Framework components for data-centric dry laboratories in the minerals industry: A path to science-and-technology-led innovation

Ghorbani, Yousef; Zhang, Steven E.; Nwaila, Glen T.; Bourdeau, Julie E.

doi:10.1016/j.exis.2022.101089

Cited by 6 publications

(5 citation statements)

References 85 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The industry can benefit from access to previously unavailable information through the B2B data trade. This would allow partners to exploit the collective data volume though machine learning (ML), artificial intelligence (AI), ,, and digital laboratories with augmented and virtual reality (AR/VR), , and can inform mineral systems analysis and exploration, , process innovation, and supply chain management . Similarly, transdisciplinary stakeholder collaborations can contribute to joint problem solving. Policy Trends and Best Practice Examples .…”

Section: Framework For Systems Integrationmentioning

confidence: 99%

Mass-Balance-Consistent Geological Stock Accounting: A New Approach toward Sustainable Management of Mineral Resources

Simoni,

Drielsma,

Ericsson

et al. 2024

Environ. Sci. Technol.

View full text Add to dashboard Cite

Global resource extraction raises concerns about environmental pressures and the security of mineral supply. Strategies to address these concerns depend on robust information on natural resource endowments, and on suitable methods to monitor and model their changes over time. However, current mineral resources and reserves reporting and accounting workflows are poorly suited for addressing mineral depletion or answering questions about the longterm sustainable supply. Our integrative review finds that the lack of a robust theoretical concept and framework for mass-balance (MB)consistent geological stock accounting hinders systematic industrygovernment data integration, resource governance, and strategy development. We evaluate the existing literature on geological stock accounting, identify shortcomings of current monitoring of mine production, and outline a conceptual framework for MB-consistent system integration based on material flow analysis (MFA). Our synthesis shows that recent developments in Earth observation, geoinformation management, and sustainability reporting act as catalysts that make MB-consistent geological stock accounting increasingly feasible. We propose first steps for its implementation and anticipate that our perspective as "resource realists" will facilitate the integration of geological and anthropogenic material systems, help secure future mineral supply, and support the global sustainability transition.

show abstract

Section: Framework For Systems Integrationmentioning

confidence: 99%

Mass-Balance-Consistent Geological Stock Accounting: A New Approach toward Sustainable Management of Mineral Resources

Simoni,

Drielsma,

Ericsson

et al. 2024

Environ. Sci. Technol.

View full text Add to dashboard Cite

show abstract

“…In some cases, manual labour becomes unfeasible, for example, where the ambient temperatures are too high. The main modern development that supports deep mining is the digital and technological revolution, which provides three key ingredients: (a) sensors, (b) data and algorithms, and (c) computing power (Ghorbani et al, 2022). Together, they produce self-reinforcing, system-level positive feedback to produce ever-increasing levels of sophistication.…”

Section: Modern Technologies and Scientific Developmentsmentioning

confidence: 99%

“…For example, sensors generate data, which empowers alorithms that enable analytics, predictive modelling and automation, which drives the evolution of computers. More capable computers permit the use of increasing amounts and complexity of data and allows for the deployment of higher densities and varieties of sensors (Ghorbani et al, 2022). It is unsurprising that many of the ideas to evolve the mining industry are technologies enabled by the key ingredients, such as artificial intelligence, machine learning and data (Global Mining Guidelines Group, 2019).…”

Section: Modern Technologies and Scientific Developmentsmentioning

confidence: 99%

“…Stochastic optimisation and swarm intelligence algorithms (Beni and Wang, 1993) may be suitable. In any case, the adoption of modern approaches such as digitalisation in mining may need to occur either within a risk-compartmentalised setting within the mining industry and/or in an external setting, such as academia or dry laboratories (Ghorbani et al, 2022).…”

Section: Pre-concentrationmentioning

confidence: 99%

“…In a modern data-centric environment, data must exhibit various qualities that allow the data to be understood by predominantly people with extensive training in data science (Ghorbani et al, 2022). To transition towards such a future, studies of legacy data in terms of its structure, lineage, intelligibility, etc.…”

Section: Value Of Legacy Data In Underground Miningmentioning

confidence: 99%

See 2 more Smart Citations

Moving towards deep underground mineral resources: Drivers, challenges and potential solutions

et al. 2023

View full text Add to dashboard Cite

Machine Learning-Based Delineation of Geodomain Boundaries: A Proof-of-Concept Study Using Data from the Witwatersrand Goldfields

et al. 2023

View full text Add to dashboard Cite

Machine-aided geological interpretation provides an opportunity for rapid and data-driven decision-making. In disciplines such as geostatistics, the integration of machine learning has the potential to improve the reliability of mineral resources and ore reserve estimates. In this study, inspired by existing geostatistical approaches that use radial basis functions to delineate domain boundaries, we reformulate the problem into a machine learning task for automated domain boundary delineation to partition the orebody. We use an actual dataset from an operating mine (Driefontein gold mine, Witwatersrand Basin in South Africa) to showcase our new method. Using various machine learning algorithms, domain boundaries were created. We show that based on a combination of in-discipline requirements and heuristic reasoning, some algorithms/models may be more desirable than others, beyond merely cross-validation performance metrics. In particular, the support vector machine algorithm yielded simple (low boundary complexity) but geologically realistic and feasible domain boundaries. In addition to the empirical results, the support vector machine algorithm is also functionally the most resemblant of current approaches that makes use of radial basis functions. The delineated domains were subsequently used to demonstrate the effectiveness of domain delineation by comparing domain-based estimation versus non-domain-based estimation using an identical automated workflow. Analysis of estimation results indicate that domain-based estimation is more likely to result in better metal reconciliation as compared with non-domained based estimation. Through the adoption of the machine learning framework, we realized several benefits including: uncertainty quantification; domain boundary complexity tuning; automation; dynamic updates of models using new data; and simple integration with existing machine learning-based workflows.

show abstract

Framework components for data-centric dry laboratories in the minerals industry: A path to science-and-technology-led innovation

Cited by 6 publications

References 85 publications

Mass-Balance-Consistent Geological Stock Accounting: A New Approach toward Sustainable Management of Mineral Resources

Mass-Balance-Consistent Geological Stock Accounting: A New Approach toward Sustainable Management of Mineral Resources

Moving towards deep underground mineral resources: Drivers, challenges and potential solutions

Machine Learning-Based Delineation of Geodomain Boundaries: A Proof-of-Concept Study Using Data from the Witwatersrand Goldfields

Contact Info

Product

Resources

About