
تعداد نشریات | 162 |
تعداد شمارهها | 6,622 |
تعداد مقالات | 71,539 |
تعداد مشاهده مقاله | 126,870,052 |
تعداد دریافت فایل اصل مقاله | 99,909,817 |
توسعه مدل هیبریدی غیرخطی برای پیشبینی جریان ماهانه ورودی مخازن سدها براساس پارامترهای هیدروکلیما و پوشش گیاهی حوضه (مطالعه موردی: سد دز) | ||
مجله اکوهیدرولوژی | ||
مقاله 3، دوره 11، شماره 1، فروردین 1403، صفحه 26-45 اصل مقاله (1.12 M) | ||
نوع مقاله: پژوهشی | ||
شناسه دیجیتال (DOI): 10.22059/ije.2024.373165.1797 | ||
نویسندگان | ||
پوریا ظهیرپور1؛ سامان جوادی* 2؛ فریماه سادات جمالی3؛ علی محمدی2 | ||
1گروه مهندسی آب، دانشکده فناوری کشاورزی (ابوریحان)، دانشکدگان کشاورزی و منابع طبیعی، دانشگاه تهران، تهران، ایران | ||
2گروه مهندسی آب، دانشکده فناوری کشاورزی (ابوریحان)، دانشکدگان کشاورزی و منابع طبیعی، دانشگاه تهران، تهران، ایران. | ||
3گروه جغرافیای طبیعی، دانشکده علوم زمین، دانشگاه شهید بهشتی ، تهران، ایران | ||
چکیده | ||
سد دز نقش اساسی در کنترل سیلابهای رودخانه دز ایفا کرده و از طرفی تأمین کننده آب مورد نیاز کشاورزی دشتهای خوزستان میباشد. بنابراین پیشبینی دقیق و قابل اعتماد ورودی جریان به مخزن، یک مرجع حیاتی برای تصمیمگیری در مورد بهرهبرداری و مدیریت این مخزن است. در این تحقیق مدل WAVELET-ARIMA-NARX برای پیشبینی جریان ماهانه ورودی مخزن سد دز توسعه یافت. از روش WAVELET جهت تجزیه سری زمانی به زیر سری ها و تحلیل بهتر سری زمانی، از مدل ARIMA به منظور مدل سازی مولفه خطی سری های تجزیه شده و از مدل NARX جهت مدل سازی خطای حاصل از مدل WAVELET-ARIMA استفاده گردید. از شاخص NDVI حوضه نیز جهت سنجش تغییر دقت مدل هیبریدی WAVELET-ARIMA-NARX بهره برده شد. نتایج نشان داد عملکرد پیش بینی مدل هیبریدی WAVELET-ARIMA-NARX نسبت به مدل ARIMA بهبود قابل توجهی یافته است. به نحوی که با توجه به معیار RMSE، دقت پیشبینی در مراحل صحتسنجی و آموزش، نسبت به مدل ARIMA و WAVELET-ARIMA به ترتیب 74 و 82 درصد کاهش یافته است. همچنین پارامتر NDVI به همراه دما و بارش متوسط حوضه به عنوان ورودی مدل NARX دقت مدل را افزایش داده بدین صورت که در این مدل با 10 نرون در لایه پنهان، در مقایسه با مدل دو پارامتری بارش و NDVI با تعداد 15 نورون، در بخش ارزیابی مدل مقادیر MAE از 2/27 به 6/18 و RMSE از 45/0 به 26/0 رسیده است که این مقادیر نشانگر اهمیت و تاثیر در نظرگرفتن همزمان سه پارامتر بر دقت پیش بینی می باشد. | ||
کلیدواژهها | ||
تئوری موجک؛ شاخص فصلی؛ شبکه عصبی مصنوعی؛ مدل هیبریدی؛ سد دز | ||
عنوان مقاله [English] | ||
Development of a nonlinear hybrid model for forecasting monthly reservoirs inflow Based on hydro-climate parameters and basin vegetation cover (Case study: Dez dam) | ||
نویسندگان [English] | ||
Pouria Zahirpour1؛ Saman Javadi2؛ Farimah Sadat Jamali3؛ Ali Mohammadi2 | ||
1Department of Water Engineering, Faculty of Agriculture Technology (Aburaihan), College of Agriculture and Natural Resources, University of Tehran, Tehran, Iran | ||
2Department of Water Engineering, Faculty of Agriculture Technology (Aburaihan), College of Agriculture and Natural Resources, University of Tehran, Tehran, Iran | ||
3Department of Physical Geography, Faculty of Earth Sciences, Shahid Beheshti University, Tehran, Iran. | ||
چکیده [English] | ||
Dez dam has an essential role in controlling the floods and water supply in Khouzestan. Accurate and reliable prediction of the flow input to the reservoir is crucial to make decisions about the exploitation and management of this reservoir. In this research, a novel WAVELET-ARIMA-NARX model was developed to predict the monthly inflow to Dez dam reservoir. The WAVELET method was used to break down the time series into sub-series and better analyzing, the ARIMA model was used to model the linear component of the analyzed series, and the NARX model used to model the error resulting from WAVELET-ARIMA model. The NDVI index was also used to measure the accuracy change of the WAVELET-ARIMA-NARX hybrid