A Novel Spatial–Element Transformer with Dual Attention Architecture for Mineral Prospectivity Mapping
Minerals · 27.07.2026 · 16 (8) · 783
DOI: 10.3390/min16080783 ↗Kurz gefasst
Fachartikel in der Zeitschrift Minerals, online erschienen am 27.07.2026. Verfasst von Yujiaying Cheng und 10 weiteren Autor:innen. Die Arbeit nennt 66 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0). Gefördert von: National Natural Science Foundation of China, Deep Earth Probe and Mineral Resources Exploration–National Science and Technology Major Project, Basic Research Fund of the Institute of Mineral Resources, Chinese Academy of Geological Sciences.
Abstract (Originalsprache)
In recent years, data-driven mineral prospectivity mapping (MPM) has become a key technical approach for delineating exploration targets. Nevertheless, two major challenges persist. First, sampling is often sparse and irregularly distributed, making it difficult to represent spatial relationships effectively. Second, many existing models implicitly assign equal importance to all geochemical elements. They also fail to jointly model heterogeneous elemental contributions and spatial neighborhood relationships. To address these issues, we propose the Spatial–Element Transformer (SETransformer), which integrates SHapley Additive exPlanations (SHAP)-derived element-importance attention bias with adaptive-bandwidth spatial-decay attention for data-driven MPM. We evaluate the proposed method using data from the Jiama porphyry–skarn Cu-polymetallic deposit in Tibet, China, within two a priori defined metallogenic feature subspaces: Mo-type and Cu-type. SETransformer is benchmarked against conventional machine learning models (Random Forest (RF), eXtreme Gradient Boosting (XGBoost), support vector machine (SVM)), and deep learning baselines (graph convolutional network (GCN) and TabNet). Model performance is assessed under two spatial validation schemes: a south–north hold-out validation and a five-fold spatial block cross-validation. Under both schemes, SETransformer achieves the best overall performance in the two subspaces. The predicted MPMs are consistent with regional geological evidence and exhibit clearer boundaries, providing a useful reference for subsequent target delineation in the study area.
Förderung
- National Natural Science Foundation of China
- Deep Earth Probe and Mineral Resources Exploration–National Science and Technology Major Project
- Basic Research Fund of the Institute of Mineral Resources, Chinese Academy of Geological Sciences
- China Scholarship Council, and the Geological Survey Project
Zitieren
APA
Cheng, Y., Jiang, Y., Ma, Y., Cao, M., Wang, Z., Wang, M., Wang, D., Guo, N., Tang, P., Lin, B., & Yang, Y. (2026). A Novel Spatial–Element Transformer with Dual Attention Architecture for Mineral Prospectivity Mapping. Minerals, 16(8), 783. https://doi.org/10.3390/min16080783
Vancouver
Cheng Y, Jiang Y, Ma Y, Cao M, Wang Z, Wang M, et al. A Novel Spatial–Element Transformer with Dual Attention Architecture for Mineral Prospectivity Mapping. Minerals. 2026;16(8):783. doi:10.3390/min16080783
BibTeX
@article{Cheng2026,
author = {Cheng, Yujiaying and Jiang, Yuchen and Ma, Yun and Cao, Minggao and Wang, Zhichao and Wang, Mengdie and Wang, Dingchun and Guo, Na and Tang, Pan and Lin, Bin and Yang, Yanbing},
title = {A Novel Spatial–Element Transformer with Dual Attention Architecture for Mineral Prospectivity Mapping},
journal = {Minerals},
year = {2026},
volume = {16},
number = {8},
pages = {783},
doi = {10.3390/min16080783}
}
EUVIMED