Shihao Shan

Accurate short-term water demand forecasting assumes a pivotal role in optimizing water supply control strategies, constituting a cornerstone of effective water management. In recent times, the rise of machine learning technologies has ushered in hybrid models that exhibit superior performance in this domain. Given the intrinsic non-linear fluctuations and variations in short-term water demand sequences, achieving precise forecasts presents a formidable challenge. Against this backdrop, this study introduces an innovative machine learning framework for short-term water demand prediction. The maximal information coefficient (MIC) is employed to select high-quality input features. A deep learning architecture is devised, featuring an Attention-BiLSTM network. This design leverages attention weights and the bidirectional information in historical sequences to highlight influential factors and enhance predictive capabilities. The integration of the XGBoost algorithm as a residual correction module further bolsters the model’s performance by refining predicted results through error simulation. Hyper-parameter configurations are fine-tuned using the Keras Tuner and random parameter search. Through rigorous performance comparison with benchmark models, the superiority and stability of this method are conclusively demonstrated. The attained results unequivocally establish that this approach outperforms other models in terms of predictive accuracy, stability, and generalization capabilities, with MAE, RMSE, MAPE, and NSE values of 544 m³/h, 915 m³/h, 1.00%, and 0.99, respectively. The study reveals that the incorporation of important features selected by the MIC, followed by their integration into the attention mechanism, essentially subjects these features to a secondary filtration. While this enhances model performance, the potential for improvement remains limited. Our proposed forecasting framework offers a fresh perspective and contribution to the short-term water resource scheduling in smart water management systems.

As one of the important policy measures to promote water conservation and efficient utilization, the evaluation of water resources tax reform policy regarding its water saving and economic impact (WSEI) is a fundamental prerequisite for policy implementation. In this study, multiple types of water production modules, including surface water, groundwater, and unconventional water, were integrated into a CGE model. Hebei Province, the first pilot area in China, was used as a case study. Through a “with–without” comparative analysis scenario, three water resources tax policy simulations were designed to address the three key issues, and the results showed that the implementation of water resources tax policy would have a certain negative impact on industry economic output in the short term, but it could effectively suppress the use of conventional water and promote the utilization of unconventional water, which is beneficial for long-term water resource conservation and sustainability. The imposition of higher differential tax rates on high water-consuming industries is more effective in further promoting the use of unconventional water and reducing the use of conventional water to achieve water conservation targets. Moreover, providing tax refunds as subsidies to water-using industries could alleviate the economic impact of water resources tax and promote water conservation. From the perspectives of water quantity, water use efficiency, and economic impact, the optimal policy scenario (S3) was selected, involving implementing differential water resources tax rates of 23% for high water-consuming industries and 18% for general water-consuming industries, coupled with tax refunds and subsidies for sectors. Based on this, corresponding recommendations in terms of differential tax rate setting, tax utilization, government regulation, and agricultural water resources tax collection were provided. These findings can offer a scientific reference for the formulation and implementation of water resources tax policies in other regions.

As a key component of water distribution management, reliable short-term water demand forecasting plays a fundamental role in the optimal control for water supply. Most reported approaches based on deep learning omit the two-way information flow existed in historical water demand data and the model inputs cannot automatically highlight the significance of crucial features to current water demands, which could have impact on the prediction accuracy. Owing to the high nonlinear changes and fluctuations in water demand series, making accurate forecast a challenging task. To address the problem in this study, maximal information coefficient (MIC) is presented for feature extraction analysis, deep learning with Attention-BiLSTM networks is developed, to reinforce the performance, that combining the XGBoost algorithm as a residual correction module to forecast short-term water demand. Hyper-parameter configurations are conducted with the models. Finally, the superiority of proposed method is illustrated by comparing to other benchmark models. The results show that the proposed method outperforms other predictive models, in which both on the accuracy and stability.