model. The results showed that the prediction performance of the WAVELET-ARIMA-NARX hybrid model has improved significantly compared to the ARIMA model. In such a way according to the RMSE criterion, the prediction accuracy in the verification and training stages has decreased by 74% and 82%, compared to the ARIMA and WAVELET-ARIMA model, respectively. The NDVI parameter with average temperature and rainfall of the basin as an input of the NARX model has increased the accuracy of the model. In the model with 10 neurons in the hidden layer, compared to the two-parameter model of rainfall and NDVI with 15 neurons, in evaluation section, the MAE values have decreased from 27.2 to 18.5 and the RMSE from 0.45 to 0.26. These values indicate the importance and impact of simultaneous consideration of three parameters on forecasting accuracy. | ||
کلیدواژهها [English] | ||
WAVELET theory, Seasonal Index, Artificial Neural Network, Hybrid Model, Dez dam | ||
مراجع | ||
[1[ Banihabib ME, Jurik L, Khorasani MM, Shahdany SM, Mohammadi A, Pokrývková J. Optimizing Embedded
Water Trades to Conserve Lakes in Arid and Semiarid Regions. Polish Journal of Environmental Studies. 2021
Jan 1;30(5):4413-23.
[2[ Yousefi H, Mohammadi A, Mirzaaghabeik M, Noorollahi Y. Virtual water evaluation for grains products in Iran
Case study: pea and bean. J water land dev. 2017 Dec 1;35(1):275-80.
[3[ Ward PJ, de Ruiter MC, Mård J, Schröter K, Van Loon A, Veldkamp T, von Uexkull N, Wanders N, AghaKouchak
A, Arnbjerg-Nielsen K, Capewell L. The need to integrate flood and drought disaster risk reduction strategies.
Water Security. 2020 Dec 1;11:100070.
[4[ Herbert ZC, Asghar Z, Oroza CA. Long-term reservoir inflow forecasts: enhanced water supply and inflow
volume accuracy using deep learning. Journal of Hydrology. 2021 Oct 1;601:126676.
[5[ Moeeni H, Bonakdari H. Forecasting monthly inflow with extreme seasonal variation using the hybrid
SARIMA-ANN model. Stochastic environmental research and risk assessment. 2017 Oct;31(8):1997-2010.
[6[ Kassem AA, Raheem AM, Khidir KM. Daily streamflow prediction for khazir river basin using ARIMA and
ANN models. Zanco Journal of Pure and Applied Sciences. 2020;32(3):30-9.
[7[ Allawi MF, Hussain IR, Salman MI, El-Shafie A. Monthly inflow forecasting utilizing advanced artificial
intelligence methods: a case study of Haditha Dam in Iraq. Stochastic Environmental Research and Risk
Assessment. 2021 Nov;35(11):2391-410.
[8[ Alzahrani SI, Aljamaan IA, Al-Fakih EA. Forecasting the spread of the COVID-19 pandemic in Saudi Arabia
using ARIMA prediction model under current public health interventions. Journal of infection and public
health. 2020 Jul 1;13(7):914-9.
[9[ Zhang GP. Time series forecasting using a hybrid ARIMA and neural network model. Neurocomputing. 2003
Jan 1;50:159-75.
[10[ Banihabib ME, Arabi A, Salha AA. A dynamic artificial neural network for assessment of land-use
change impact on warning lead-time of flood. International Journal of Hydrology Science and Technology.
2015;5(2):163-78.
[11[ Xu A, Chang H, Xu Y, Li R, Li X, Zhao Y. Applying artificial neural networks (ANNs) to solve solid waste-
related issues: A critical review. Waste Management. 2021 Apr 1;124:385-402.
[12[ Ebrahimi H, Rajaee T. Simulation of groundwater level variations using wavelet combined with neural
network, linear regression and support vector machine. Global and Planetary Change. 2017 Jan 1;148:181-91..
[13[ Wang Z, Lou Y. Hydrological time series forecast model based on wavelet de-noising and ARIMA-LSTM.
In2019 IEEE 3rd Information Technology, Networking, Electronic and Automation Control Conference
(ITNEC) 2019 Mar 15 (pp. 1697-1701). IEEE.
