Comparison of N-BEATS with Standalone and Hybrid Deep Learning Models in Monthly Inflow Forecasting to the Aras Dam Reservoir: A Feature Selection Analysis

Abstract

Reservoir dams play a pivotal role in water resource management. Accurate prediction of inflow to reservoirs significantly enhances operational performance. While standalone artificial intelligence methods have recently been frequently used to predict inflow, hybrid models have shown quite more satisfactory success. In this study, various deep learning models, including MLP, GRU, LSTM, CNN, CNN-MLP, CNN GRU, CNN-LSTM, CNN-GRU-MLP, and CNN-LSTM-MLP, were utilized to predict the monthly inflow to the Aras reservoir in the Azerbaijan-Iran region. The results were compared with the Neural Basis Expansion Analysis for Time Series Forecasting (N-BEATS) model for univariate forecasting and the NBEATSx model for multivariate forecasting using a monthly inflow time series dataset. To enhance prediction accuracy, the hyperparameters of the models were optimized. Additionally, to evaluate the impact of feature selection on model performance, five different scenarios were developed as combinations of input variables for forecasting one future time step. The evaluation metrics revealed that among the scenarios, Scenario 5 (comprising lagged inflows at months 1, 11, and 12; lagged average monthly precipitation in the upstream basin at months 1 and 12; the solar month counter; and a three-month moving average of monthly inflow) yielded the best results. Among the models, the hybrid CNN-LSTM-MLP demonstrated the highest prediction accuracy. Specifically, the performance metrics for this model and the best scenario included MAE, RMSE, PBIAS, R², KGE, and NSE, which were 8.78 m³/s, 12.95 m³/s, 1.5%, 0.89, 0.91, and 0.89, respectively. Conversely, the NBEATSx model exhibited suboptimal performance, with reduced accuracy as the number of input features increased, although the N-BEATS model performed well in univariate forecasting. This study highlights the high potential of hybrid deep learning models in accurately forecasting reservoir inflows and underscores their utility in enhancing water resource and reservoir operation management.

Keywords

• Data Preprocessing
• Hyperparameter Tuning
• Random Search
• Bayesian Optimization
• NBEATSx
• CNN-LSTM-MLP

References

1. Ahmadi A, Daccache A, Sadegh M & Snyder R L (2023). Statistical and deep learning models for reference evapotranspiration time series forecasting: A comparison of accuracy, complexity, and data efficiency. Computers and Electronics in Agriculture, 215, 108424. https://doi.org/10.1016/j.compag.2023.108424
2. Alquraish M M, Abuhasel K A, Alqahtani A S & Khadr M (2021). A Comparative Analysis of Hidden Markov Model, Hybrid Support Vector Machines, and Hybrid Artificial Neural Fuzzy Inference System in Reservoir Inflow Forecasting (Case Study: The King Fahd Dam, Saudi Arabia). Water, 13(9): 1236. https://doi.org/10.3390/w13091236
3. Apaydin H, Feizi H, Sattari M T, Colak M S, Shamshirband S & Chau K W (2020). Comparative Analysis of Recurrent Neural Network Architectures for Reservoir Inflow Forecasting. Water 12(5): 1500. https://doi.org/10.3390/w12051500
4. Babaei M, Moeini R & Ehsanzadeh E (2019). Artificial neural network and support vector machine models for inflow prediction of dam reservoir (case study: Zayandehroud dam reservoir). Water Resources Management, 33(6): 2203–2218. https://doi.org/10.1007/s11269 019-02252-5
5. Cho K, van Merriënboer B, Bahdanau D & Bengio Y (2014). On the properties of neural machine translation: Encoder-decoder approaches. arXiv preprint arXiv:1409.1259. https://arxiv.org/abs/1409.1259
6. Deb D, Arunachalam V & Raju K S (2024). Daily reservoir inflow prediction using stacking ensemble of machine learning algorithms. Journal of Hydroinformatics, 26(5): 972–997. https://doi.org/10.2166/hydro.2024.210
7. Du S, Li T, Gong X & Horng S J (2018). A hybrid method for traffic flow forecasting using multimodal deep learning. IEEE Transactions on Intelligent Transportation Systems, 21(12): 5412–5421. https://doi.org/10.1109/TITS.2020.2972974
8. optimizations Ghimire S, Deo R C, Casillas-Pérez D, Salcedo-Sanz S, Sharma E & Ali M (2022). Deep learning CNN-LSTM-MLP hybrid fusion model for feature and daily solar https://doi.org/10.1016/j.measurement.2022.111759

