of Hydrology 347(1-2):67-78
Choubin B, Darabi H, Rahmati O, Sajedi-Hosseini F, Kløve B (2018) River suspended sediment modelling using the CART model: A comparative study of machine learning techniques. Science of the Total Environment 615:272-281
Durigon VL, Carvalho DF, Antunes MAH, Oliveira PTS, Fernandes MM (2014) NDVI time series for monitoring RUSLE cover management factor in a tropical watershed. International Journal of Remote Sensing 35:441-453
Fathian H, Shafeizadeh M, and Nikbakht Shahbazi AR (2019) Continuous rainfall-runoff simulation by artificial neural networks based on efficient input variables selection using partial mutual information (PMI) algorithm. Iran-Water Resources Research 15(2):120-130 (In Persian)
Hagan MT, Menhaj MB (1994) Training feedforward networks with the marquardt algorithm. IEEE Transactions on Neural Networks 5:989-993
Haykin S (1999) Neural networks: A comprehensive foundation second edition. Pearson Education
Kakaei Lafdani E, Moghaddam Nia A, Ahmadi A (2013) Daily suspended sediment load prediction using artificial neural networks and support vector machines. Journal of Hydrology 478(25):50-62
Khan MYA, Tian F, Hasan F, Chakrapani GJ (2019) Artificial neural network simulation for prediction of suspended sediment concentration in the River Ramganga, Ganges Basin, India. International Journal of Sediment Research 34(2):95-107
Khosravi M, Salajegheh A (2013) Peak discharge forecast in the downstream station using the upstream stations by neural network (Case study: Taleghan). Iran-Water Resources Research 9(1):96-100 (In Persian)
Kim T-W, Valdés JB (2003) Nonlinear model for drought forecasting based on a conjunction of wavelet transforms and neural networks. Journal of Hydrologic Engineering 8:319-328
Kişi Ö (2009) Evolutionary fuzzy models for river suspended sediment concentration estimation. Journal of Hydrology 372:68-79
Kisi O, Haktanir T, Ardiclioglu M, Ozturk O, Yalcin E, Uludag S (2009) Adaptive neuro-fuzzy computing technique for suspended sediment estimation. Advances in Engineering Software 40:438-444
Kumar D, Pandey A, Sharma N, Flügel WA (2016) Daily suspended sediment simulation using machine learning approach. Catena 138:77-90
Chiang L, Tsai K J, Chen Y R, Lee MH, Sun JW (2014) Suspended sediment load prediction using support vector machines in the Goodwin Creek experimental watershed. In EGU General Assembly Conference Abstracts 16:52-85
Lesschen JP, Schoorl JM, Cammeraat LH (2009) Modelling runoff and erosion for a semi-arid catchment using a multi-scale approach based on hydrological connectivity. Geomorphology 109(3-4):174-183
Tabatabaei M, Solaimani K, Habibnejad Roshan M, Kavian A (2014) Estimation of daily suspended sediment concentration using artificial neural networks and data clustering by self organizing map (Case study: Sierra Hydrometry Station- Karaj Dam Watershed). Journal of Watershed Management 5:98-116 (In Persian)
Melesse AM, Ahmad S, McClain ME, Wang X, Lim YH (2011) Suspended sediment load prediction of river systems: An artificial neural network approach. Agricultural Water Management 98(5):855-866
Dehghani N, Vafakhah M (2013) Comparison of daily suspended sediment load estimations by sediment rating curve and neural network models (Case study: Ghazaghli Station in Golestan Province). Journal of Water and Soil Conservation 20(2):1-10 (In Persian)
Rajaee T, Mirbagheri SA, Zounemat-Kermani M, Nourani V (2009) Daily suspended sediment concentration simulation using ANN and neuro-fuzzy models. Science of the Total Environment 407(17):4916-4927
Renard KG, Foster GR, Weesies G, McCool D, Yoder D (1997) Predicting soil erosion by water: A guide to conservation planning with the Resived Universal Soil Loss Equation (RUSLE). Agriculture Handbook, 703
Najafi S, Sadeghi SHR, Heckmann T (2017) Temporospatial variations of structural sediment connectivity patterns in Taham-Chi watershed in Zanjan province, Iran. Journal of Water and Soil Conservation 24(3):131-147 (In Persian)
Sheykhalipour Z (2013) Comparison of artificial intelligence methods and equations of sediment transformation in Systan River. Master's thesis, Zabol university, 144p (In Persian)
Lillesand TM, Kiefer RW (1994) Remote sensing and photo interpretation. John Wiley and Sons: New York
Vafakhah M (2013) Comparison of cokriging and adaptive neuro-fuzzy inference system models for suspended sediment load forecasting. Arabian Journal of Geosciences 6(8):3003-3018
Vapnik VN (1995) The nature of statistical learning theory. IEEE Transactions on Neural Networks
Wester T, Wasklewicz T, Staley D (2014) Functional and structural connectivity within a recently burned drainage basin. Geomorphology 206: 362-373
Wischmeier WH, Smith DD (1978) Predicting rainfall erosion losses: A guide to conservation planning. U.S. Department of Agriculture, Agriculture Handbook No. 537
Yang CT, Marsooli R, Aalami MT (2009) Evaluation of total load sediment transport formulas using ANN. International Journal of Sediment Research 24:274-286
Zhu YM, Lu XX, Zhou Y (2007) Suspended sediment flux modeling with artificial neural network: An example of the Longchuanjiang River in the Upper Yangtze Catchment, China. Geomorphology 84(1):111-125
Zounemat-Kermani M, Kişi Ö, Adamowski J, Ramezani-Charmahineh A (2016) Evaluation of data driven models for river suspended sediment concentration modeling. Journal of Hydrology 535:457-472