[14[ Shoaib M, Shamseldin AY, Melville BW, Khan MM. Runoff forecasting using hybrid wavelet gene expression
programming (WGEP) approach. Journal of Hydrology. 2015 Aug 1;527:326-44.
[15[ Agarwal A, Maheswaran R, Sehgal V, Khosa R, Sivakumar B, Bernhofer C. Hydrologic regionalization using
wavelet-based multiscale entropy method. Journal of Hydrology. 2016 Jul 1;538:22-32.
[16[ Rodríguez-Murillo JC, Filella M. Significance and causality in continuous wavelet and wavelet coherence
spectra applied to hydrological time series. Hydrology. 2020 Nov 2;7(4):82.
[17[ Sang YF. A review on the applications of wavelet transform in hydrology time series analysis. Atmospheric
research. 2013 Mar 1;122:8-15.
[18[ Nikmanesh, Mohammad Reza. Predicting average monthly discharge using an integrated model of artificial
neural network and wavelet transformations (Case study: Ker River - Pol Khan Station). Journal of Water and
Soil Conservation Research, 2015; 22 (3): 231-239. [in Persian[.
[19[ Seo Y, Kim S, Kisi O, Singh VP. Daily water level forecasting using wavelet decomposition and artificial
intelligence techniques. Journal of Hydrology. 2015 Jan 1;520:224-43.
[20[ Iwok IA, Udoh GM. A Comparative study between the ARIMA-Fourier Model and the Wavelet model.
American Journal of Scientific and Industrial Research. 2016;7(6):137-44.
[21[ Banihabib ME, Ahmadian A, Jamali FS. Hybrid DARIMA-NARX model for forecasting long-term daily
inflow to Dez reservoir using the North Atlantic Oscillation (NAO) and rainfall data. GeoResJ. 2017 Jun
1;13:9-16
[22[ Adib, Arash, Gorjizadeh, Ali. Drought assessment and monitoring using drought indicators; Case study of
Dez catchment. Iranian Journal of Irrigation and Water Engineering, 2016; 7 (2): 173-185. [in Persian[.
[23[ Cryer JD, Chan KS. Time series analysis: with applications in R. New York: Springer; 2008 Apr 4.
[24[ Mallat SG. A theory for multiresolution signal decomposition: the wavelet representation. IEEE transactions
on pattern analysis and machine intelligence. 1989 Jul;11(7):674-93.
[25[ Dickey DA, Fuller WA. Distribution of the estimators for autoregressive time series with a unit root. Journal
of the American statistical association. 1979 Jun 1;74(366a):427-31.
[26[ Said SE, Dickey DA. Testing for unit roots in autoregressive-moving average models of unknown order.
Biometrika. 1984 Dec 1;71(3):599-607.
[27[ Zhang X, Wu X, Zhu G, Lu X, Wang K. A seasonal ARIMA model based on the gravitational search algorithm
(GSA) for runoff prediction. Water Supply. 2022 Aug 1;22(8):6959-77.
[28[ Daubechies I. The wavelet transform, time-frequency localization and signal analysis. IEEE transactions on
information theory. 1990 Sep;36(5):961-1005.
[29[ Shao Y, Zhao J, Xu J, Fu A, Li M. Application of rainfall-runoff simulation based on the NARX dynamic
neural network model. Water. 2022 Jun 29;14(13):2082.
[30[ Nury AH, Hasan K, Alam MJ. Comparative study of wavelet-ARIMA and wavelet-ANN models for
temperature time series data in northeastern Bangladesh. Journal of King Saud University-Science. 2017 Jan
1;29(1):47-61.
[31[ Abbaszadeh H, Daneshfaraz R, Sume V, Abraham J. Experimental investigation and application of soft
computing models for predicting flow energy loss in arc-shaped constrictions. AQUA—Water Infrastructure,
Ecosystems and Society. 2024 Feb 23:jws2024010.
[32[ Hoque MJ, Bayezid M, Sharan AR, Kabir MU, Tareque T. Prediction of Strength Properties of Soft Soil
Considering Simple Soil Parameters. Open Journal of Civil Engineering. 2023 Jul 31;13(3):479-96.
[33] Kumar P, Foufoula‐Georgiou E. A multicomponent decomposition of spatial rainfall fields: 1. Segregation of
large‐and small‐scale features using wavelet transforms. Water Resources Research. 1993 Aug;29(8):2515-32.
[34[ Cheng Y, Zhang H, Liu Z, Chen L, Wang P. Hybrid algorithm for short-term forecasting of PM2. 5 in China.
Atmospheric environment. 2019 Mar 1; 200:264-79. | ||
آمار تعداد مشاهده مقاله: 271 تعداد دریافت فایل اصل مقاله: 203 |