Taking the section of Hunan in Xiangjiang River Basin (XRB) as an example, bases on the land use and evapotranspiration data in 2000, 2010 and 2020, this study discusses the characteristics of land use type, area change and mutual conversion in the XRB by using the methods of land use transfer matrix, integrated and single dynamic attitude model and GIS spatial analysis. The effects of land use type, area and conversion on evapotranspiration in the study area were revealed. The results show that the area, proportion and spatial pattern of land use types in the XRB have undergone great changes, especially the frequent conversion among land use types. However, in the past 20 years, the order of main land use areas in the XRB remained stable: forest > farmland > grassland > construction land > water area. The order of theoretical annual evapotranspiration based on land use type in the XRB is forest > grassland > farmland > construction land, which is different from the order of actual annual total evapotranspiration based on land use area: forest > farmland > grassland > construction land. Therefore, the land use type and land use area to evapotranspiration in the study area should be considered comprehensively. The conversion of different land use types in the XRB caused the change of evapotranspiration in different trends and degrees. The conversion between construction land and other land use types has a relatively large impact on evapotranspiration in the study area, while the conversion of other land use types has a small impact on regional evapotranspiration. The research results can provide scientific reference for land use planning and water resources management in the basin.

Aiming at the evolution of water resources in Qiandao Lake Basin under the condition of climate change, a WEP-L distributed hydrological model was established to simulate the water cycle process in the basin during 1960-2020. The Mann-Kendall non-parametric test method and Hurst index method were used to analyze the inter-annual variation and annual distribution characteristics of the total water resources in the basin. The temporal and spatial distribution and evolution trend of water resources in Qiandao Lake Basin were evaluated. The results indicate that The WEP-L model performs well in simulation the Qiandao Lake basin, and the Nash coefficient rate is above 0.83 in the calibration period and above 0.85 in the verification period; The water yield coefficient of the whole basin ranges from 0.436 to 0.630. The annual average total water resource is 122.5×10⁸m³, equivalent to 1 176.4 mm of water depth. The annual distribution process shows a unimodal structure, and the water depth of each sub-basin ranges from 742 mm to 1 266 mm, and the spatial distribution is higher in the west and lower in the east; The annual water resources series in the basin show an insignificant upward trend, and the Hurst index is 0.86, indicating a continuous upward trend. From the perspective of monthly water resources, January and February increased significantly, the other months were not significant changes.

In order to coordinate the balance between water resources supply and demand and promote the sustainable use of water resources in Wuhan City, this paper conducts a comprehensive evaluation and simulation of the water resources carrying capacity of Wuhan based on the improved TOPSIS method and system dynamics, and realizes a combination of static evaluation and dynamic prediction. The results show that the overall water resources carrying capacity of Wuhan City fluctuates and increases from 2010 to 2020, and the overall level is in a critical state; By simulating the development of Wuhan City from 2021 to 2035, the water resources carrying capacity of Wuhan City under the conventional development model has exceeded the limit and it is difficult to maintain the demand; The economic priority model sacrifices resources and environment for economic speed up, which shows the most serious water resources; The environment-friendly model can reduce water consumption and improve the ecological environment, but the economic development is also limited to a certain extent; The integrated development model, from the perspective of coordination and balance, can achieve resource conservation and environmental protection while satisfying the steady and rapid economic development, and obtain the maximum economic and ecological benefits with the minimum water consumption, achieving the harmonious development of human and nature.

Timely and accurate forecasting residential water consumption is critical to design and operational management of water supply systems. Long short-term memory (LSTM) is an effective data-driven prediction model for water consumption, but it usually relies on a large number of parameter settings. This paper proposed a multilayer long short-term memory neural network model (MLSTM), which was built on the LSTM model by superimposing a time distribution module. The results indicate that the MLSTM model has lower complexity and higher prediction accuracy than the LSTM model, especially for the prediction of peak water consumption with M_MAPE reduced by about 60%. Meanwhile, the MLSTM model is insignificantly affected by external environmental conditions (e.g., weather).

It is of great significance for the long-term planning and allocation of Nanjing water resources to analyze the current situation of Nanjing water consumption, make reasonable prediction of Nanjing water consumption and master the future water demand. The analysis of water consumption in Nanjing from 2009 to 2019 showed that industrial and agricultural water consumption accounted for a large proportion of total water consumption in Nanjing, which played a crucial role in the change of total water consumption. The combined model of grey GM(1,1) model and Elman neural network was used to forecast the water consumption of all districts and the total water consumption of Nanjing. The results show that the grey Elman neural network model has a good prediction effect on the total water consumption of Nanjing City from 2009 to 2019. The relative errors of the forecasts were all less than 3.5%, and the average relative errors of the predicted results over the years were 1.55%; The relative error of the forecast results is less than 8.5% in the forecast of the water consumption of all districts in Nanjing in 2019. The model used in this paper can accurately predict the water consumption of Nanjing, which is of great significance to effectively control the regional water consumption and realize the principle of "four water and four determinations".