9. radiation prediction. Measurement, 202, Article 111759.
10. Ghimire S, Nguyen-Huy T, Prasad R C, Deo R C, Casillas-Pérez D, Salcedo-Sanz S & Bhandari B (2023). Hybrid convolutional neural network–multilayer model for solar radiation prediction. Cognitive Computation 15(3): 645–671. https://doi.org/10.1007/s12559-022-10070-y
11. Guo J, Zhou J, Qin H, Zou Q & Li Q (2011). Monthly streamflow forecasting based on improved support vector machine model. Expert Systems with Applications, 38(10): 13073–13081. https://doi.org/10.1016/j.eswa.2011.04.097
12. Gupta H V, Kling H, Yilmaz K K & Martinez G F (2009). Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modelling. Journal of Hydrology, 377(1–2): 80–91. https://doi.org/10.1016/j.jhydrol.2009.08.003
13. Hochreiter S & Schmidhuber J (1997). Long short-term memory. Neural Computation 9(8): 1735–1780. https://doi.org/10.1162/neco.1997.9.8.1735
14. Hu D, Huang J, Lu D & Wang J (2024). A real-time hydrogen consumption estimation method for fuel cell vehicles. International Journal of Green Energy 21(13): 3112–3124. https://doi.org/10.1080/15435075.2024.2356099
15. Jiao L, Luo X, Zha L, Bao H, Zhang J & Gu X (2024). Machine learning assisted water management strategy on a self-sustaining seawater desalination and vegetable cultivation platform. Computers and Electronics in Agriculture, 217, Article 108569. https://doi.org/10.1016/j.compag.2023.108569
16. Khorram S & Jehbez N (2023). A hybrid CNN–LSTM approach for monthly reservoir inflow forecasting. Water Resources Management, 37(10): 4097–4121. https://doi.org/10.1007/s11269-023-03541-w
17. Kim T, Shin J Y, Kim H, Kim S & Heo J H (2019). The use of large-scale climate indices in monthly reservoir inflow forecasting and its application on time series and artificial intelligence models. Water 11(2), Article 374. https://doi.org/10.3390/w11020374
18. Kim T, Yang T, Gao S, Zhang L, Ding Z, Wen X & Hong Y (2021). Can artificial intelligence and data-driven machine learning models match or even replace process-driven hydrologic models for streamflow simulation? A case study of four watersheds with different hydro-climatic regions across the CONUS. Journal of Hydrology, 598, Article 126423. https://doi.org/10.1016/j.jhydrol.2021.126423
19. Latif S D & Ahmed A N (2023). A review of deep learning and machine learning techniques for hydrological inflow forecasting. Environment, Development and Sustainability, 25(11): 12189–12216. https://doi.org/10.1007/s10668-023-03131-1
20. Latif S D, Ahmed A N, Sathiamurthy E, Huang Y F & El-Shafie A (2021). Evaluation of deep learning algorithm for inflow forecasting: A case study of Durian Tunggal Reservoir, Peninsular Malaysia. Natural Hazards 109(1): 351–369. https://doi.org/10.1007/s11069-021 04839-x
21. LeCun Y, Bottou L, Bengio Y & Haffner P (1998). Gradient-based learning applied to document recognition. Proceedings of the IEEE, 86(11): 2278–2324. https://doi.org/10.1109/5.726791
22. Li P, Zhang J & Krebs P (2022). Prediction of Flow Based on a CNN-LSTM Combined Deep Learning Approach. Water 14(6): 993. https://doi.org/10.3390/w14060993
23. Li Y, Xu J & Anastasiu D C (2023). An Extreme-Adaptive Time Series Prediction Model Based on Probability-Enhanced LSTM Neural Networks. Proceedings of the AAAI Conference on Artificial Intelligence 37(7) 8684-8691. https://doi.org/10.1609/aaai.v37i7.26045
24. Majeed T, Mir R A, Dar R A, Haq M A, Rasool S N & Assad A (2024). Deep learning-based streamflow prediction for western Himalayan river basins. International Journal of System Assurance Engineering and Management 15(4): 1–14. https://doi.org/10.1007/s13198-024 02403-x
25. Moeini R, Nasiri K & Hosseini S H (2024). Predicting the water inflow into the dam reservoir using the hybrid intelligent GP-ANN-NSGA-II method. Water Resources Management 38(11): 4137–4159. https://doi.org/10.1007/s11269-024-03856-2
26. Najafabadi M M, Villanustre F, Khoshgoftaar T M, Seliya N, Wald R & Muharemagic E (2015). Deep learning applications and challenges in big data analytics. Journal of Big Data 2(1): 1–21. https://doi.org/10.1186/s40537-014-0007-7
27. Ni L, Wang D, Singh V P, Wu J, Wang Y, Tao Y & Zhang J (2020a). Streamflow and rainfall forecasting by two long short-term memory based models. Journal of Hydrology, 583, 124296. https://doi.org/10.1016/j.jhydrol.2019.124296
28. Ni L, Wang D, Wu J, Wang Y, Tao Y, Zhang J & Liu J (2020b). Streamflow forecasting using extreme gradient boosting model coupled with Gaussian mixture model. Journal of Hydrology, 586, 124901. https://doi.org/10.1016/j.jhydrol.2020.124901
