AI-driven optimization under uncertainty for mineral processing operations
Abstract
The global capacity for mineral processing must expand rapidly to meet the demand for critical minerals, which are essential for building the clean energy technologies necessary to mitigate climate change. However, the efficiency of mineral processing is severely limited by uncertainty, which arises from both the variability of feedstock and the complexity of process dynamics. To address this uncertainty, the current approach to designing and operating mineral processing circuits emphasizes process stability and control, relying on limited and/or indirect empirical tests, deterministic methods, and expert intuition. Yet a significant portion of valuable minerals is lost in waste streams, translating to millions of dollars of lost revenue and greater potential for environmental damage. To optimize mineral processing circuits under uncertainty, we introduce an AI-driven approach that formulates mineral processing as a Partially Observable Markov Decision Process. We demonstrate the capabilities of this approach in handling both feedstock uncertainty and process model uncertainty to optimize the operation of a simulated, simplified flotation cell as an example. We show that by integrating the process of information gathering (i.e., uncertainty reduction) and process optimization, this approach has the potential to consistently perform better than traditional approaches at maximizing an overall objective, such as net present value. We highlight the power of this approach in scenarios where the dynamics of the system, and subsequently the relationship between the inputs (e.g., feedstock composition, flotation operation settings) and desired outputs (e.g., recovery and grade), are not well known. Our methodological demonstration of this optimization-under-uncertainty approach for a synthetic case provides a mathematical and computational framework for later real-world applications, with the potential to improve both the laboratory-scale design of experiments and industrial-scale operation of mineral processing circuits without any additional hardware.
Document Type: Original article
Cited as: Xu, W., Eskanlou, A., Arief, M., Yin, D. Z., Caers, J. K. AI-Driven Optimization under Uncertainty for Mineral Processing Operations. Sustainable Earth Resources Communications, 2025, 1(2): 100-112. https://doi.org/10.46690/serc.2025.02.07
DOI:
https://doi.org/10.46690/serc.2025.02.07Keywords:
Mineral processing; process optimization; flotation; critical mineralsReferences
Amini, S. H. Optimization of mineral processing circuit design under uncertainty. Morgantown, West Virginia University, 2017.
Amini, S. H., Noble, A. Design of cell-based flotation circuits under uncertainty: A techno-economic stochastic optimization. Minerals, 2021, 11: 459.
Arief, M., Alonso, Y., Oshiro, C., et al. Managing geological uncertainty in critical mineral supply chains: A POMDP approach with application to us lithium resources, arXiv 2025, arXiv:2502.05690. Available online: https://arxiv.org/abs/2502.05690 (accessed on December 2025).
Bai, Z., Gao, P., Chu, M., et al. Artificial intelligence of mineral processing process: A review of research progress. Journal of Environmental Chemical Engineering, 2025, 13(5): 118313.
Bascur, O. Process control and operational intelligence, in SME Mineral Processing and Extractive Metallurgy Handbook, Society for Mining, Metallurgy, and Exploration (SME), edited by R. C. Dunne and S. K. Kawatra, pp. 277–316, 2019.
Concha A, F., Bascur, O. A. The Engineering Science of Mineral Processing: A Fundamental and Practical Approach, CRC Press, 2024.
Ding, J., Chai, T., Wang, H., et al. Knowledge-based global operation of mineral processing under uncertainty. IEEE Transactions on Industrial Informatics, 2012, 8: 849–859.
Hodouin, D. Methods for automatic control, observation, and optimization in mineral processing plants. Journal of Process Control, 2011, 21: 211–225.
Hodouin, D., Jämsä-Jounela, S.-L., Carvalho, M., et al. State of the art and challenges in mineral processing control. Control Engineering Practice, 2001, 9: 995–1005.
International Energy Agency (IEA). (2021). The role of critical minerals in clean energy transitions, 2021. Available online: https://www.iea.org/reports/the-role-of-critical-minerals-in-clean-energy-transitions (accessed on December 2025).
