UNSUPERVISED DELINEATION OF PROSPECTIVITY ZONES FOR STRATIFORM CU-CO IN THE SOUTHERN COPPERBELT MARGIN (ZAMBIA)

This study presents an unsupervised workflow for delineating prospectivity zones for stratiform copper-cobalt mineralization in the southern margin of the Central African Copperbelt, Zambia, using only airborne geophysical data (gravity, magnetics, radiometry, terrain). Three clustering algorithms-K-Means, Fuzzy C-Means (FCM), and Self-Organizing Maps (SOM)-were applied, followed by consensus clustering to isolate robust target zones. Key geophysical filters (tilt derivative, total horizontal derivative, analytic signal) and radiometric ratios (U/Th, U/K) were computed and compared across clusters. The most prospective cluster was validated against literature-calibrated geophysical thresholds and was found to match known exploration criteria and regional structural trends. A final probabilistic prospectivity map was generated from FCM membership, classifying targets into three confidence levels. While lack of drill-hole data prevents quantitative accuracy assessment, this approach demonstrates that fully unlabeled machine learning on airborne data can effectively guide early-stage exploration in data-sparse regions. The proposed workflow offers a reproducible framework for AI-driven prospectivity mapping in frontier terrains.

1. Ndonfack, K.I.A., Yang, Z., Zhang, J., Whattam, S.A., Xie, Y. Geology, geochemistry, and exploration of the Central African Copperbelt: a review. International Geology Review (2024). http://doi.org/10.1080/00206814.2024.2426200

2. Yousefi, M., Carranza, E.J.M. Data-driven index overlay and Boolean logic mineral prospectivity modeling in greenfields exploration. Natural Resources Research, 25(1), 3–18 (2016). https://doi.org/10.1007/s11053-014-9261-9

3. Saremi, M., Hezarkhani, A., Seyyed Mirzabozorg, S.A.A., DehghanNiri, R., Shirazy, A., Shirazi, A. Unsupervised anomaly detection for mineral prospectivity mapping using Isolation Forest and Extended Isolation Forest algorithms. Minerals, 15(4), 411 (2025). https://doi.org/10.3390/min15040411

4. Xiong, Y., Zuo, R. A positive and unlabeled learning algorithm for mineral prospectivity mapping. Computers & Geosciences, 147, 104667 (2021). https://doi.org/10.1016/j.cageo.2020.104667

5. Wang, C., Chen, J., Ouyang, Y. Determination of predictive variables in mineral prospectivity mapping using supervised and unsupervised methods. Natural Resources Research, 31, 2081–2102 (2022). https://doi.org/10.1007/s11053-021-09930-5

6. Sharapatov, A., Saduov, A., Assirbek, N., Abdyrov, M., Zhumabayev, B. Prediction of rare and anomalous minerals using anomaly detection and machine learning techniques. Applied Computing and Geosciences, 26, 100250 (2025). https://doi.org/10.1016/j.acags.2025.100250

7. Rezapour, M.J., Abedi, M., Bahroudi, A., Rahimi, H. A clustering approach for mineral potential mapping: a deposit-scale porphyry copper exploration targeting. Geopersia, 10(1), 149–163 (2020). http://doi.org/10.22059/geope.2019.284414.648488

8. Martin, R., Boisvert, J. Ensemble spatial and multivariate clustering with geomodeling-specific clustering metrics. Computers & Geosciences, 120, 82–96 (2018). https://doi.org/10.1016/j.cageo.2018.08.005

9. Strehl, A., Ghosh, J. Cluster ensembles – a knowledge reuse framework for combining multiple partitions. Journal of Machine Learning Research, 3, 583–617 (2002). https://doi.org/10.1162/153244303321897735

10. Miller, H.G., Singh, V. Potential field tilt – A new concept for location of potential field sources. Journal of Applied Geophysics, 32(2-3), 213-217 (1994). https://doi.org/10.1016/0926-9851(94)90022-1

11. Cooper, G.R.J. Balancing images of potential-field data. Geophysics, 74(3), L17–L20 (2009). https://doi.org/10.1190/1.3096615

12. Yan, T.-J., Wu, Y.-G., Yuan, Y., Chen, L.-N. Edge detection of potential field data using an enhanced analytic signal tilt angle. Chinese Journal of Geophysics, 59(4), 341-349 (2016).

