GeoChemAD: Benchmarking Unsupervised Geochemical Anomaly Detection for Mineral Exploration
Fuente:
arXiv
Salvato in:
| Autori principali: | , , , , |
|---|---|
| Natura: | Preprint |
| Pubblicazione: |
2026
|
| Soggetti: | |
| Accesso online: | |
| Tags: |
Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
|
| _version_ | 1866911512484904960 |
|---|---|
| author | Ding, Yihao Zhang, Yiran Gonzalez, Chris Holden, Eun-Jung Liu, Wei |
| author_facet | Ding, Yihao Zhang, Yiran Gonzalez, Chris Holden, Eun-Jung Liu, Wei |
| contents | Geochemical anomaly detection plays a critical role in mineral exploration as deviations from regional geochemical baselines may indicate mineralization. Existing studies suffer from two key limitations: (1) single region scenarios which limit model generalizability; (2) proprietary datasets, which makes result reproduction unattainable. In this work, we introduce \textbf{GeoChemAD}, an open-source benchmark dataset compiled from government-led geological surveys, covering multiple regions, sampling sources, and target elements. The dataset comprises eight subsets representing diverse spatial scales and sampling conditions. To establish strong baselines, we reproduce and benchmark a range of unsupervised anomaly detection methods, including statistical models, generative and transformer-based approaches. Furthermore, we propose \textbf{GeoChemFormer}, a transformer-based framework that leverages self-supervised pretraining to learn target-element-aware geochemical representations for spatial samples. Extensive experiments demonstrate that GeoChemFormer consistently achieves superior and robust performance across all eight subsets, outperforming existing unsupervised methods in both anomaly detection accuracy and generalization capability. The proposed dataset and framework provide a foundation for reproducible research and future development in this direction. |
| format | Preprint |
| id |
arxiv_https___arxiv_org_abs_2603_13068 |
| institution | arXiv |
| publishDate | 2026 |
| record_format | arxiv |
| spellingShingle | GeoChemAD: Benchmarking Unsupervised Geochemical Anomaly Detection for Mineral Exploration Ding, Yihao Zhang, Yiran Gonzalez, Chris Holden, Eun-Jung Liu, Wei Machine Learning Artificial Intelligence Geochemical anomaly detection plays a critical role in mineral exploration as deviations from regional geochemical baselines may indicate mineralization. Existing studies suffer from two key limitations: (1) single region scenarios which limit model generalizability; (2) proprietary datasets, which makes result reproduction unattainable. In this work, we introduce \textbf{GeoChemAD}, an open-source benchmark dataset compiled from government-led geological surveys, covering multiple regions, sampling sources, and target elements. The dataset comprises eight subsets representing diverse spatial scales and sampling conditions. To establish strong baselines, we reproduce and benchmark a range of unsupervised anomaly detection methods, including statistical models, generative and transformer-based approaches. Furthermore, we propose \textbf{GeoChemFormer}, a transformer-based framework that leverages self-supervised pretraining to learn target-element-aware geochemical representations for spatial samples. Extensive experiments demonstrate that GeoChemFormer consistently achieves superior and robust performance across all eight subsets, outperforming existing unsupervised methods in both anomaly detection accuracy and generalization capability. The proposed dataset and framework provide a foundation for reproducible research and future development in this direction. |
| title | GeoChemAD: Benchmarking Unsupervised Geochemical Anomaly Detection for Mineral Exploration |
| topic | Machine Learning Artificial Intelligence |
| url | https://arxiv.org/abs/2603.13068 |