University Centre for Research and Development, Chandigarh University, Mohali, Punjab, India.
Laboratory of Architecture, Cities and Environment, Department of Hydraulic, Faculty of Civil Engineering and Architecture, Hassiba Benbouali University of Chlef, Chlef, Algeria.
Water Sci Technol. 2024 Aug;90(3):844-877. doi: 10.2166/wst.2024.222. Epub 2024 Jul 3.
This research explores machine learning algorithms for reservoir inflow prediction, including long short-term memory (LSTM), random forest (RF), and metaheuristic-optimized models. The impact of feature engineering techniques such as discrete wavelet transform (DWT) and XGBoost feature selection is investigated. LSTM shows promise, with LSTM-XGBoost exhibiting strong generalization from 179.81 m/s RMSE (root mean square error) in training to 49.42 m/s in testing. The RF-XGBoost and models incorporating DWT, like LSTM-DWT and RF-DWT, also perform well, underscoring the significance of feature engineering. Comparisons illustrate enhancements with DWT: LSTM and RF reduce training and testing RMSE substantially when using DWT. Metaheuristic models like MLP-ABC and LSSVR-PSO benefit from DWT as well, with the LSSVR-PSO-DWT model demonstrating excellent predictive accuracy, showing 133.97 m/s RMSE in training and 47.08 m/s RMSE in testing. This model synergistically combines LSSVR, PSO, and DWT, emerging as the top performers by effectively capturing intricate reservoir inflow patterns.
本研究探索了用于水库入流预测的机器学习算法，包括长短期记忆 (LSTM)、随机森林 (RF) 和启发式优化模型。研究了特征工程技术（如离散小波变换 (DWT) 和 XGBoost 特征选择）的影响。LSTM 表现出潜力，LSTM-XGBoost 在训练中表现出较强的泛化能力，从 179.81 m/s 的均方根误差 (RMSE) 降至测试中的 49.42 m/s。RF-XGBoost 和包含 DWT 的模型，如 LSTM-DWT 和 RF-DWT，也表现良好，突出了特征工程的重要性。比较表明 DWT 有增强作用：LSTM 和 RF 在使用 DWT 时大大降低了训练和测试 RMSE。像 MLP-ABC 和 LSSVR-PSO 这样的启发式模型也受益于 DWT，其中 LSSVR-PSO-DWT 模型表现出优异的预测精度，在训练中达到 133.97 m/s 的 RMSE，在测试中达到 47.08 m/s 的 RMSE。该模型通过有效捕捉复杂的水库入流模式，协同结合了 LSSVR、PSO 和 DWT，成为表现最佳的模型。
