Fluoride hydrogeochemistry and associated human health risks implications are investigated in several aquifers along the southern edge of the Chinese Loess Plateau. Locally, 64% shallow groundwater samples in loess aquifer exceed the fluoride limit (1.5 mg/L) with the maximum of 3.8 mg/L. Presently, the shallow groundwater is the main source of private wells for domestic use, and this is clearly a potential risk for human health. Hydrogeochemistry and stable isotopes are used to elucidate the diversity of occurrence mechanisms. Enrichment of fluoride in groundwater is largely controlled by the F-containing minerals dissolution. Furthermore, alkaline condition and calcium-removing processes promote water–rock interactions. Stable isotopes of hydrogen and oxygen (δD and δ¹⁸O) in study area waters demonstrate that groundwater in loess aquifer is old, which means groundwater remains in the aquifer for a long time. Long residence time induces sufficient water–rock interactions, which play significant roles in the resolution of fluoride minerals. Samples from the shallow loess aquifer show elevated fluoride levels, which may pose human health risk for both adults (60%) and children (94%) via oral intake. To ensure drinking water safety, management measures such as popularizing fluoride-removing techniques and optimizing water supply strategies need to be implemented.

Nitrate pollution is considered to be one of the most common environmental problems in groundwater, especially in areas affected by human mining, such as the arid region of northern China. However, the human health risk assessment of nitrate pollution in this area has not yet been carried out. In this study, groundwater samples were taken in the Selian mining area in Inner Mongolia to conduct a full analysis of water quality. On this basis, the groundwater quality, the distribution range of nitrate pollution, and human health risks were evaluated. The results show that the groundwater in the Selian mining area is neutral to alkaline, with high salinity and hardness. The concentration of nitrate ions in groundwater generally exceeds the standard, and the maximum exceeds 5.48 times the value specified in the Chinese national standard, indicating that groundwater nitrate pollution needs to be controlled urgently. Groundwater is polluted by large amounts of nitrogen fertilizer used by humans in agricultural activities. At the same time, mining activities have accelerated the severity and spread of pollution. Groundwater is not recommended for direct human life and irrigation use in the study area unless purification measures are taken. Nitrate pollution is more harmful to children through groundwater, about 1.54 times that of adults. Excess nitrate is transported into the body through drinking groundwater, so proper drinking water control will reduce the health risks of nitrate, such as centralized water supply. This study will provide a scientific basis for the rational use of groundwater and nitrate pollution control in the area.

Water level management is an important part of urban water system management. In flood season, the river should be controlled to ensure the ecological and landscape water level. In non-flood season, the water level should be lowered to ensure smooth drainage. In urban areas, the response of the river water level to rainfall and artificial regulation is relatively rapid and strong. Therefore, building a mathematical model to forecast the short-term trend of urban river water levels can provide a scientific basis for decision makers and is of great significance for the management of urban water systems. With a focus on the high uncertainty of urban river water level prediction, a real-time rolling forecast method for the short-term water levels of urban internal rivers and external rivers was constructed, based on long short-term memory (LSTM). Fuzhou City, China was used as the research area, and the forecast performance of LSTM was analyzed. The results confirm the feasibility of LSTM in real-time rolling forecasting of water levels. The absolute errors at different times in each forecast were compared, and the various characteristics and causes of the errors in the forecast process were analyzed. The forecast performance of LSTM under different rolling intervals and different forecast periods was compared, and the recommended values are provided as a reference for the construction of local operational forecast systems.

While irrigated crops produce much higher yields than rain-fed crops, the ionic components of irrigation water have important effects on crop yield. Groundwater is widely used for irrigation in the Baojixia irrigation area in China. The chemical characteristics and water quality of groundwater in the Baojixia irrigation area were analyzed and evaluated to study the impact of groundwater quality on crop yield. Results showed cations in the groundwater to mainly be Na⁺, Ca²⁺, and Mg²⁺, whereas the anions are mainly HCO₃⁻, SO₄²⁻, and Cl⁻. Water-rock interaction and cation exchange were identified as the main factors affecting hydrogeochemical properties from west to east. The study found salinity and alkalinity of groundwater in the western region of the study area to be low, and therefore suitable for irrigation. Groundwater in the eastern part of the study area was found to have a medium to high salinity and alkalinity, and is therefore not recommended for long-term irrigation. The groundwater irrigated cultivation of wheat and corn in the research area over 2019, for example, would have resulted in a drop in the annual crop output and an economic loss of 0.489 tons and 0.741 × 10⁴ yuan, respectively. Irrigation using groundwater was calculated to result in the cumulative loss of crop yields and an economic loss of 49.17 tons and 80.781 × 10⁴ yuan, respectively, by 2119. Deterioration of groundwater quality will reduce crop yields. It is recommended that crop yields in the study area be increased by strengthening irrigation water management and improving groundwater quality.

To support water resource management, flood control, disaster mitigation, and environmental protection in the middle reaches of the Jinsha River, precipitation and runoff data from five monitoring stations—Shigu, A’hai, Zhongjiang, Jin’anqiao, and Panzhihua—were jointly used as multivariate inputs to forecast runoff at Panzhihua Station. To obtain well-separated intrinsic mode functions (IMFs) at different frequencies while avoiding the use of future information during feature construction, SVMD was implemented in a rolling manner, with only the historical observations available up to each forecasting origin used for decomposition. The original runoff series was reconstructed using sliding windows with different historical input window lengths, and the optimal historical input window length was selected according to the forecasting performance. For enhanced adaptive optimization and reduced manual intervention, an Improved Exponential–Trigonometric Optimization (IETO) algorithm was employed to optimize SVMD parameters. Finally, a dual-attention temporal convolutional network (DATCN) was developed for runoff prediction. At a historical input window length of L = 5, the proposed IETO-SVMD-DATCN model achieved an NSE of 0.9826, compared with 0.9813 for DATCN and 0.9820 for SVMD-DATCN. The proposed model also achieved lower RMSE, MAE, and MAPE values than the compared models. These results indicate improved forecasting performance for the evaluated runoff data.