Mineral prospectivity mapping (MPM) is crucial for efficient mineral exploration, where prospective zones are identified in a cost-effective manner. This study focuses on generating prospectivity maps for hydrothermal polymetallic mineralization in the Feizabad area, in northeastern Iran, using unsupervised anomaly detection methods, i.e., isolation forest (IForest) and deep isolation forest (DIF) algorithms. As mineralization events are rare and complex, traditional approaches continue to encounter difficulties, despite advances in MPM. In this respect, unsupervised anomaly detection algorithms, which do not rely on ground truth samples, offer a suitable solution. Here, we compile geospatial datasets on the Feizabad area, which is known for its polymetallic mineralization showings. Fourteen evidence layers were created, based on the geology and mineralization characteristics of the area. Both the IForest and DIF algorithms were employed to identify areas with high mineralization potential. The DIF, which uses neural networks to handle non-linear relationships in high-dimensional data, outperformed the traditional decision tree-based IForest algorithm. The results, evaluated through a success rate curve, demonstrated that the DIF provided more accurate prospectivity maps, effectively capturing complex, non-linear relationships. This highlights the DIF algorithm’s suitability for MPM, offering significant advantages over the IForest algorithm. The present study concludes that the DIF algorithm, and similar unsupervised anomaly detection algorithms, are highly effective for MPM, making them valuable tools for both brownfield and greenfield exploration.

Traditional clustering algorithms are popular unsupervised methods and have been widely applied in mineral prospectivity mapping (MPM). Despite the advantages of these algorithms in terms of simplicity and popularity, they are not strong enough to struggle with high-dimensional, complex, and non-linear geospatial data. Consequently, they may lead to suboptimal clustering performance, a reason for not being able to precisely recognize and discriminate complex mineralization-related anomaly patterns in mineral exploration datasets. To improve the clustering performance, we propose a deep embedded clustering (DEC) approach for MPM. DEC is an unsupervised method that uses deep neural networks to learn from the feature representations and optimize cluster assignments simultaneously. In this study, evidence layers, representing porphyry copper mineralization, were first generated. Then, four clustering techniques were applied to generate prospectivity models. The prediction rate of the models was evaluated using the prediction-area (P-A) plot. The results showed that the prediction rates of K-means, Gaussian mixture model (GMM), DEC-K-means, and DEC-GMM prospectivity models were 66, 68, 69, and 72%, respectively. This demonstrates that DEC-based clustering outperforms conventional clustering algorithms and that DEC-GMM effectively recognizes mineralization-related patterns. Finally, to benefit from the advantages of all the applied clustering methods, we calculated a confidence index, as an ensemble technique, to recognize exploration targets, those that support further mineral exploration programs in terms of low uncertainty.

Convolutional neural networks (CNNs) have shown considerable potential for mineral prospectivity mapping (MPM); however, their predictive performance largely depends on appropriate hyperparameter optimization. In practice, hyperparameters are commonly selected through trial and error, which is labor-intensive, time-consuming, and often depends on user’s experience with both the application domain and the algorithm. This study investigates the use of the grey wolf optimization (GWO) algorithm to automatically optimize the hyperparameters of a lightweight CNN for regional-scale MPM. To demonstrate the proposed procedure, the Pariz porphyry copper district in Kerman province, Iran, was selected as a case study. Seven evidence layers representing different ore-forming subsystems were generated based on the geological characteristics of the region and a conceptual model of porphyry copper mineralization, and subsequently integrated using both the proposed GWO-CNN model and an expert-tuned CNN. The results of cross-validation show that neither model consistently outperformed the other across conventional classification metrics. The GWO-CNN outperformed the expert-tuned CNN in terms of AUC (0.8 versus 0.76), whereas both models achieved the same mean accuracy. However, in terms of exploration-oriented evaluation, the prediction-area (P-A) plot showed a higher prediction rate for the GWO-CNN (76%) than for the expert-tuned CNN (73%). The performance evaluation highlights the importance of considering prospective area in model evaluation. In addition, the final prospectivity map delineated several exploration targets that show strong spatial associations with intrusive rocks and other favorable geological features related to porphyry copper mineralization. Some targets, however, were identified in areas characterized by weak mineralization-related signals and no known mineral occurrences (KMOs). From the perspective of the survival bias concept, these areas may represent opportunities for future mineral discoveries at depth.