Jiang, Y., Fan, J., Chai, T., et al. Lewis, Data-driven flotation industrial process operational optimal control based on reinforcement learning. IEEE Transactions on Industrial Informatics, 2017, 14: 1974–1989.
Jovanović, I., Miljanović, I. Contemporary advanced control techniques for flotation plants with mechanical flotation cells–A review. Minerals Engineering, 2015, 70: 228–249.
Koch, P.-H., Rosenkranz, J. Sequential decision-making in mining and processing based on geometallurgical inputs. Minerals Engineering, 2020, 149: 106262.
Kochenderfer, M. J., Wheeler, T. A., Wray, K. H. Algorithms for decision making. MIT press, 2022.
Koermer, S. C. Bayesian methods for mineral processing operations. Blacksburg, Virginia, Virginia Polytechnic Institute and State University, 2022.
Koermer, S., Noble, A. (2025). Optimization of a metallurgical process with uncertain dynamics. Available online: (accessed on December 2025).
Lee, H., Calvin, K., Dasgupta, D., et al. (2023). Synthesis report of the IPCC sixth assessment report (AR6). Available online: https://www.ipcc.ch/report/ar6/syr/downloads/report/IPCC_AR6_SYR_SPM.pdf (accessed on December 2025).
McCoy, J. T., Auret, L. Machine learning applications in minerals processing: A review. Minerals Engineering, 2019, 132: 95–109.
Shean, B., Cilliers, J. A review of froth flotation control. International Journal of Mineral Processing, 2011, 100: 57–71.
Silver, D., Veness, J. (2010) Monte-Carlo planning in large POMDPs. Available online: https://proceedings.neurips.cc/paper/2010/file/edfbe1afcf9246bb0d40eb4d8027d90f-Paper.pdf (accessed on December 2025).
Sunberg, Z., Kochenderfer, M. Online algorithms for POMDPs with continuous state, action, and observation spaces. Proceedings of the International Conference on Automated Planning and Scheduling, 2018, 28(1): 259–263.
U.S. Geological Survey. (2024). Phosphate rock. Available online: https://pubs.usgs.gov/periodicals/mcs2024/mcs2024-phosphate.pdf (accessed on January 2024).
Välikangas, H., Ohenoja, M., Brochot, S., et al. Evaluation of model uncertainty propagation in mineral process flowsheet designs. Scandinavian Simulation Society, 2025, 456–463.
World Bank. (2025). World Bank Commodities Price Data. Available online: https://thedocs.worldbank.org/en/doc/18675f1d1639c7a34d463f59263ba0a2-0050012025/related/CMO-PinkSheet-April-2025.pdf (accessed on 2 April 2025).
World Meteorological Organization (WMO). (2025). WMO confirms 2024 as warmest year on record at about 1.55 °C above pre-industrial level, 2025. Available online: https://wmo.int/news/media-centre/wmo-confirms-2024-warmest-year-record-about-155degc-above-pre-industrial-level (accessed on 10 January 2025).
Xiang, X., Foo, S. Recent advances in deep reinforcement learning applications for solving partially observable markov decision processes (POMDP) problems: Part 1-fundamentals and applications in games, robotics and natural language processing. Machine Learning and Knowledge Extraction, 2021, 3: 554–581.
Xiang, X., Foo, S., Zang, H. Recent advances in deep reinforcement learning applications for solving partially observable markov decision processes (POMDP) problems part 2-applications in transportation, industries, communications and networking and more topics. Machine Learning and Knowledge Extraction, 2021, 3: 863–878.
Downloads
Additional Files
Published
How to Cite
Issue
Section
License
Copyright (c) 2025 William Xu, Amir Eskanlou, Mansur Arief, David Zhen Yin, Jef Caers
This work is licensed under a Creative Commons Attribution-NonCommercial-NoDerivatives 4.0 International License.