پیش‌بینی رواناب با استفاده از مدل‌های جعبه سیاه و خاکستری

نوع مقاله : مقاله پژوهشی

نویسندگان

1 استادیار /دانشکده کشاورزی، دانشگاه گنبد کاووس-گنبد کاووس.

2 دانش آموخته کارشناسی ارشد/ آبخیزداری، دانشگاه گنبدکاووس-گنبد کاووس

3 استادیار /دانشکده کشاورزی ، دانشگاه گنبد کاووس-گنبد کاووس

4 استادیار/ دانشکده کشاورزی ، دانشگاه گنبد کاووس-گنبد کاووس

چکیده

در دهه گذشته، یادگیری ماشین یک روش مناسب برای مدل‌سازی تجربی بارش-رواناب به عنوان یک مکمل مفید برای مدل‌های هیدرولوژیکی مطرح شده است، به ویژه در حوضه‌هایی که داده‌ها برای مدل‌های داده محور محدود هستند. در این تحقیق از مدل‌های جعبه سیاه (نروفازی و ماشین بردار پشتیبان) و مدل های جعبه خاکستری (TOPMODEL و HBV) برای شبیه سازی فرآیند بارش-رواناب روزانه در حوضه نوده خاندوز که در رودخانه گرگانرود قرار دارد، استفاده شد و عملکرد آن‌ها با توجه به دقت پیش‌بینی رواناب مقایسه گردید. برای مدل های جعبه سیاه، سه سری ورودی شامل دبی، دما و بارندگی در 9 سناریوی متفاوت بر اساس داده‌های سری زمانی انتخاب گردید. مقایسه مقادیر میانگین مربعات خطا و ضریب تعیین نشان می‌دهد مدل نروفازی با دبی تا سه گام زمانی قبل و دمای گام زمانی قبل عملکرد بهتری نسبت به سایر سناریوها دارد. به طور کلی مدل‌های جعبه سیاه رواناب را در مرحله واسنجی و صحت‌سنجی با دقت بیشتری نسبت به HBV و TOPMODEL شبیه‌سازی کرده‌اند. مقایسه دقیق عملکرد کل مدل‌ها نشان داد که مدل‌های نروفازی و ماشین بردار پشتیبان رواناب را در فصل‌های گرم با دقت کمتری نسبت به فصل‌های سرد پیش بینی کرده است.

کلیدواژه‌ها

موضوعات


عنوان مقاله [English]

Runoff prediction using black and gray box models

نویسندگان [English]

  • S. M. Seyedian 1
  • M. Bagherpour 2
  • A. Fathabadi 3
  • A. Mohammadi 4
1 Assistant Professor, Department of Agriculture, University, Ghonbad Kavous, Iran.
2 Graduate student of watershed management, Ghonbad Kavous University, Gonbad Kavous, Iran.
3 Assistant Professor, Department of Agriculture, University, Ghonbad Kavous, Iran
4 Assistant Professor, Department of Agriculture, University, Ghonbad Kavous, Iran.
چکیده [English]

In the past decade, machine learning for empirical rainfall–runoff modeling is considered to be a promising approach as a useful complement to hydrologic models, particularly in basins where data to support process-based models are limited. In this paper, we used black-box models (i.e. neuro-fuzzy and support vector machine) and gray-box models (i.e. TOPMODEL and HBV) for simulating the transformation of daily rainfall-runoff process in the Nodeh khormaloo watershed located in Gorganrood River Basin and compare their performance in terms of predictive accuracy. For the black-box models, the three input vectors including discharge, temperature and rainfall are selected in nine different scenarios based on the sequential time series data. Our result show that the neuro-fuzzy model which consists of three antecedent values of flow and one antecedent values of temperature outperforms other models when the root mean square error and coefficient of determination are used as quality indicators. In general, the black- box models outperformed the HBV and TOPMODEL simulations for the calibration and validation data sets. A detailed comparison of the overall performance indicated that the neuro-fuzzy and SVM models predicted runoff in warm months were consistently lower than that in the cold months.

