Groundwater level dynamic monitoring data have the characteristics of spatio-temporal non-smoothness and strong spatio-temporal correlation. However, the current groundwater level prediction model is insufficient to consider the spatio-temporal factors of the groundwater level and the autocorrelation of spatio-temporal series, particularly the lack of consideration of hydrogeological conditions in the actual study area. Thus, this study constructed a model based on the hydrogeological conditions and the spatio-temporal characteristics of the dynamic monitoring data of groundwater in the porous confined aquifer III in Nantong, the northern wing of the Yangtze River Delta, China. The spatial autocorrelation coefficient of the hydrogeology important parameter, permeability coefficient K, is used to optimize the distance weighting coefficient of monitoring wells obtained by the K-nearest neighbor (KNN) algorithm and then reconstruct the spatio-temporal dataset and long short-term memory (LSTM) network. A spatio-temporal groundwater level prediction model LSTM-K-KNN that introduces the spatial autocorrelation of hydrogeological parameters was constructed. The reliability and accuracy of LSTM-K-KNN, LSTM, autoregressive integrated moving average (ARIMA) model, and support vector machine (SVM) were evaluated by a cross-validation algorithm. Results showed that the prediction accuracy of LSTM-K-KNN is 19.86, 43.64, and 52.38% higher than that of the other single prediction models (LSTM, ARIMA, and SVM).

The development of green energy sources, such as shallow geothermal energy, is one of the most important measures to reduce the environmental pollution caused by the use of traditional energy sources. At present, coastal cities in the east of the Yangtze River Delta, China, have favorable conditions for the development of shallow geothermal energy because of their abundant geothermal resources. However, the development and utilization of shallow geothermal energy are still in their infancy, and adaptability zoning is yet to be fully carried out. The study area is Nantong City, which is in the eastern coast of the Yangtze River Delta. A comprehensive analysis of the conditions of shallow geothermal energy is carried out based on the analysis of the regional geological, hydrogeological, and environmental geological conditions. The adaptability zoning index system of the groundwater source heat pump and buried pipe ground source heat pump system is then constructed, and the weight of evaluation factors is determined according to analytic hierarchy process. Finally, the adaptability zoning of shallow geothermal energy development and utilization mode is obtained by using the spatial analysis function of geographic information. The results showed that the areas with good suitability and better suitability account for 98.24% of the study area and those with good economy and better economy account for 99.67% of the study area. This method can provide reference suggestions for the orderly development and sustainable utilization of shallow geothermal energy in coastal cities in plain areas.

Porous groundwater seepage flow field reflects the spatiotemporal dynamic characteristics of porous groundwater movement. The geometric point and vector line methods are the traditionally used visualization methods for groundwater seepage flow field; however, they exhibit difficulty in describing the characteristics and attributes of a seepage flow field. Therefore, a new particle flow method in the field of computer graphics is introduced in this study to visualize seepage flow field, including the storage conditions, transport mechanism, and seepage field properties of porous groundwater. This visualization method is discussed from four aspects: the generation of seed points, the life cycle of particles, the movement velocity of particles, and the formation of particle trajectory and smooth processing. The seepage field of confined aquifer III groundwater expressed via particle flow and the contour of critical groundwater level are superimposed and analyzed in Yancheng City in the east coast of China. Results show that particle flow can be effectively applied to the visualization of groundwater seepage flow field and provide spatial auxiliary decision-making support for the sustainable exploitation of groundwater and the formulation of geological environment protection measures.

Water Supply issues a formal retraction in relation to the above article by Liang He, Liwen Yang, Ling Chen, Yabin Ye, Shuo Zhang and Chenfang Xu. The publisher issues this retraction due to concerns relating to unreliable quality and inappropriate references. The response from the authors to these concerns were found to be insufficient and as such, the Editors-in-Chief no longer have confidence in the integrity of the article. The authors disagreed with the editors' decision. We apologize for any confusion this may have caused.