13. Kianoush, P., Faraj Khah, N.K., Hosseini, S.A., Jamshidi, E., Afzal, P., Ebrahimabadi, A. Geobody estimation by Bhattacharyya method utilizing nonlinear inverse modeling of magnetic data in Baba-Ali iron deposit, NW Iran (2023). https://doi.org/10.21203/rs.3.rs-2433584/v6

14. Abdel-Hakeem, M., El-Tahir, M., Abu Zeid, E., et al. Genetic implications of Th/U, Th/K, and U/K ratios for U mineralizations: a case study from El-Missikat and El-Erediya shear zones, Eastern Desert, Egypt. Geochemical Transactions, 24(1), 3 (2023). https://doi.org/10.1186/s12932-023-00083-3

15. Sharapatov, A., Assirbek, N., Saduov, A., Abdyrov, M., Zhumabayev, B. Consolidated geological and geophysical characteristics of uranium deposit rocks and prospects for their utilization (Shu-Sarysu Province, Kazakhstan). News of the National Academy of Sciences of the Republic of Kazakhstan, Series of Geology and Technical Sciences, 2024(6), 210–229 (2024). https://doi.org/10.32014/2024.2518-170X.471

16. Torremans, K., Gauquier, J., Boyce, A.J., Barrie, C.D., Muchez, Ph., Visser, W., Cnudde, V. Remobilisation features and structural control on ore grade distribution at the Konkola stratiform CuCo ore deposit, Zambia. Journal of African Earth Sciences, 79, 10–23 (2013). https://doi.org/10.1016/j.jafrearsci.2012.10.005

17. Cailteux, J.L.H., Kampunzu, A.B., Lerouge, C., Kaputo, A.K., Milesi, J.P. Genesis of sediment-hosted stratiform copper-cobalt deposits, Central African Copperbelt. Journal of African Earth Sciences, 42(1–5), 134–158 (2005). https://doi.org/10.1016/j.jafrearsci.2005.08.001

18. Jackson, M.P.A., Warin, O.N. Neoproterozoic allochthonous salt tectonics during the Lufilian orogeny in the Katangan Copperbelt, central Africa. Geological Society of America Bulletin, 115(3), 314–330 (2003). https://doi.org/10.1130/0016-7606(2003)115<0314:NASTDT>2.0.CO;2

19. Hitzman, M.W., et al. The Central African Copperbelt: diverse stratigraphic, structural, and temporal settings in the world’s largest sedimentary copper district. University of Tasmania, Journal contribution (2012). https://hdl.handle.net/102.100.100/572953

20. Sharapatov, A., Saduov, A., Assirbek, N. Sravnitel’nyi analiz vozmozhnostei algoritmov mashinnogo i glubokogo obucheniia v geologii [Comparative analysis of machine and deep learning capabilities in geology]. Nauchno-tekhnicheskii i proizvodstvennyi Gornyi zhurnal Kazakhstana [Scientific-Technical and Industrial Mining Journal of Kazakhstan], 11 (223), 14–21 (2023). https://doi.org/10.48498/minmag.2023.223.11.002 (in Russian).

21. Wilford, J. A weathering intensity index for the Australian continent using airborne gamma-ray spectrometry and digital terrain analysis. Geoderma, 183–184, 124–142 (2012). https://doi.org/10.1016/j.geoderma.2010.12.022

22. Carranza, E.J.M., Hale, M. Where are regional geochemical anomalies found? Geochemistry: Exploration, Environment, Analysis, 1(3), 173–184 (2001). https://doi.org/10.1144/geochem.1.3.173

23. Jain, A.K. Data clustering: 50 years beyond K-means. Pattern Recognition Letters, 31(8), 651–666 (2010). https://doi.org/10.1016/j.patrec.2009.09.011

24. Bezdek, J.C., Ehrlich, R., Full, W. FCM: The fuzzy c-means clustering algorithm. Computers & Geosciences, 10(2–3), 191–203 (1984). https://doi.org/10.1016/0098-3004(84)90020-7

25. Sharapatov, A., Zhumabayev, B.T., Saduov, A.B., Assirbek, N. Geomagnitnye dannye i ikh ispol’zovanie pri reshenii zadach geonauk [Geomagnetic data and their use in solving geoscience problems]. Nauchno-tekhnicheskii i proizvodstvennyi Gornyi zhurnal Kazakhstana [Scientific-Technical and Industrial Mining Journal of Kazakhstan], 12 (224), 30–36 (2023). https://doi.org/10.48498/minmag.2023.224.12.004 (in Russian).