Metric learning networks for accurate mineral detection with different augmentation techniques

Accurate mineral identification from hyperspectral satellite data is critical for efficient mineral exploration. Traditional one-class classification methods, such as OCSVM and Isolation Forest with data augmentation, often struggle to generalize across diverse spectral patterns, leading to low F1 scores despite high recall. In this study, we propose a metric learning network approach for a one-class mineral classification, utilizing an augmented dataset and preprocessing techniques such as continuum removal. The results show that the proposed method significantly improves the F1 scores for minerals such as Alunite or Jarosite compared to previous methods, while using continuous removal further enhances recall. These findings demonstrate that a simple metric learning architecture, combined with careful preprocessing, can outperform traditional one-class classifiers and provide more reliable detection of target minerals from hyperspectral data. The proposed solution achieves F1-scores up to 0.725 (Jarosite) and 0.451 (Alunite), representing multiple-fold improvements over previous one-class baselines, with recall reaching 0.945 and 0.679 respectively.