The Hatu region in the Western Junggar, Xinjiang, is one of the most significant gold metallogenic concentration areas in China. Gold mineralization is primarily controlled by several parallel NE-trending strike-slip faults and Late Paleozoic granitic plutons, accompanied by multiple stages of hydrothermal activity. To enhance the objectivity and accuracy of mineral prospecting prediction, this study develops an integrated forecasting framework that combines multi-source remote sensing datasets with machine learning techniques. Alteration anomalies related to iron staining and hydroxyl-bearing minerals are extracted from ASTER data, alteration mineral mapping is performed using GF-5 hyperspectral imagery, and Landsat-9 data is used for structural interpretation to refine the regional metallogenic framework. On this basis, these multi-source remote sensing products are then integrated to delineate five prospective metallogenic areas (T1–T5). Subsequently, a Random Forest (RF) model optimized by the Grey Wolf Optimizer (GWO) algorithm is employed to quantitatively integrate key evidence layers, including alteration, structure, and geochemistry, for estimating mineralization probability. The results show that the GWO-RF model effectively concentrates anomalous areas and identifies two high-confidence targets, Y1 and Y2, both with mineralization probabilities exceeding 0.8. Among them, the Y1 target is associated with the Bieluagaxi pluton and exhibits strong montmorillonitization, chloritization, and iron-staining alteration, typical for magmatic–hydrothermal controlled mineralization. In contrast, the Y2 target is strictly controlled by the Anqi Fault and its subsidiary faults, primarily characterized by linear chloritization and iron-staining anomalies indicative of structure–hydrothermal mineralization. Field verification confirms the significant metallogenic potential of both Y1 and Y2, demonstrating the effectiveness of integrating multi-source remote sensing and machine learning for predicting orogenic gold systems. This approach not only deepens the understanding of the diverse gold mineralization processes in the Western Junggar but also provides a transferable methodology and case study for improving regional mineral exploration accuracy.

Coal spontaneous combustion in arid regions poses severe threats to both ecological security and resource sustainability. Focusing on the detection challenges in Fire Zone No. 1 of the Miaoergou Coalfield, Xinjiang, this study proposes an Integrated Geophysical Collaborative Detection Framework that combines high-precision magnetic surveys, spontaneous potential (SP) measurements, and transient electromagnetic (TEM) methods. This innovative framework effectively overcomes the limitations of traditional single-method detection approaches, enabling the precise delineation of fire zone boundaries and the accurate characterization of spatial dynamics of coal fires. The key findings of the study are as follows: (1) High-magnetic anomalies (with a maximum ΔT of 1886.3 nT) exhibit a strong correlation with magnetite-enriched burnt rocks and dense fracture networks (density > 15 fractures/m), with a correlation coefficient (R²) of 0.89; (2) Negative SP anomalies (with a minimum SP of −38.17 mV) can effectively reflect redox interfaces and water-saturated zones (moisture content > 18%), forming a “positive–negative–positive” annular spatial structure where the boundary gradient exceeds 3 mV/m; (3) TEM measurements identify high-resistivity anomalies (resistivity ρ = 260–320 Ω·m), which correspond to non-waterlogged goaf collapse areas. Spatial integration analysis of the three sets of geophysical data shows an anomaly overlap rate of over 85%, and this result is further validated by borehole data with an error margin of less than 10%. This study demonstrates that multi-parameter geophysical coupling can effectively characterize the thermo-hydro-chemical processes associated with coal fires, thereby providing critical technical support for the accurate identification of fire boundaries and the implementation of disaster mitigation measures in arid regions.

Interpreting multispectral remote sensing data for hydrothermal alteration mapping remains challenging in complex mountainous metallogenic belts because dense pixel-level field labels are difficult to obtain and weak spectral responses are affected by lithological background, vegetation, snow/ice cover, and topographic shadow. This study proposes a principal component analysis (PCA)-guided weakly supervised workflow for mapping hydroxyl- and iron-oxide-related spectral anomalies in the Bulong–Maidan–Tuoyun gold–copper metallogenic belt, southwestern Tianshan, China, using Landsat 8 Operational Land Imager (OLI) imagery. PCA was used as a spectral prior to generate PCA-derived positive spectral anomaly samples for model training. A Residual-ECA Alteration Information Extraction (REA-AIE) model was developed to refine PCA-derived anomalies by learning local spectral–spatial features from multispectral image patches. Under the PCA-constrained random sample-level evaluation, REA-AIE achieved F1 scores of 95.90% and 97.09% for hydroxyl- and iron-oxide-related spectral anomalies, respectively; these values indicate agreement with PCA-derived pseudo-labels rather than spatially independent estimates of mapping performance. Petrography-constrained site-level assessment showed that REA-AIE-predicted spectral anomalies occurred within 90 m of 43 of the 53 altered sites, corresponding to a site-level recall of 81.13% and supporting their consistency with field-based geological evidence.

The Karamaili Granite Belt (KGB) in the southern margin of the Eastern Junggar is the most important tin metallogenic belt in the southwestern Central Asian Orogenic Belt. The plutons in the western part have a close genetic relationship with tin mineralization. The zircon U-Pb ages of the Kamusite, Laoyaquan, and Beilekuduke plutons are 315.1 ± 3.4 Ma, 313.6 ± 2.9 Ma, and 316.5 ± 4.6 Ma, respectively. The plutons have high silica (SiO₂ = 75.53%–77.85%), potassium (K₂O = 4.43%–5.42%), and alkalis (K₂O + Na₂O = 8.17%–8.90%) contents and low ferroan (Fe₂O₃^T = 0.90%–1.48%), calcium, and magnesium contents and are classified as metaluminous–peraluminous, high-potassium, calc-alkaline iron granite. The rocks are enriched in Rb, Th, U, K, Pb, and Sn and strongly depleted in Ba, Sr, P, Eu, and Ti. They have strongly negative Eu anomalies (δEu = 0.01–0.05), 10,000 Ga/Al = 2.87–4.91 (>2.6), showing the geochemical characteristics of A-type granite. The zircon U/Pb ratios indicate that the above granites should be I- or A-type granite, which is generally formed under high-temperature (768–843 °C), low-pressure, and reducing magma conditions. The high Rb/Sr ratio (a mean of 48 > 1.2) and low K/Rb ratio (53.93–169.94) indicate that the tin-bearing plutons have undergone high differentiation. The positive whole-rock εNd(t) values (3.99–5.54) and the relatively young Nd T_2DM model ages (616–455 Ma) suggest the magma is derived from partially melted juvenile crust, and the underplating of basic magma containing mantle materials that affected the source area. The results indicate the KGB was formed in the tectonic transition period in the late Carboniferous subduction post-collision environment. Orogenic compression influenced the tin-bearing plutons in the western part of the KGB, forming highly differentiated and reduced I, A-type transition granite. An extensional environment affected the plutons in the eastern sections, creating A-type granite with dark enclaves that suggest magma mixing with little evidence of tin mineralization.