Time Series Modeling of Jiroft Dam Inflow Using Tow Deep Learning models case study (Jiroft and Nesa Dams)

Sayari, Nasrin; Shahrokhi, Armin

doi:10.22059/ije.2025.398750.1879

Time Series Modeling of Jiroft Dam Inflow Using Tow Deep Learning models case study (Jiroft and Nesa Dams)

Document Type : Research Article

Authors

nasrin sayari ¹
Armin Shahrokhi ²

¹ Assistant Professor, Department of Water Science and Engineering, Faculty of Agriculture, Shahid Bahonar University of Kerman, Kerman, Iran

² Master's degree in Water Resources Engineering, Department of Water Science and Engineering, Faculty of Agriculture, Shahid Bahonar University of Kerman, Kerman, Iran

10.22059/ije.2025.398750.1879

Abstract

Analyzing temporal and spatial changes in precipitation, temperature, and surface runoff is essential for water resources discussions and long-term forecasts for watershed management. Therefore, the aim of this study was to model the time series of inflow discharge to Jiroft and Nesa dams under different climatic conditions. For this purpose, two LSTM and GRU models were used in Jiroft and Nesa dams over a period of 25 and 12 years in the Python program environment. Based on the output results, the model is in its best state when it has reached the convergence point. Based on the output results, the model is in its best state when it has reached the convergence point. In the Jiroft Dam LSTM model, the RMSE criteria for training and testing the model were 0.72 and 0.78, respectively, and the MAE values were 0.10 and 0.12, respectively. These values in the GRU model were 0.94, 1.02, 0.15, and 0.20, respectively. Also, in the Nesa Dam in the LSTM model, the RMSE criteria for training and testing the model were 0.11 and 0.10, respectively, and the MAE values were 0.05 and 0.04, respectively. These values in the GRU model were 0.01, 0.09, 0.04, and 0.03, respectively. Also, by planning, it is possible to prevent damage from the dam outlet downstream and to drain and control possible floods as much as possible.

