This work aims to investigate the hydrochemical characteristics and formation mechanisms of shallow groundwater in a part of the Nanchang section of Ganfu plain. The hydrochemical data from 90 groundwater samples were interpreted by the methods of mathematical statistics, Piper diagrams, Gibbs plots, ratio graphs of ions, and geochemical modeling. The results show that shallow groundwater is weakly acidic, the average concentration of cation in groundwater decrease in Ca²⁺ > Na⁺ > Mg²⁺ > K⁺, and the abundance is in the order HCO₃⁻ > NO₃⁻ > SO₄²⁻ > Cl⁻ for anions. The hydrochemical type of groundwater was dominated by HCO₃-Na·Ca·Mg, HCO₃·Cl-Na·Ca·Mg, and HCO₃-Na·Ca. Moreover, the main controlling factor of groundwater hydrochemistry is water-rock interactions. Na⁺ and K⁺ mainly originate from the dissolution of halite. Ca²⁺ and Mg²⁺ are mainly controlled by carbonate dissolution, while the main anions come from the dissolution of evaporite and carbonate. The groundwater chemical evolution is affected by the dissolution and precipitation of the mineral phase and cation exchange.

Physics-informed neural networks (PINNs) have recently emerged as a promising machine learning paradigm that embeds physical laws into data-driven modeling, offering new opportunities for addressing long-standing challenges in groundwater science. Distinct from previous reviews, this study presents a dual-track framework that integrates bibliometric analysis with critical methodological synthesis to systematically review 178 articles published between 2019 and 2025 in the Web of Science Core Collection. The results show that current research hotspots center on groundwater flow and seepage simulation, multi-physics coupling, parameter inversion, and the characterization of porous media flow processes, with a clear shift from idealized synthetic cases toward more complex heterogeneous aquifer applications. Furthermore, this review summarizes the major strengths of PINNs in groundwater applications and identifies key methodological bottlenecks related to training stability, computational efficiency, boundary condition enforcement, and cross-scenario generalization. Building on these insights, a development roadmap is proposed to advance PINNs in groundwater science, emphasizing weak-form formulations, neural operators, hybrid physics–numerical solvers, high-performance computing, and integrated frameworks for multi-source data fusion and uncertainty quantification. These directions provide guidance for evolving PINNs into scalable and reliable tools for groundwater modeling and management.

Groundwater quality assessment is essential for sustainable water resource management, particularly in regions experiencing intensive anthropogenic pressures. In this study, we developed a data-driven framework that integrates groundwater quality indices, PSO-optimized XGBoost modeling, SHAP-based interpretability, and ensemble-based quantile uncertainty quantification. This framework enables simultaneous prediction, interpretation, and rigorous uncertainty analysis, and was applied to the Ganfu Plain, China, to predict both the water quality index (WQI) and entropy-weighted water quality index (EWQI) using hydrochemical and spatial parameters. The models achieved strong predictive performance, with nested cross-validation yielding low RMSE values across most folds. SHAP analysis consistently identified Mn, NO $$_{3}\,^{-}$$ , and spatial coordinates as the most influential predictors, whereas conventional bulk parameters such as total hardness and sulfate contributed minimally, particularly in the EWQI model. Uncertainty analysis showed that predictive variance was dominated by aleatoric contributions, while epistemic variance remained comparatively small but informative of data scarcity. Predictive intervals were wider for EWQI, reflecting its greater sensitivity to key parameters and its ability to capture localized spatial heterogeneity. Overall, the framework provides a robust, interpretable, and scalable tool for groundwater quality evaluation and sustainable management under data-limited conditions.

Conducting quantitative research on the microstructure of soft clay can reveal the essence of its soil mechanical behavior, which is of important practical significance for geological disaster risk assessment and prevention. To quantitatively investigate the microscopic properties of natural structured clay, soft clay soils from various sedimentary environments in the Hangzhou Estuarine Bay area were chosen as the research subject in this study. Subsequently, a comprehensive investigation into the microstructure of clay was conducted, involving X-ray phase analysis and SEM imaging analysis. The results revealed the following: (1) In comparison to the deep clay deposited in fluvial-lacustrine environments, the shallow mucky clay in marine sediments had a higher clay mineral content, accounting for 48%. Illite makes up the majority of it, with minor levels of kaolinite and montmorillonite being present. (2) The shallow mucky clay in the Hangzhou Estuarine Bay area had a typical agglomerate-flocculated structure. In contrast, the deeper clay showed a flocculated structure with less uniform particle sizes, strong stacking randomness, poor directional alignment of soil pores, and tends to form arrangements where edges are adjacent to faces or edges are adjacent to other edges. (3) Compared to the deep clay deposited in fluvial-lacustrine environments, the marine-deposited shallow mucky clay displayed orderly pore arrangements, strong directional alignment, significant pore shape variability, and minimal pore size changes between adjacent pores. The microstructure of soil plays a crucial role in determining the physical, mechanical, and other engineering properties of the soil. This study provides insightful information about the relationship between clay microstructure and geotechnical characteristics in Hangzhou and the surrounding areas.