کلیدواژه‌ها [English]

  • Artificial intelligence
  • Conceptual model
  • Rainfall
  • runoff
Aalami M, Hosseinzadeh H (2010) Modeling rainfall–runoff process in Lighvan Chai basin using conditional threshold temperature neuron. Journal of Water and Soil Sciences 20.1(2):97-110 (In Persian)
Aghakouchak A, Habib E (2010) Application of a conceptual hydrologic model in teaching hydrologic processes. International Journal of Engineering Education 26(4):963–973
Ahani A, Shourian M (2017) Prediction of Monthly Streamflow Using Data-driven Models. Iran-Water Resources Research 13(2):207-214 (In Persian)
Ahmadi F, Radmanesh F, Mirabbasi Najaf Abadi R (2014) Comparison between genetic programming and support vector machine methods for daily river flow forecasting (Case Study: Barandoozchay River). Journal of Water and Soil 28(6):1162-1171 (In Persian)
Al-safi H, Sarukkalige P (2017) Assessment of future climate change impacts on hydrological behavior of Richmond river catchment. Water Science and Engineering 10(3):197-208
Anusree K, Varghese KO (2016) Streamflow prediction of karuvannur river basin using ANFIS, ANN and MNLR Models. Procedia Technology 24:101-108
Azizian A, Shokoohi A (2014) An investigation on the effects of DEM creation methods on performance of the TOPMODEL. Iran-Water Resources Research 10(1):111-116 (In Persian)
Bastola S, Ishidaira H, Takeuchi K (2008) Regionalisation of hydrological model parameters under parameter uncertainty: a case study involving TOPMODEL and basins across the globe. Journal of Hydrology 357:188-206
Behmanesh J, Ayashm S (2015) Rainfall-runoff modeling in the turkey river using numerical and regression methods. Journal of Fundamental Applied Sciences 7(1):91-102
Behzad M, Asghari K, Eazi M, Palhang M (2009) Generalization performance of support vector machines and neural networks in runoff modeling. Expert Systems with Applications 36(4):7624-7629
Beven KJ (1997) TOPMODEL: a critique. Hydrological Processes 11(9):1069-1085
Bouffard JS (2014) A comparison of conceptual rainfall-runoff modelling structures and approaches for hydrologic prediction in ungauged peatland basins of the James Bay lowlands. M.Sc. Thesis, School of Geography, University of Carleton
Dastorani MT, Sharifi Darani H, Talebi A, Moghadam Nia A (2011) Evaliation of the application of artificial; neural network and adaptive neuro fuzzy interface system for rainfall runoff modeling in Zayande Rood river basin. Journal of Water and Wastewater 22(4):114-125 (In Persian)
Dewan A (2013) Floods in a megacity: Geospatial techniques in assessing hazards, risk and vulnerability. Dordrecht, Springer, 199p
Dorum A, Yarar A, Sevimli F, Onucyildiz M (2010) Modelling the rainfall-runoff data of susurluk basin. Expert Systems with Applications 37(9):6587-6593
Etter S, Addor N, Huss M, David F (2017) Climate change impacts on future snow ice and rain runoff in a swiss mountain catchment using multi-dataset calibration. Journal of Hydrology: Regional Studies 13:222-239
Euser T, Winsemius HC, Hrachowitz M, Fenicia F, Uhlenbrook S, Savenije H (2013) Framework to assess the realism of model structures using hydrological signatures. Hydrology and Earth System Sciences 17(5):1893-1912
Falkenmark M, Finlayson CM, Gordon LJ (2007) Agriculture, water and ecosystems: avoiding the costs of going too far. In: Water for Food, Water for Life: A Comprehensive Assessment of Water Management in Agriculture (ed. by D. Molden), London: Earthscan and Colombo, Sri Lanka: International Water Management Institute, 10248p
Ghafari GH, Vafakhah M (2013) Simulation of rainfall-runoff process using artificial neural network and adaptive neuro-fuzzy interface system (Case Study: Hajighoshan Watershed). Journal of Watershed Management Research 4(8):120-136 (In Persian)
Ghorbani MA, Azani A, Mahmoudi Vanolya S (2015) Rainfall-runoff modeling using hybrid intelligent models. Iran-Water Resources Research 11(2):146-150 (In Persian)