In response to the problems of low accuracy and poor reliability of water consumption prediction due to the strong randomness and non-stationary state exhibited by the water consumption signal, this paper proposed a hybrid water consumption prediction model based on improved EEMD-WOA-SRU. Firstly, the LSTM prediction method was used to suppress the endpoint effect of the EEMD to obtain the improved intrinsic mode functions (IMF). Then the whale optimization algorithm (WOA) was used to optimize the simple recurrent unit (SRU) and predicted each component. Finally, the final prediction results were obtained by accumulation. The experimental results show that the decomposition error of the EEMD is reduced by 0.94% on average; Compared with the SRU, the average absolute error of EEMD-WOASRU model prediction is reduced by 45.42%, the root mean square error is reduced by 50.43%, and the reliability is improved by 52.38%. It can provide a basis for water resources decision making.

The current regional water supply and power generation structure is not able to achieve sustainable development in the long term. It is worth exploring whether the production, trade and the corresponding water footprint of the power sector in the Beijing-Tianjin-Hebei (BTH) region can meet the long-term development needs of the region after the dual-carbon goals is proposed. Therefore, this study constructed a dynamic multiregional computable general equilibrium model to simulate the changes in the production and trade of the power sector and its water footprint in the BTH region caused by the carbon reduction policy. Four carbon reduction scenarios were designed in the model to explore the impacts of policies such as carbon tax, investment and renewable energy subsidies. The results show that the carbon tax policy has the most significant water saving effect on power generation; The carbon reduction policy significantly increases the inter-regional flow of virtual water in the power trade; The complete water footprint of the power sector under various scenarios does not change much (less than 15%), in which the water footprint of the power sector in Beijing has the highest sensitivity to the carbon reduction policy. Therefore, the focus of water conservation in the power sector under the dual-carbon target should be on the trade chain, optimizing the trade structure and reducing interregional virtual water flows.

The identification of key influencing factors and their critical values for the prevention and control of water bloom in lakes is of great significance. Taking Wuhan South Lake as the study area, based on hydrological, water quality and meteorological monitoring data, Pearson Correlation Analysis, Gray Correlation Analysis and Principal Component Analysis were used to screen and identify key environmental factors with high correlation with chlorophyll a concentration, and the critical values of key environmental impact factors were analyzed by the Receiver Operating Characteristic (ROC) curve method. The results show that the COD_Mn, total phosphorus, total nitrogen, water temperature and air temperature had strong correlations with chlorophyll a concentration and were the key factors for water bloom outbreak, with the critical values of 6.25 mg/L, 0.146 mg/L, 0.725 mg/L, 27.05 ℃ and 22.35 ℃, respectively. It was found that the accuracy of the ROC curve method for solving the critical values of COD_Mn, total phosphorus, total nitrogen and other environmental factors with small daily variation was better than that of environmental factors with large daily variation such as air temperature and water temperature, and the ROC curve method has a greater advantage in determining the critical values of nutrient concentrations for water blooms in lakes.

The health of the water cycle is a key factor in high-quality regional development. The prediction of water cycle health state is of great significance to the coordinated development of regional water resources system, economic and social system and ecological environment system. Taking Zhengzhou City as a typical research area, this study constructed a DPSIR model for urban water cycle health evaluation, and analyzed the evolution process of water cycle health status in Zhengzhou from 2010 to 2020 by using entropy weight fuzzy comprehensive evaluation method. The system dynamics model and entropy weight fuzzy comprehensive evaluation method were used to predict the health status of water cycle in Zhengzhou from 2021 to 2030 under five types of comprehensive coordination type, economic development type and water resources optimization type. The results show that the health status of water cycle in Zhengzhou has been developing well in the past decade, and the indicators of per capita GDP, urbanization rate and intelligent water resources management have reached the "healthy" state. Under the five prediction scenarios, the urban water cycle reaches the state of "subhealth" or above, and under the comprehensive coordination scenario that takes into account economic development, ecological protection and water resources optimization, the water cycle health status of Zhengzhou reaches the state of " health", and this scheme is the optimal scheme. The results can provide theoretical basis and technical support for ecological protection and high quality development in Zhengzhou City.

In order to understand the water quality of Wuliangsu Lake, an inversion method of total suspended matter concentration based on M-GA-BP was proposed. Using Sentinel-2 remote sensing satellite images as the data source and considering the spatial and temporal characteristics existing in the study area, the monthly data was considered as a feature for the inversion of TSM concentration. The GA-BP model was built by optimizing the weights and thresholds of the BP neural network using genetic algorithm (GA), and comparing with the traditional BP neural network model. The results show that the introduction of the monthly feature model effectively reduces the model complexity and improves the model inversion accuracy, among which the M-GA-BP model has the highest inversion accuracy with the coefficients of determination of 0.916 and 0.903 for the training and test sets, respectively, and the root mean square errors of 0.049 μg/L and 0.057 μg/L for the training and test sets, respectively. The study can provide a new idea for the inversion of TSM concentration in the Wuliangsu Lake.