The close spatial and genetic coexistence of Skarn-type and Hydrothermal Vein-type Pb-Zn deposits in the Shanghulin area, Inner Mongolia, poses a significant challenge to conventional “ undifferentiated” prediction models. This study aims to decouple these distinct metallogenic patterns using a data-driven, “type-specific modeling” strategy, establishing separate prediction models for Skarn-type and Hydrothermal Vein-type mineralization. Our workflow first employs Lasso–RFECV for rigorous pre-screening of over 60 geoscience features to identify the optimal predictive subset. Subsequently, an XGBoost model is trained on these selected features, and the SHAP framework is applied to interpret the geological significance of its decision logic. The results confirm two distinct indicator systems. (1) The Skarn-type model is controlled by spatial proximity to a heat source, heavily relying on Distance_to_Volcano and high-temperature indicators (CLR_Mo, CLR_W, CLR_Mn). (2) The Hydrothermal Vein-type model is “chemical fingerprint-driven”, prioritizing CLR_Y and identifying a complex “leaching-enrichment” pattern: mineralization requires simultaneous wall-rock leaching (low CLR_Al₂O₃, low CLR_Y) and specific metal enrichment (high CLR_Co, high CLR_Zn). This study confirms the controlling factors: Skarn-type deposits are governed by magmatic proximity, whereas Hydrothermal Vein-type deposits are defined by specific alteration geochemical signatures. The proposed “Lasso–RFECV → XGBoost → SHAP” workflow successfully decouples these independent, geologically meaningful prospectivity models from complex data, offering a new paradigm for precise exploration.

The Xiaoyinuogaigou (XYN) gold deposit is located in the central Erguna Metallogenic Belt, northeastern China, and represents a characteristic example of Mesozoic gold mineralization in the Mongol–Okhotsk orogenic province. Despite its economic significance, the timing of mineralization and the nature of the ore-forming fluid system have not been well constrained. To address these questions, a systematic investigation of fluid inclusions, isotopes, geochemistry, and geochronology was conducted. The study reveals that: (i) four types of fluid inclusions are identified in auriferous quartz veins, with co-existing aqueous liquid-vapor and NaCl daughter-mineral three-phase inclusions, indicating the involvement of at least two chemically distinct fluids; (ii) the ore-forming fluids are characterized by moderate temperatures (163.2–357.6 °C), low to moderate salinities (3.06–11.34 wt% NaCleqv.), and H–O isotope compositions (δD = −133.3 to −112.3‰; δ¹⁸O fluid (SMOW) = +1.74 to +4.06‰) consistent with a hydrothermal system incorporating a substantial non-magmatic water component; and (iii) REE geochemistry and sulfur isotopes (δ³⁴S = +4.47 to +11.75‰, mean +8.29‰, n = 4) indicate that ore-forming materials were derived at least in part from the ore-hosting granite porphyry. Zircon U–Pb geochronology constrains the granite porphyry crystallization to 180 ± 3 Ma, and hydrothermal monazite U–Pb dating yields an age of 162.3 ± 3.6 Ma (MSWD = 0.95), for a Middle Jurassic hydrothermal event. We therefore conclude that XYN is an epizonal orogenic gold deposit formed during the late compressional to post-collisional transition of the Mongol–Okhotsk orogeny.