Ghumman AR, Ghazaw YM, Sohail AR, Watanabe K (2011) Runoff forecasting by artificial neural network and conventional model. Alexandria Engineering Journal 50(4):345-350
Golestan regional water authority (2004) Annual report of the Nodeh Khandouz station. Golestan regional water authority Publishers, Iran
Goswami M, O’Connor KM (2007) Real-time flow forecasting in the absence of quantitative precipitation forecasts: A multi-model approach. Journal of Hydrology 334(1-2):125-140
Hallegatte S, Green C, Nicholls RJ, Corfee-Morlot J (2013) Future flood losses in major coastal cities. Nature Climate Change 3(9):802-806
He Z, Wen X, Liu H, Du J (2014) A comparative study of artificial neural network adaptive neuro fuzzy inference system and support vector machine for forecasting river flow in the semiarid mountain region. Journal of Hydrology 509:379-386
Holko L, Lepisto A (1997) Modelling the hydrological behavior of a mountain catchment using TOPMODEL. Journal of Hydrology 196:361-377
Humphrey G, Gibbs M, Dandy G, Maier H (2016) A hybrid approach to monthly streamflow forecasting: integrating hydrological model outputs into a Bayesian artificial neural network. Journal of Hydrology 540:623-640
Jakeman AJ, Letcher J, Norton JP (2006) Ten iterative steps in development and evaluation of environmental models. Environmental Modeling Software 21(5):602-614
Javan K, Fallah Haghgoo Lialestani MR, Nejadhossein M (2015) A comparison of ANN and HSPF models for runoff simulation in Gharehsoo River watershed, Iran. Modeling Earth Systems and Environment 1(41):1-13
Jothiprakash V, Magar R (2009) Soft computing tools in rainfall-runoff modeling. ISH Journal of Hydraulic Engineering 15(1):84-96
Kakaei Lafdani E, Moghaddamnia A, Pahlavanravi A, Ahmadi A, Jajarmizadeh M (2013) Daily rainfall-runoff prediction and simulation using ANN, ANFIS and conceptual hydrological MIKE11/NAM models. International Journal of Engineering and Technology Sciences 1(1):32-50
Kashani MH, Ghorbani MA, Dinpashoh Y, Shahmorad S (2016) Integration of Volterra model with artificial neural networks for rainfall-runoff simulation in forested catchment of Northern Iran. Journal of Hydrology 540:340-354
Khan MS, Coulibaly P (2006) Bayesian neural network for rainfall-runoff modeling. Water Resources Research 42(7):1-18
Kuczera G, Parent E (1998) Monte Carlo assessment of parameter uncertainty in conceptual catchment models: The Metropolis algorithm. Journal of Hydrology 211(1-4):69–85
Kuo CH, Gan T, Yu P (2010) Seasonal stremflow prediction by a combined climate-hydrologic system for river basins of Taiwan. Journal of Hydrology 387:292-303
Liu R, Wang J, Shi J, Chen Y, Sun C, Zhang P, Shen Z (2014) Runoff characteristics and nutrient loss mechanism from plain farmland under simulated rainfall conditions. Science of the Total Environment 468-469:1069-1077
McMillan HK, Clark MP, Bowden WB, Duncan M, Woods RA (2011) Hydrological field data from a modeller's perspective: Part 1. Diagnostic tests for model structure. Hydrological Processes 25(4):511-522
Minns AW, Hall MJ (1996) Artificial neural networks as rainfall-runoff models. Hydrological Sciences Journal 41(3):399-417
Misra D, Oommen T, Agarwal A, Mishra S, Thompson A (2009) Application and analysis of support vector machine based simulation for runoff and sediment yield. Biosystems Engineering 103(4):527-535
Montaseri M, Ghavidel S (2014) River flow forecasting by using soft computing. Journal of Water and Soil 28(2):394-405 (In Persian)
Mutlu E, Chaubey I, Hexmoor H, Bajwa1 SG (2008) Comparison of artificial neural network models for hydrologic predictions at multiple gauging stations in an agricultural watershed. Hydrological Processes 22(26):5097–5106
Nabizadeh M, Mosaedi A, Hesam M, Dehghani A, Zakerinia M, Meftah M (2011) River flow forecasting using fuzzy inference system (fis) and comparative fuzzy inference system (ANFIS). Iran-Watershed Management Science & Engineering 5(17):7-14 (In Persian)
