Runoff forecasting is one of the important non-engineering measures for flood prevention and disaster reduction. The accurate and reliable runoff forecasting mainly depends on the development of science and technology, many machine learning models have been proposed for runoff forecasting in recent years. Considering the non-linearity and real-time of hourly rainfall and runoff data. In this study, two runoff forecasting models were proposed, which were the combination of the bidirectional gated recurrent unit and backpropagation (BGRU-BP) neural network and the bidirectional long short-term memory and backpropagation (BLSTM-BP) neural network. The two models were compared with the gated recurrent unit (GRU), long short-term memory (LSTM), bidirectional gated recurrent unit (BGRU), and bidirectional long short-term memory (BLSTM) models. The research methods were applied to simulate runoff in the Yanglou hydrological station, Northern Anhui Province, China. The results show that the bidirectional models were superior to the unidirectional model, and the backpropagation (BP) based bidirectional models were superior to the bidirectional models. The bidirectional propagation was conducive to improving the generalization ability of the model, and BP neural network could better guide the model to find the optimal nonlinear relationship. The results also show that the BGRU-BP model performs equally well as the BLSTM-BP model. The BGRU-BP model has few parameters and a short training time, so it may be the preferred method for short-term runoff forecasting.

This study hopes to develop a multi-criteria decision-making (MCDM) method for equitable and efficient allocation of water resources under scarcity. Based on the Bankruptcy problems, five classic plus one proposed allocation rules are introduced to generate water distribution alternatives. The “Core” solution of Cooperative Game Theory (CGT) and the Security Restriction have been used to select feasible alternatives. Additionally, five voting methods in Social Choice Theory (SCT) are launched to aggregate preferences and obtain a “win” alternative. Apply this model to the 2030 water allocation planning project of Ezhou City, China, as a case study. Under the proposed rule, Adjust minimal overlap rule (AMO), five regions, Urban Area, Gedian DZ, and three counties, hold the water deficit rate of 5.9%, 15.8%, and 4.7%-6.1%, respectively. In aggregating preferences by voting, AMO wins four out of five methods and takes second place in the last one, which provides some insights for allocating water fairly and feasibly.

Since water supply association analysis plays an important role in attribution analysis of water supply fluctuation, how to carry out effective association analysis has become a critical problem. However, the current techniques and methods used for association analysis are not very effective because they are based on continuous data. In general, there is different degrees of monotone relationship between continuous data, which makes the analysis results easily affected by monotone relationship. The multicollinearity between continuous data distorts these analytical methods and may generate incorrect results. Meanwhile, we cannot know the association rules and value interval between features and water supply. Therefore, the lack of an effective analysis method hinders the water supply association analysis. Association rules and value interval of features obtained from association analysis are helpful to grasp cause of water supply fluctuation and know the fluctuation interval of water supply, so as to provide better support for water supply dispatching. But the association rules and value interval between features and water supply are not fully understood. In this study, a data mining method coupling kmeans clustering discretization and apriori algorithm was proposed. The kmeans was used for data discretization to obtain the one-hot encoding that can be recognized by apriori, and the discretization can also avoid the influence of monotone relationship and multicollinearity on analysis results. All the rules eventually need to be validated in order to filter out spurious rules. The results show that the method in this study is an effective association analysis method. The method can not only obtain the valid strong association rules between features and water supply, but also understand whether the association relationship between features and water supply is direct or indirect. Meanwhile, the method can also obtain value interval of features, the association degree between features and confidence probability of rules.

The water supply in megacities can be affected by the living habits and population mobility, so the fluctuation degree of daily water supply data is acute, which presents a great challenge to the water demand prediction. This is because that non-stationarity of daily data can have a large influence on the generalization ability of models. In this study, the Hodrick-Prescott (HP) and wavelet transform (WT) methods were used to carry out decomposition of daily data to solve the non-stationarity problem. The bidirectional long short term memory (BLSTM), seasonal autoregressive integrated moving average (SARIMA) and Gaussian radial basis function neural network (GRBFNN) were developed to carry out prediction of different subseries. The ensemble learning was introduced to improve the generalization ability of models, and prediction interval was generated based on student's t-test to cope with the variation of water supply laws. This study method was applied to the daily water demand prediction in Shenzhen and cross-validation was performed. The results show that WT is superior to HP decomposition method, but maximum decomposition level of WT should not be set too high, otherwise the trend characteristics of subseries will be weakened. Although the corona virus disease 2019 (COVID-19) outbreak caused a variation in water supply laws, this variation is still within the prediction interval. The WT and coupling models accurately predict water demand and provide the optimal mean square error (0.17%), Nash-Sutcliffe efficiency (97.21%), mean relative error (0.1), mean absolute error (3.32%), and correlation coefficient (0.99).

The basin water cycle affected by human activities presents the duality of natural and human characteristics. The effect of human activities to hydrology is becoming point of focus in the world with the development of society. As a physically based distributed parameter model, soil and water assessment tool is deficient when applied to the area with more human activities. In areas of increased activities, monthly changes in irrigation and consumptive water use has been observed over the years. In the past, this module was applied to a system with very little human influence. In this study we revised the theory and made appropriate improvement on irrigation module and consumptive water use module in order to apply it to the water system in Tianjin City, China, where water cycle is strongly affected by the human activities. The watershed model has been calibrated and validated using measured data available for the main river. By comparing the simulation results between initial model and improved model, the Nash-Sutcliffe efficiency is adjusted from 0.62 to 0.89 and correlation coefficient is improved from 0.79 to 0.91. The resulting validated model improves the simulation precision, especially amends the peak value of runoff, and adequately describes the impact of consumptive water use and irrigation on the natural water cycle. The model developed in this paper can be used to study water resource and water environment management in area of high human activities.

With the intensification of human activities, the natural water cycle has a significant nature-society dual feature, and identifying the mutual feedback mechanism between natural and social water cycles is an important basis for a more accurate simulation of the dualistic water cycle. In this study, two indexes of cumulative runoff change rate and social water cycle feedback rate are put forward, representing the degree of change in socio-hydrological unit runoff under the mutual feedback of the natural social water cycle in all upstream regions, and the degree influence of the water intake, consumption, and discharge process of the social water cycle on the natural water cycle in the socio-hydrological unit, respectively. Taking the Beijing–Tianjin–Hebei region, which is marked by strong human activities, as the study area, the 2035 natural-social dualistic water cycles were simulated by a water allocation and simulation (WAS) model. Different water supply types and use structures cause the social water cycle to increase or decrease local runoff in different areas. The social water cycle feedback rate is greater than 1 in Beijing and Tianjin, and less than 0.25 in the mountainous areas and the Hebei plain, indicating that the social water cycle of each unit in the Beijing–Tianjin–Hebei region increases or decreases local runoff due to different water supply types and use structures. The cumulative runoff change rate in this region was 0.66, indicating that the overall runoff was attenuated due to the social water cycle, and runoff attenuation was greater in the south than the north.