The Zhuxihe River has faced significant water quality challenges in recent years. Although control measures have been implemented, the pollution levels remain concerning. This paper aims to investigate the spatio-temporal variations in the water quality of the Zhuxihe River through field sampling, chemical testing, and synthetic evaluation. We collected 52 water samples in both dry and wet seasons along the main river and its tributaries. The evaluation, which utilized the integrated SFE-FCE method, identified MnO₄²⁻, NH₃-N, TP, and TFe as the primary pollutants. In the dry season, MnO₄²⁻ concentrations ranged from 1.6 mg/L to 19.8 mg/L, NH₃-N ranged from 0.12 mg/L to 2.04 mg/L, and TP concentrations varied from 0.1 mg/L to 5.61 mg/L. In the wet season, MnO₄²⁻ concentrations ranged from 4.9 mg/L to 13.9 mg/L, NH₃-N from 0.27 mg/L to 1.73 mg/L, and TP from 0.07 mg/L to 1.31 mg/L. The results indicate the concentrations of MnO₄²⁻ are higher in the wet season, and TP and NH₃-N show seasonal fluctuations. Spatially, the downstream section of the main river faces the highest pollution levels. This study provides insights into the pollution dynamics of the Zhuxihe River, offering a scientific foundation for future research and water quality management strategies.

Deep learning outperforms traditional interpolation methods in 3D geological modeling due to its ability to model nonlinear relationships and its flexibility in incorporating diverse geological data. However, acquiring geological data for practical applications is challenging, and the quality of the data can vary significantly, which limits the effectiveness of purely data-driven deep learning models in 3D geological modeling. To address this challenge, this paper introduces GeoSAE, a geoconstraint-driven 3D geological modeling method. GeoSAE improves potential field prediction by employing a stacked autoencoder network (SAE) and incorporating geological constraints as a loss function during model training. This approach generates a geologically consistent, smooth, and continuous 3D stratigraphic model. To validate the method, this study applies it to a 60-square-kilometer region in Jiangdong new district, Haikou city, China. Stratigraphic interface points were utilized to predict the 3D potential field, with PyVista (version 0.44.2) enabling the accurate extraction of stratigraphic interfaces. Model quality was evaluated through comprehensive assessments of loss function analysis, data fitting, and the verification of stratigraphic smoothness constraints. Results indicate that the stratigraphic model generated by GeoSAE closely aligns with the actual data, accurately capturing stratigraphic geometry. Additionally, incorporating smoothness constraints enhances model smoothness, minimizes irregular stratigraphic fluctuations, and produces a more natural and continuous stratigraphic morphology.

The southeastern Hainan Island boasts abundant hydrothermal resources, most of which are exposed as thermal springs. Analyzing the hydrochemical characteristics, hydrochemical evolutionary mechanisms, and material transition of these resources is significant for their exploitation and utilization. This study investigated the Nanping geothermal field in southeastern Hainan Island, using five groups of geothermal water samples collected in 2022, as well as seven groups of geothermal water samples, one group of shallow groundwater samples, and one group of surface water samples taken in 2023. Specifically, this study examined water–rock interactions in the geothermal field using the Gibbs model, ion ratios, chloro-alkaline indices (CAIs), and the sodium adsorption ratio (SAR). Moreover, the mineral transfer process in groundwater was analyzed using inverse hydrogeochemical simulation. The results indicate that in the study area the geothermal water temperatures range from 64 °C to 80 °C, pH values from 8.32 to 8.64, and TDS concentrations from 431 mg/L to 623 mg/L. The primary hydrochemical types of geothermal water in the study area include Cl-Na and Cl·HCO₃-Na, suggesting low-temperature, slightly alkaline geothermal water. The hydrochemical components of geothermal water in the study area are primarily affected by water–rock interactions. Besides the dissolution of silicate minerals and halite, cation exchange reactions contribute greatly to the formation of Na⁺ and K⁺ in geothermal water. Geothermal water receives recharge from the atmospheric precipitation of the Diaoluo Shan area in the northwest of the study area, with the recharge elevation ranging from 967 to 1115 m. The inverse hydrogeochemical simulation results reveal that during the water–rock interactions, silicate minerals, clay minerals, gypsum, and halite dissolve, while quartz and carbonate minerals precipitate. Additionally, these processes are accompanied by cation exchange reactions dominated by the replacement of Na⁺ in surrounding rocks by Ca²⁺ in geothermal water. This study can provide a geological basis for the exploitation, utilization, and management of the Nanping geothermal field.