Nayak PC, Venkatesh B, Krishna B, Jain SK (2013) Rainfall-runoff modeling using conceptual, data driven, and wavelet based computing approach. Journal of Hydrology 493(17):57–67
Noori R, Khakpour A, Dehghani M, Farokhnia A (2011) Monthly stream flow prediction using support vector machine based on principal component analysis. Journal of Water and Wastewater 22(1):118-129 (In Persian)
Nourani V (2016) An emotional ANN (EANN) approach to modeling rainfall-runoff process. Journal of Hydrology 544:267-277
Nourani V, Kisi O, Komasi M (2011a) Two hybrid artificial intelligence approaches for modeling rainfall–runoff process. Journal of Hydrology 402(1-2):41-59
Nourani V, Roughani A, Gebremichael M (2011b) TOPMODEL capability for rainfall-runoff modeling of the ammameh watershed at different time scales using different terrain algorithms. Journal of Urban and Environmental Engineering 5(1):1-14
Okkan U, Serbes ZA (2012) Rainfall-runoff modeling using least squares support vector machines. Environmetrics 23(6):549-564
Pourreza Bilondi M, Khashei Siuki A, Sadeghi Tabas S (2014) Daily rainfall-runoff modeling with Least Square Support Vector Machine (LS-SVM). Journal of Water and Soil Conservation Research 21(6):293-304 (In Persian)
Rezaeianzadeh M, Stein A, Tabari H, Abghari H, Jalalkamali N, Hosseinipour EZ, Singh VP (2013) Assessment of a conceptual hydrological model and artificial neural networks for daily outflows forecasting. International Journal of Environtal Sciences Technology 10(2):1181–1192
Seibert J (1999) Conceptual runoff models-fiction or representation of reality?. Ph.D. Thesis, Faculty of Science and Technology, Acta University
Seyedian M, Soleimani M, Kashani M (2014) Flood flow forecasting using data mining and time series. Journal of Ecohydrology 1(3):167-179 (In Persian)
Singh VP (1995) Computer models of watershed hydrology. Water Resources Publication, Fort Collins, Colorado, 1130p
Talei A, Choy Chua L, Quek Ch (2010a) A novel application of a neuro-fuzzy computational technique in event-based rainfall-runoff modeling. Expert Systems with Applications 37(12):7456-7468
Talei A, Choy Chua L, Wong T (2010b) Evaluation of rainfall and discharge inputs used by adaptive network –based fuzzy inference systems (ANFIS) in rainfall-runoff modeling. Journal of Hydrology 391(3-4):248-262
Tingsanchali T, Gautam MR (2000) Application of tank, NAM, ARMA and neural network models to flood forecasting. Hydrological Processes 14(14):2473-2487
Uhlenbrook S, Roser S, Tilch N (2004) Hydrological process representation at the meso-scale: the potential of a distributed, conceptual catchment model. Journal of Hydrology 291(3-4):278-296
Veintimilla-Reyes J, Cisneros F, Vanegas P (2016) Artificial neural networks applied to flow prediction: a use case for the Tomebamba River. Procedia Engineering 162:153-161
Vrugt JA, Gupta HV, Bouten W, Sorooshian S (2003) A shuffled complex evolution metropolis algorithm for optimization and uncertainty assessment of hydrologic model parameters. Water Resources Research 39(8):1201-1219
Wang W, Chau K, Cheng Ch, Qiu L (2009) A comparison of performance of several artificial intelligence methods for forecasting monthly discharge time series. Journal of Hydrology 374(3-4):294–306
Westerberg IK, Guerrero JL, Younger PM, Beven KJ, Seibert J, Halldin S, Freer JE, Xu CY (2011) Calibration of hydrological models using flow-duration curves. Hydrological Earth System Sciences 15(7):2205-2227
Wu Cl, Chau KW (2011) Rainfall-runoff modeling using artificial neural network coupled with singular spectrum analysis. Journal of Hydrology 399(3-4):394-409
Yaghoubi M, Massah Bavani A (2014) Sensitivity analysis and comparison of capability of three conceptual models HEC-HMS, HBV and IHACRES in simulating continuous rainfall-runoff in semi-arid basins. Journal of Earth and Space Physics 40(2):153-172 (In Persian)
Zhou ZZ, Huang TL, Ma WX, Li Y, Zeng K (2015) Impacts of water quality variation and rainfall runoff on Jinpen Reservoir, in Northwest China. Water Science and Engineering 8(4):301-308