1887

Abstract

Summary

The mineral prospectivity mapping (MPM) approach traditionally relies on binary classification using confirmed mineral deposit data, often leading to label imbalance and limited exploration scope. To address this, we propose an expanded labelling strategy that incorporates the distribution of associated minerals spatially related to the target mineral. This approach quantitatively reflects mineralization patterns by applying conditional Jaccard similarity and distance-based weighting to generate continuous labels. A CNN-based 2D MPM model was trained using combined surface geology, geophysics, geochemistry, and remote sensing data. Compared to binary classification, the continuous label approach enables broader exploration of areas potentially affected by mineralization processes. Additionally, principal component analysis (PCA) and entropy-based weighting were applied to assess infrastructure factors such as transportation access, water supply, and environmental restrictions. The integration of prospectivity and development feasibility results was visualized using an RGB channel mapping technique, supporting more intuitive and strategic exploration decision-making.

© EAGE Publications BV
Loading

Article metrics loading...

/content/papers/10.3997/2214-4609.202520156
2025-09-07
2026-02-15

  • From This Site

    /content/papers/10.3997/2214-4609.202520156
    dcterms_title,dcterms_subject,pub_keyword
    -contentType:Journal -contentType:Contributor -contentType:Concept -contentType:Institution
    10
    5
Loading full text...

Full text loading...

References

  1. Cai, P. and Ma, X. [2024] Metallogenic regularity and main research progress of cobalt and nickel deposits in China. Journal of Geochemical Exploration, 107574.
     [Google Scholar]
  2. Naldrett, A. J. [2013] Magmatic sulfide deposits: geology, geochemistry and exploration. Springer Science & Business Media.
     [Google Scholar]
  3. Müller, D., Groves, D. I., Santosh, M. and Yang, C. X. [2025] Critical metals: Their mineral systems and exploration. Geosystems and Geoenvironment, 4(1), 100323.
     [Google Scholar]
  4. Han, Y., Liu, Y. and Li, W. [2020] Mineralogy of Nickel and Cobalt Minerals in Xiarihamu Nickel–Cobalt Deposit, East Kunlun Orogen, China. Frontiers in Earth Science, 8, 597469.
     [Google Scholar]
  5. Enns, S. G. [1971] A nickel deposit in southern British Columbia.
     [Google Scholar]
  6. Zuo, R., Peng, Y., Li, T. and Xiong, Y. [2020] Challenges of geological prospecting big data mining and integration using deep learning algorithms. Earth Science (In Chinese with English abstract).
     [Google Scholar]
  7. Li, T., Zuo, R., Xiong, Y. and Peng, Y. [2021] Random-drop data augmentation of deep convolutional neural network for mineral prospectivity mapping. Natural Resources Research, 30, 27–38.
     [Google Scholar]
  8. Li, Q., Chen, G. and Luo, L. [2023] Mineral prospectivity mapping using attention-based convolutional neural network. Ore Geology Reviews, 156, 105381.
     [Google Scholar]
/content/papers/10.3997/2214-4609.202520156
Loading
CNN-Based Mineral Prospectivity Mapping for Critical Mineral Exploration in South Korea
Conference Proceedings 2025, 1 (2025); https://doi.org/10.3997/2214-4609.202520156
/content/papers/10.3997/2214-4609.202520156
/content/papers/10.3997/2214-4609.202520156
Loading

Data & Media loading...

Most Cited This Month Most Cited RSS feed

This is a required field
Please enter a valid email address
Approval was a Success
Invalid data
An Error Occurred
Approval was partially successful, following selected items could not be processed due to error