Keywords

Main Subjects

Surface water resources

References

Ahmadi, P., Arefi, H., & Kardan, N. (2020). Modeling the discharge of Karun River Using a New Method Based on the Joint LSTM and GRU Neural Networks. Journal of Ecohydrology, 7(3), 619-633.‏ (In Persian)
Ansari Qujqar, M., Iraqinejad, Sh., Bazarafshan, J., Zahraei, B., & Parsi, E. (2021). Evaluating the effectiveness of GRU-LSTM hybrid model in forecasting dust storms (case study: Khuzestan province). Iran Water Resources Research, 17(1), 16-32. (In Persian)
Akbari Osmavandani, S., Sharafati, A., & Moghaddam, H. K. (2024). Assessing the effectiveness of artificial intelligence models in predicting Zayanderud dam inflow at different time scales. Acta Geophysica, 72(5), 3511-3527.‏ (In Persian)
Anvari, S. (2018). Probabilistic Forecasts of Streamflow Scenarios Using ESP Approach (Case study: Halil River). Journal of Irrigation Sciences and Engineering, 41(3), 75-87.‏ (In Persian)
Baharlu, R. (2009). Forecasting time series with long-term dependencies using NARX recurrent neural network. The 12th Electrical Engineering Student Conference, (In Persian)
Bakhshi Ostadkalayeh, F., Moradi, S., Asadi, A., Moghaddam Nia, A., & Taheri, S. (2023). Performance improvement of LSTM-based deep learning model for streamflow forecasting using Kalman filtering. Water Resources Management, 37(8), 3111-3127.‏ (In Persian)
Chadha, G. S., Panambilly, A., Schwung, A., & Ding, S. X. (2020). Bidirectional deep recurrent neural networks for process fault classification. ISA transactions, 106, 330-342.‏
Chung, J., Gulcehre, C., Cho, K., & Bengio, Y. (2014). Empirical evaluation of gated recurrent neural networks on sequence modeling. arXiv preprint arXiv, 1412-3555.‏
Cho, K., Van Merriënboer, B., Bahdanau, D., & Bengio, Y. (2014). On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv, 1259-1409.‏
Damle, C., & Yalcin, A. (2007). Flood prediction using time series data mining. Journal of Hydrology, 333(2-4), 305-316.‏
Day, G. N. (1985). Extended streamflow forecasting using NWSRFS. Journal of Water Resources Planning and Management, 111(2), 157-170.‏
Fang, X., & Yuan, Z. (2019). Performance enhancing techniques for deep learning models in time series forecasting. Engineering Applications of Artificial Intelligence, 85, 533-542.‏
Fathi, P., Mohammadi, Y., & Homai, M. (2009). Intelligent modeling of monthly time series of input to Vahdat Dam in Sanandaj. Water and Soil (Agricultural Sciences and Industries), 23(1), 209-220 (In Persian)
Frank, R. J., Davey, N., & Hunt, S. P. (2001). Time series prediction and neural networks. Journal of intelligent and robotic systems, 31(1), 91-103.‏
Ghose, D. K. (2018). Measuring discharge using back-propagation neural network: a case study on Brahmani river basin. Intelligent Engineering Informatics: Proceedings of the 6th International Conference on FICTA, 591-598.
Hajizadeh Tahan, M., Ghasemzadeh, M., & Rezaeian, M. (2020). An evolutionary attention-based deep long short-term memory for time series prediction. Computational Intelligence in Electrical Engineering, 11(4), 15-28.‏ (In Persian)
Hosseinikhah, M., Zainiwand, H., Haqizadeh, A., & Tahmasabipour, N. (2013). Validation of temperature and precipitation values of general circulation models in Kermanshah Ravansar and West Islamabad stations. Ecohydrology, 1(3), 195 206 (In Persian)
Khalili, R., & Moridi, A. (2023). A Review of Artificial Intelligence Applications in Modeling and Removal Processes of Pollutants Soluble in Water and Wastewater. Iran-Water Resources Research, 19(1), 136-166.‏ (In Persian)
Momeneh, S. (2022). Performance comparison of artificial intelligence models with IHACRES model in streamflow modeling of the Gamasiab River catchment. Water and Soil Management and Modelling, 2(3), 1-16.‏ (In Persian)
Muhammad, A. U., Li, X., & Feng, J. (2019). Using LSTM GRU and hybrid models for streamflow forecasting. In International Conference on Machine Learning and Intelligent Communications, 510-524.
Management and Planning Organization of Iran. (2005). Regional balance between water resources and uses in catchment basins current and future status of water resources. Office of Water Affairs Agriculture and Natural Resources Studies of Comprehensive Climate Adaptation Program. (In Persian)
Samadi M. and Fathabadi A. (2019). Application of time series, ANN, and SVM models in forecasting the Gorgan Dam inflow rate. Environ. Water Eng, 4(4), 299-309. (In Persian)
Shafa'i Bejestan, M. (1999). Hydraulic precipitation. Publications of Shahid Chamran University of Ahvaz (In Persian)
SohrabiBidar, A., & Aminnejad, M. (2015). Investigating the displacements of Jiroft concrete dam foundations using dam extensometers. Iran Engineering Geology Association Journal,7(3-4), 95-102 (In Persian)
Swagatika, S., Paul, J. C., Sahoo, B. B., Gupta, S. K., & Singh, P. K. (2024). Improving the forecasting accuracy of monthly runoff time series of the Brahmani River in India using a hybrid deep learning model. Journal of Water and Climate Change, 15(1), 139-156.‏
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.‏
Wang, W. C., Chau, K. W., Cheng, C. T., & 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.‏
Zaytar, M. A., & El Amrani, C. (2016). Sequence to sequence weather forecasting with long short-term memory recurrent neural networks. International Journal of Computer Applications, 143(11), 7-11.‏
Zhang, B., & Govindaraju, R. S. (2000). Prediction of watershed runoff using Bayesian concepts and modular neural networks. Water Resources Research, 36(3), 753-762.‏