A Proof-of-Concept Machine Learning Model for Gold-Processing Optimisation Using Blanket Mine as an Industrial Benchmark for Gwanda-Zimbabwe
Keywords:
Machine learning; artificial intelligence; gold-processing optimisation; proof-of-concept; Blanket Mine; industrial benchmark; Gwanda; gold mining; process optimisation; data-driven optimisationAbstract
Artisanal and small-scale gold mining (ASGM) plays an important role in Zimbabwe's gold sector but faces persistent challenges related to processing efficiency, resource utilisation, environmental impacts, and occupational risks. This study presents a proof-of-concept machine learning approach for exploring gold-processing optimisation using data from Blanket Mine as an industrial benchmark for the Gwanda gold-mining context. A dataset comprising nine monthly observations was used to investigate relationships between selected processing variables and gold-production performance. A machine learning model was developed to estimate processing outcomes and identify combinations of operating variables associated with improved performance. An optimisation procedure was subsequently applied to explore potential operating conditions that could enhance gold-processing outcomes. The results demonstrate the potential of data-driven methods to support process optimisation and provide a computational basis for future AI-assisted decision-making in gold processing. However, the small sample size, limited test observations, absence of direct ASGM measurements, and restricted range of process and environmental variables limit the statistical generalisability and operational interpretation of the findings. Therefore, the results should not be interpreted as a validated optimisation solution for Zimbabwean ASGM operations. Instead, the study establishes a proof-of-concept and demonstrates how an industrial dataset from Blanket Mine can serve as a benchmark for investigating AI-supported gold-processing optimisation relevant to the Gwanda mining context. Further research should incorporate larger datasets, direct ASGM measurements, additional process variables, and occupational and environmental indicators to validate and extend the proposed approach.
References
1. E. Mwandiringana and J. Ye, “Mining what is not mine: Artisanal gold mining in Gwanda, Zimbabwe,” The Extractive Industries and Society, vol. 13, Art. no. 101217, 2023.
2. A. K. Donkor et al., “A comparison of factors affecting the small-scale distribution of mercury from artisanal small-scale gold mining in a Zimbabwean stream system,” Science of the Total Environment, vol. 647, pp. 400–410, 2019.
3. N. Basu et al., “Artisanal and small-scale gold mining: A cross-sectional assessment of occupational mercury exposure and exposure risk factors in Kadoma and Shurugwi, Zimbabwe,” Environmental Research, vol. 184, Art. no. 109379, 2020.
4. J. T. McCoy and L. Auret, “Machine learning applications in minerals processing: A review,” Minerals Engineering, vol. 132, pp. 95–109, 2019.
5. A. Gomez-Flores, S. Ilyas, G. W. Heyes, and H. Kim, “A critical review of artificial intelligence in mineral concentration,” Minerals Engineering, vol. 189, Art. no. 107884, 2022.
6. A. Szmigiel, D. B. Apel, K. Skrzypkowski, L. Wojtecki, and Y. Pu, “Advancements in machine learning for optimal performance in flotation processes: A review,” Minerals, vol. 14, no. 4, Art. no. 331, 2024.
7. U. Engelmann and D. van Heerden, “Caledonia Mining Corporation Plc NI 43-101 technical report on the Blanket Gold Mine, Zimbabwe,” Caledonia Mining Corporation Plc, May 17, 2021.
8. IEEE, IEEE Editorial Style Manual for Authors, IEEE Author Center, 2025.
9. Caledonia Mining Corporation Plc, “Blanket Gold Mine production statistics,” Caledonia Mining Corporation Plc, 2022.
10. P. van Straaten, “Mercury contamination associated with small-scale gold mining in Tanzania and Zimbabwe,” Science of the Total Environment, vol. 259, nos. 1–3, pp. 105–113, 2000.
11. M. M. Veiga, P. A. Maxson, and L. D. Hylander, “Origin and consumption of mercury in small-scale gold mining,” Journal of Cleaner Production, vol. 14, nos. 3–4, pp. 436–447, 2006.
Downloads
Published
Issue
Section
License
Copyright (c) 2026 Author(s)
This work is licensed under a Creative Commons Attribution 4.0 International License.
Articles published in the Journal of Advanced Multidisciplinary Studies (JAMS) are licensed under a Creative Commons Attribution 4.0 International License (CC BY 4.0), unless otherwise stated. Authors retain copyright of their work and grant JAMS the right of first publication.
