The Xiahe-Hezuo area in Gansu Province, China, located in the West Qinling Metallogenic Belt, is characterized by complex regional geological structures and abundant mineral resources. A number of gold-polymetallic deposits have been identified in this region, demonstrating significant potential for gold-polymetallic mineral prospecting within the metallogenic belt. This study focuses on regional Mineral Prospectivity Mapping (MPM) in the Xiahe-Hezuo area. To address the common challenge of small-sample data limitations in geological prediction, we introduce a Wasserstein Generative Adversarial Network with gradient penalty (WGAN-GP) to generate high-fidelity geological feature samples, effectively expanding the training dataset. A Convolutional Neural Network (CNN) was used to train and predict on both pre- and post-augmentation data. The experimental results show that, before augmentation, the CNN model’s Receiver Operating Characteristic (ROC) value was 0.9648. After data augmentation with the WGAN-GP, the CNN model’s ROC value improved to 0.9792. Additionally, the CNN model’s classification performance was significantly enhanced, with the training set accuracy increasing by 5% and the test set accuracy improving by 2%, successfully overcoming the issue of insufficient model generalization caused by small sample sizes. The mineralization prediction results based on data augmentation delineate five prospective mineralization targets, whose spatial distribution exhibits strong correlations with known deposits and fault structural belts, confirming the reliability of the predictions. This study validates the effectiveness of data augmentation techniques in MPM and provides a transferable technical framework for MPM in data-scarce regions.

This study employs multi-source remote sensing information and machine learning methods to comprehensively assess the geological background, structural features, alteration anomalies, and spectral characteristics of the Malkansu Manganese Ore Belt in Xinjiang. Manganese mineralization is predicted, and areas with high mineralization potential are delineated. The results of the feature factor weight analysis indicate that structural density and lithological characteristics contribute most significantly to manganese mineralization. Notably, linear structures are aligned with the direction of the manganese belt, and areas exhibiting high controlling structural density are closely associated with the locations of mineral deposits, suggesting that structure plays a crucial role in manganese production in this region. The Area Under the Curve (AUC) values for the Random Forest (RF), Naïve Bayes (NB), and eXtreme Gradient Boosting (XGBoost) models were 0.975, 0.983, and 0.916, respectively, indicating that all three models achieved a high level of performance and interpretability. Among these, the NB model demonstrated the highest performance. By algebraically overlaying the predictions from these three machine learning models, a comprehensive mineralization favorability map was generated, identifying 11 prospective mineralization zones. The performance metrics of the machine learning models validate their robustness, while regional tectonics and stratigraphic lithology provide valuable characteristic factors for this approach. This study integrates multi-source remote sensing information with machine learning methods to enhance the effectiveness of manganese prediction, thereby offering new research perspectives for manganese forecasting in the Malkansu Manganese Ore Belt.