The Yishu Fault Zone (YSFZ) is located in a key tectonic transition zone shaped by the interaction between the Pacific and Tethyan tectonic domains in eastern China. Despite sparse geothermal borehole coverage across this region, the deeply incised fault structures create favorable hydrogeological prerequisites for fault-mediated subsurface heat migration and hydrothermal fluid circulation. This study integrates hydrochemistry, multi-isotope tracing (δD, δ¹⁸O, ⁸⁷Sr/⁸⁶Sr, and δ³⁴S), multi-mineral equilibrium modeling, and silica–enthalpy mixing analysis to constrain the evolution process and genetic mechanism of geothermal groundwater in the middle segment of the YSFZ. The geothermal groundwater displays weakly alkaline to alkaline properties and in situ temperatures of 35.2~75.0 °C, which is characterized by the HCO₃–Na, SO₄–Na, and Cl·SO₄–Na type. Stable isotope signatures demonstrate that the geothermal groundwater is recharged by the atmospheric precipitation with elevations of 822~1274 m. The hydrochemical evolution of the geothermal waters is governed by silicate weathering, evaporite dissolution, and cation exchange. The ⁸⁷Sr/⁸⁶Sr ratios indicate mixed solute contributions from silicate and evaporite lithologies, whereas the δ³⁴S signatures suggest that SO₄²⁻ is predominantly derived from gypsum dissolution. Two distinct hydrochemical evolution patterns can be identified in the study area. Samples GG1 and GG5 are characterized by HCO₃⁻ enrichment, whereas GG2, GG3, and GG4 exhibit enrichment in Na⁺ and SO₄²⁻. Reservoir temperatures estimated using multi-mineral equilibrium geothermometry range from 56.7 °C to 92.1 °C, with circulation depths of 1648~2304 m and cold-water mixing ratios of 48%~69%. The results of this study provide geochemical evidence for hidden geothermal resource exploration in deep fault zones.

Mine water hazards are one of the main factors limiting the safe and efficient extraction of coal resources in China. The rapid and accurate identification of the source of water inrushes is central to the prevention and control of mine water hazards. This study aims to address the issues of complex pre-treatment procedures and low accuracy in identifying mixed water samples associated with traditional methods for determining the source of mine water inrushes. This study proposes an intelligent model for identifying the source of mine water inrushes that integrates ultraviolet–visible spectrophotometry (UV–Vis) with convolutional neural networks (CNNs). This model utilizes convolutional neural networks to automatically extract features from and classify spectral images of water sources associated with mine water inrushes, eliminating the cumbersome pre-processing steps involved in traditional spectral source analysis and significantly improving the efficiency of water source identification. The CNN is used to classify and identify the mine water spectral images measured by UV–Vis. The model training results showed that the accuracy of the model was 98.89%, 95.93%, and 90.67% for the training sets of single water samples, mixed water samples, and overall water samples, respectively. The test results indicated that the model was accurate for all the water samples in the test set, and the UV-CNN model had better classification recognition ability for complex mixed water samples compared with the water chemistry-based kernel function principal component analysis and support vector machine (KPCA-SVM) discrimination model. When the characteristics of water samples are relatively similar, the discriminative advantage of the model becomes more prominent. This model has the features of fast convergence speed, short computing time, high discriminative accuracy and stability, and can provide an efficient technical method for the rapid and accurate identification of the water source of mine water inrush.