The deep integration of machine learning technology with geological prospecting has brought to the forefront a key challenge: how to construct geological-mineralization models by fusing multi-source data, select model features with guidance from metallogenic factors, build multi-source metallogenic prediction models with geological constraints, and ultimately achieve a thorough integration of domain knowledge and machine intelligence. The Eastern-Central Tianshan region is one of China’s most important copper–nickel mineral resource bases, predominantly hosting magmatic copper–nickel sulfide deposits with significant resource potential. In this context, this paper proposes a metallogenic prediction model based on multi-modal feature fusion technology. The model employs a Residual Neural Network (ResNet) incorporating a Squeeze-and-Excitation (SE) attention mechanism and a Multi-Layer Perceptron (MLP) to extract features from different modalities. It integrates multi-source data, including geochemical information, geological metallogenic factors, and aeromagnetic data. A cross-modal feature interaction module, constructed using attention weighting and a gating mechanism, enables deep fusion of the features. After training, the model achieved a prediction accuracy of 97% on the test set. Compared to a unimodal model constructed using Random Forest, the confidence and discriminative capability of the training results were significantly enhanced, validating the effectiveness of multi-modal feature fusion. Applying the trained model to the study area, a total of 11 prospective metallogenic zones were delineated. These include 4 zones in the peripheries of known deposits and 7 zones in previously unexplored (blank) areas. Notably, some known mineral occurrences fall within the predicted blank-area targets, validating the feasibility and significant value of multi-modal feature fusion in mineral prediction. This work provides a novel methodology for the subsequent integrated processing of multi-source data.

The geoelectrochemical extraction method is effective for locating deep concealed deposits, but research on the particle size distribution of its anomaly-causing substances remains limited. To address this, 20 sampling points were established along the No. 20 exploration profile at the Tongjiangling Copper Deposit in Jiangxi Province. Using consistent technical conditions, geoelectrochemical measurements were compared across filter membranes/papers with pore sizes of 0.22 μm, 0.45 μm, 1 μm, 3 μm, and qualitative medium-speed filter paper (approx. 20–30 μm). The results are as follows: (1) The 20–30 μm filter paper effectively detected anomalies corresponding to both shallow and deep concealed ore bodies, whereas smaller pore sizes only revealed shallow ore bodies. (2) Element content and anomaly contrast were significantly higher with the 20–30 μm filter paper compared to smaller pore sizes. (3) Geoelectrochemical anomalies originate from various surface soil substances, which may exist independently or be adsorbed onto particles of different sizes. The applied electric field mobilizes these charged particles, enabling their adsorption onto the collector and acquisition of deep mineralization anomalies. (4) For similar landscapes and deposit types, using filter paper with a pore size of approximately 20–30 μm is recommended to effectively capture deep ore body anomalies while reducing analytical complexity.