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.

Hebei Province of China is facing a severe water resource shortage, making it urgent to formulate economical and effective water conservation policies. However, few studies have focused on analyzing the resource and economic impacts of a water policy. This study developed an improved computable general equilibrium (CGE) model with an extended water resources module as a policy analysis tool. The extended water resources module includes different water resources as commodities and water sectors, and introduces a substitution mechanism among the water resources. Policy scenarios containing different policy types and policy objects were established, including water price, technology (tech) improvement, structure adjustment, and water reuse policies in primary, secondary, and tertiary sectors. The impact on the water resource and economy of the scenarios was analyzed using the CGE model. The recommended policies include: an agricultural technology improvement policy that decreases groundwater usage by 240 hm³; an industrial technology improvement policy under which water usage per 10,000 CNY of industrial added value decreases by 13%; an industrial water reuse policy that increases unconventional water usage by 20%; and a structure adjustment policy to increase the proportion of the tertiary sector. The study provides an analysis tool for simulating and evaluating a water resource policy.

Water shortages in the Beijing-Tianjin-Hebei (BTH) region in China have constrained the region’s coordinated development. A feasible solution is introducing water rights transactions through the middle route of the South-to-North Water Diversion Project (SNWDP). However, there are few methods available for systematically simulating and evaluating the impact of inter-regional water rights transactions. In this study, an improved computable general equilibrium (CGE) model was developed to simulate the water rights transactions. Different water resources were integrated as intermediate inputs, and the model includes a substitution mechanism between different water resources. The water stress index (WSI) was used to evaluate the impact on the economy and water resources simulated by the model. The study proposes and evaluates different scenarios with different water-saving levels and transaction volumes. Water rights transactions have a positive effect on the overall economic growth of the BTH region, reducing the local water resource stress in Beijing and Tianjin; the transactions have a limited impact on the economy and water usage of Hebei Province. Compared with the general water-saving intensity scenario without water rights transactions, the recommended scenario adopts ultra water-saving intensity, along with the transfer of 100 hm³ of water rights from Hebei to Beijing and Tianjin. This leads to an increase in the overall gross domestic product (GDP) of the BTH region by CNY 0.587 trillion (USD 99.6 billion); a decrease in local water usage in Beijing and Tianjin of 197 hm³; and a relief in the regional imbalance of water resources stress. This study provides a quantitative analysis tool for evaluating the impact of water rights transactions and optimizing water resources allocations in the BTH region, providing a reference for simulating and evaluating water rights transactions in other regions.

Northwest China frequently experiences significant droughts and water shortages. To better balance the supply and demand, and provide sufficient funds for water resource projects, this study applied a computable general equilibrium model to construct an agricultural water pricing policy model that depends on the crops' economic value and regional water use characteristics. Wuwei City in Gansu Province was used as a case study to test the model. Three agricultural water price increase policies and three supporting subsidy policies were developed. The study quantitatively investigated the impact of these policies on the agricultural economy, water use, and efficiency of water use from different water sources. The results indicated that water pricing reform promotes water conservation and improves water use efficiency. Subsidies can reduce the negative impact of water pricing policies on the agricultural economy. Economic crops (e.g. vegetables) are more sensitive to water prices compared to food crops (e.g. wheat). Finally, to the best of our knowledge, this study provided the best water pricing reform scenario expected to be the most effective for local development.

The arid regions of Northwest China are facing water shortages and ecological fragility. Making full use of unconventional water is one of the effective ways of solving water issues and achieving high-quality regional development. The high cost of unconventional water utilization is the main obstacle to its utilization and technological development, and the subsidy policy may become a breaking point. Taking Ningdong Energy and Chemical Industry Base (NECI Base) as a case study, the article proposes raising the Yellow River water price to subsidize the utilization of mine water. The development and utilization of mine water can be effectively improved. Considering the optimal allocation of multiple water sources and the substitution relationship between the Yellow river water and mine water, this paper extends the water resources module (WRM) of the Computable General Equilibrium (CGE) model. The model can reflect the substitution of water sources and the linkage between water prices and the economy. Ten different subsidy policy scenarios are simulated through the extended CGE model, and the laws and mechanisms of the subsidy policy on the economy and water usage are summarized. The results show that increasing the price of Yellow River water by 8% to subsidize the mine water will achieve optimal socio-economic output. Under this scenario, the industrial value added (IVA) is basically unaffected, the water-use efficiency (WUE) is significantly improved, and the affordability of the enterprise is satisfied. The Yellow River water usage decreased from 319.03 million (M)m³ to 283.58 Mm³ (11.1% saving), and mine water usage increased from 27.88 Mm³ to 47.15 Mm³ (69.1% increase).