29. Olivares K G, Challu C, Marcjasz G, Weron R & Dubrawski A (2023). Neural basis expansion analysis with exogenous variables: Forecasting electricity prices with NBEATSx. International Journal of Forecasting 39(2): 884-900. https://doi.org/10.1016/j.ijforecast.2022.03.001
30. Oreshkin B N, Carpov D, Chapados N & Bengio Y (2019). N-BEATS: Neural basis expansion analysis for interpretable time series forecasting. arXiv preprint arXiv:1905.10437. https://doi.org/10.48550/arXiv.1905.10437
31. Pes B (2021). Learning from High-Dimensional and Class-Imbalanced Datasets Using Random Forests. Information, 12(8), 286. https://doi.org/10.3390/info12080286
32. Pini M, Scalvini A, Liaqat M U, Ranzi R, Serina I & Mehmood T (2020). Evaluation of machine learning techniques for inflow prediction in Lake Como, Italy. Procedia Computer Science, 176: 918–927. https://doi.org/10.1016/j.procs.2020.09.093
33. Puszkarski B, Hryniów K & Sarwas G (2022). Comparison of neural basis expansion analysis for interpretable time series (N-BEATS) and recurrent neural networks for heart dysfunction classification. Physiological Measurement, 43(6): 064006. https://doi.org/ 10.1088/1361 6579/ac6e55
34. Rashidi M, Zarghami M, Pishbahar E & Fallahi F (2022). Assessing coalition in meeting environmental flow based on Shapley value and Nash equilibrium: Case study Aras River. International Journal of Environmental Science and Technology, 19(7), 6521–6530. https://doi.org/10.1007/s13762-021-03855-5
35. Rumelhart D E, Hinton G E & Williams R J (1986). Learning representations by back-propagating errors. nature, 323(6088): 533 536.https://doi.org/10.1038/323533a0
36. Semmelmann L, Henni S & Weinhardt C (2022). Load forecasting for energy communities: a novel LSTM-XGBoost hybrid model based on smart meter data. Energy Informatics, 5(Suppl 1), 24.https://doi.org/10.1186/s42162-022-00212-9
37. Shi X, Chen Z, Wang H, Yeung D Y, Wong W K & Woo W C (2015). Convolutional LSTM network: A machine learning approach for precipitation nowcasting. Advances in Neural Information Processing Systems, 28: 802–810. https://proceedings.neurips.cc/paper/2015/file/07563a3fe3bbe7e3ba84431ad9d055af-Paper.pdf
38. Shu X, Ding W, Peng Y, Wang Z, Wu J & Li M (2021). Monthly streamflow forecasting using convolutional neural network. Water Resources Management, 35(15): 5089–5104. https://doi.org/10.1007/s11269-021-02961-w
39. Skariah M & Suriyakala C D (2022). Forecasting reservoir inflow combining exponential smoothing, ARIMA, and LSTM models. Arabian Journal of Geosciences, 15(14): 1292. https://doi.org/10.1007/s12517-022-10564-x
40. Sureh F S, Sattari M T, Rostamzadeh H, Kahya E (2024). Meteorological Drought Assessment and Prediction in Association with Combination of Atmospheric Circulations and Meteorological Parameters via Rule Based Models. Journal of Agricultural Sciences 30(1): 61-78. https://doi.org/10.15832/ankutbd.1067486
41. Song C M (2022). Data construction methodology for convolution neural network based daily runoff prediction and assessment of its applicability. Journal of Hydrology, 605, 127324. https://doi.org/10.1016/j.jhydrol.2021.127324
42. Tran T D, Tran V N & Kim J (2021). Improving the accuracy of dam inflow predictions using a long short-term memory network coupled with wavelet transform and predictor selection. Mathematics 9(5) 551. https://doi.org/10.3390/math9050551
43. Tran V N, Dinh D D, Pham B D H, Dang K D, Anh T N, Ngoc H N & Nguyen G T (2024). Data-driven dam outflow prediction using deep learning with simultaneous selection of input predictors and hyperparameters using the Bayesian optimization algorithm. Water Resources Management 38(2): 401–421. https://doi.org/10.1007/s11269-023-03677-9
44. Wang T, Guo Y, Evgenievna M S & Wu Z (2024). Application of a Multi-Model Fusion Forecasting Approach in Runoff Prediction: A Case Study of the Yangtze River Source Region. Sustainability 16(14): 5964. https://doi.org/10.3390/su16145964
45. Yang T, Asanjan A A, Welles E, Gao X, Sorooshian S & Liu X (2017). Developing reservoir monthly inflow forecasts using artificial intelligence and climate phenomenon information. Water Resources Research 53(4): 2786–2812. https://doi.org/10.1002/2017WR020482
46. Yaseen Z M, Awadh S M, Sharafati A & Shahid S (2018). Complementary data-intelligence model for river flow simulation. Journal of Hydrology 567: 180–190. https://doi.org/10.1016/j.jhydrol.2018.10.020