Predicting Inlet Flow to Jamishan Dam Using Time Series Models

Document Type : Research paper

Authors

1 Assistant Professor, Department of Water Engineering and Sciences, Faculty of Agricultural Sciences and Food Industries, Science and Research Branch, Islamic Azad University, Tehran, Iran

2 M.Sc. of Water Resources, Department of Water Engineering and Sciences, Faculty of Agricultural Sciences and Food Industries, Science and Research Branch, Islamic Azad University, Tehran, Iran

3 Associate Professor, Department of Renewable Energies and Environment, Faculty of New Sciences and Technologies, University of Tehran,, Iran

Abstract

As aquifer feeder and influential parameter in water balance equations and groundwater resources balance, accurate prediction of dams and rivers discharge plays an important role in planning managing and operating optimal and sustainable water resources. In this research, in order to organize the Jamishan catchment area. In order to predict the future natural hazards of the basin, the monthly discharge of this basin is predicted by time series analysis methods. In this regard Was used from monthly discharge data of entrance to jamishan dam in sonqor city of kermanshah province during the period (1360-1389). Initial analysis of data included a review of definitive series semantics (period, trend, jump) done on the time series and after assurance remove these semantics, data was normal and the data stagnation was made. By examining the correlation and partial correlation functions for fifty percent of the data, the self-correlated model (AR) and the moving average model (MA) were fitted for the calibration period to the time series and with the non-correlation test of Port-Manto and the normalization of the remainder, a number of models that did not have these conditions were eliminated, and the best models were identified among the remaining models with Akayek's test. In the verification stage, using the best model during the calibration period, for the fifty-second percent of the data, the prediction verification step was performed. And error validation values were evaluated using white nose, Barlett-Test (Cumulative Rotational), mean of remaining significance, and after the success of the model in the verification prototypes, it was used to predict the monthly discharge of the next 15 years. It can be concluded that the more the model is more static, the analysis of the series is easier and the model with less acacia gives a better answer.

Keywords

References

بشری، م. و وفاخواه، م.، 1389. مقایسه روش‌های مختلف تحلیل سری زمانی در پیش‌بینی دبی ماهانه حوزه آبخیز کرخه. مهندسی آبیاری و آب، سال 1، شماره 2، ص86-75.
جمعدار، م.، سرائی تبریزی، م.، یوسفی، ح.، 1399. پتانسیل‌یابی میزان کارستی­شدن چشمه‌ها از منظر هیدروژئوشیمیایی در محدوده مطالعاتی هشتگرد. هیدروژئولوژی، سال 5، شماره 2، ص 113-126.
باباعلی، ح. دهقانی، ر.، 1395. مقایسه مدل‌های شبکه عصبی موجک و شبکه عصبی مصنوعی در پیش‌بینی سطح آب زیرزمینی. هیدروژئولوژی، سال 2، شماره 2، ص 108-96.
سعیدی، ب.، عرب، ع.، 1397. پیش‌بینی سطح آب زیرزمینی با استفاده از مدل‌های منطق فازی، شبکه عصبی و سری زمانی.ذهیدروژئولوژی، سال پنجم، شماره 2، ص 69-81.
صمدی، م. فتح‌آبادی، ا.، 1397. استفاده از مدل­های سری زمانی، شبکه عصبی و ماشین‌بردار پشتیبان جهت پبش‌بینی دبی ورودی به سد گرگان، محیط زیست و مهندسی آب، سال 2، شماره 2، ص 309-299.
فتح آبادی، ا.، سلاجقه، ع. و مهدوی، م.، 1387. پیش‌بینی دبی رودخانه با استفاده از روش­های نوروفازی و مدل­های سری زمانی. علوم و مهندسی آبخیزداری ایران، سال دوم، شماره 5، ص30-21.
کارآموز، م. و عراقی نژاد، ش.، 1389. هیدرولوژی پیشرفته، انتشارات دانشگاه صنعتی امیرکبیر (پلی‌تکنیک تهران)، 464 ص.
معینی، ح.، بنکداری، ح.، فاطمی، ا. و ابتهاج، ع.، 1395. مدل‌سازی دبی ماهانه ورودی به مخزن سد جامیشان با مدل­های خودهمبسته با میانگین متحرک تجمعی و سامانه استنتاج فازی-عصبی انطباقی، آب و خاک، شماره 2، ص 285-273.
Box, G.E.P and G.M. Jenkinks., Reinsel, G.C.., 1994. Time series analysis: Forcasting and control. Third Edition, Holden-Day.
Cryer, J.D., 1992. Time series Analysis. Translated by Niroomand, H.A., Mashhad University Publication, 404  pp.
Damle, C., A. Yalcin. 2007. Flood prediction using time series data mining. Journal of Hydrology. 333(2-4): 305-316.
Kendall, D.R., J.A. Dracup. 1991. A comparisx and AR (1) generated hydrologic sequences, J. Hydrology, 122, 335-352.
Mohammadi, K., Eslami, H.R., Dardashti, S.D., 2005. Comparison of regression, ARIMA and ANN models for reservoir inflow forecasting using snowmelt equivalent (a case study of Karaj). J. Agric. Sci. Technol, 7, 17-30.
Valipour, M., Banihabib, M.E., Behbahani, S.M.R., 2013. Comparison of the ARMA, ARIMA, and the autoregressive artificial neural network models in forecasting the monthly inflow of Dez dam reservoir. Journal of hydrology, 476, 433-441.
Hydrogeology
Volume 6, Issue 1
Publisher
September 2021
Pages 153-164

Files

Share

How to cite

Statistics