Predicting mineral deposits accurately requires capturing the complex interactions among geological structures, geochemical anomalies, and alteration patterns. To address this challenge, this study develops a Knowledge–Data Collaboration Graph Attention Network (KDCGAT) to improve copper mineralization prediction by integrating multi-source geological data. The model combines Graph Attention Network (GAT) with multimodal geoscience data, including fracture structures, remote sensing alteration maps, and geochemical anomalies. Spatial correlations are captured through a self-attention mechanism, aligning deep learning predictions with geological and geochemical knowledge. Using the eastern Tien Shan copper belt in Xinjiang as a case study, KDCGAT achieves a copper deposit identification accuracy of 85.9%, outperforming Weight of Evidence (WoE) by 7%, Graph Convolutional Network (GCN) by 11.3%, and Convolutional Neural Network (CNN) by 19.7%. Ablation experiments show a 21.1% improvement over the baseline GAT model. Finally, five Class A and three Class B mineralization prediction zones are delineated. This study demonstrates the effectiveness of graph neural networks for copper prospectivity prediction and highlights knowledge–data collaboration as a practical tool for mineral exploration.
Geochemical anomaly detection is a critical stage in mineral exploration, playing a key role in predicting potential mineral targets. Traditional methodologies often struggle to integrate the spatial structure of geochemical data with underlying geological constraints effectively. To address this limitation, we propose GeoCLA, a geochemical anomaly detection framework that integrates Convolutional Neural Networks (CNNs), Bidirectional Long Short-Term Memory (BiLSTM) networks, and an Attention Mechanism (AM). This integrated spatial-attention architecture captures complex correlations among multiple features to improve anomaly identification. The method constructs spatial sequential samples from geochemical data. The CNNs extract local spatial patterns, the BiLSTM models sequential dependencies, and the AM enhances the representation of critical features. Anomaly scores are computed using the reconstruction error between the model output and the original data. In addition, a fault-distance weighting factor is incorporated to build a comprehensive anomaly evaluation index. The proposed model was applied to the Hatu gold district in Xinjiang, China. Both visual analysis and quantitative evaluation demonstrate effectiveness, achieving a ROC-AUC of 0.86 and a mineral occurrence coverage rate of 97% within moderate-to-high anomaly prospective areas, significantly outperforming baseline methods.