Harnessing the Power of Emerging Technologies to Navigate Critical Resource Challenges
The global transition to renewable energy is a complex and multifaceted challenge that requires a holistic understanding of the Earth’s natural systems and the intricate balance between environmental, social, and governance (ESG) factors. As the demand for critical raw materials (CRM) surges to fuel this green revolution, it has become increasingly clear that geological abundance alone is not the primary constraint. Instead, geopolitical tensions, social license, and environmental risks pose significant threats to the security and sustainability of CRM supply chains.
In this article, we explore how advancements in geospatial data and deep learning techniques are enabling a new era of data-driven decision-making that can help navigate these complex challenges. By leveraging publicly available geospatial data as proxies for key ESG indicators, we demonstrate the power of machine learning models to accurately predict the potential for natural resource conflicts – a critical factor in securing CRM supply chains.
Balancing CRM Development and ESG Principles
The global supply chains of CRM, such as lithium, cobalt, and rare earth elements, are susceptible to a range of disruptive forces, including resource nationalism, export bans, and severe price fluctuations. These vulnerabilities are particularly concerning for countries heavily dependent on imported CRM for their manufacturing industries. In response, governments are developing policies to “onshore” or “friend-shore” the exploration, production, and processing of CRM, with the aim of diversifying and securing supply chains.
However, this shift towards CRM frontiers also has the potential to accelerate pressure on natural ecosystems, particularly in greenfield exploration settings that may have previously been deemed too remote or costly to operate. Balancing CRM development with ESG principles has therefore become a pressing priority, as corporations and governments strive to ensure a sustainable and responsible transition to renewable energy.
Mapping Spatially Situated Risks
Embedding ESG principles into the mining sector represents a valuable opportunity to strengthen global CRM supply chains by mitigating some of the major sources of risk. Previous efforts to map spatially situated risks in a CRM context have focused on the spatial overlap between ESG indicators and mineral deposits, demonstrating that a significant proportion of global CRM resources are situated in “high-risk” regions.
Building on these earlier studies, we present a comprehensive approach that combines public geospatial data as mappable proxies for key ESG indicators and a global dataset of news events to train and validate three models for predicting “conflict” events (e.g., disputes, protests, violence) that can negatively impact CRM supply chains:
- A knowledge-driven fuzzy logic model that yields an area under the curve (AUC) for the receiver operating characteristics plot of 0.72 for the entire model.
- A naïve Bayes model that yields an AUC of 0.81 for the test set.
- A deep learning model comprising stacked autoencoders and a feed-forward artificial neural network that yields an AUC of 0.91 for the test set.
The high AUC of the deep learning model demonstrates that public geospatial data can accurately predict natural resources conflicts, but we show that machine learning results are biased by proxies for population density and likely underestimate the potential for conflict in remote areas. Knowledge-driven methods are the least impacted by population bias and are used to calculate an ESG rating that is then applied to a global dataset of lithium occurrences as a case study.
The Lithium Case Study
Lithium was selected as a case study example because some of the geological sources of this CRM are geographically restricted (e.g., lithium brines are restricted to high elevations and/or low latitudes) and associated with distinct ore characteristics as well as extraction and processing routes.
Our results reveal that giant lithium brine deposits (i.e., >10 Mt Li2O) are restricted to regions with higher spatially situated risks (i.e., lower ESG ratings) relative to a subset of smaller pegmatite-hosted deposits that yield higher ESG ratings (i.e., lower risk). This points to trade-offs between the sources of lithium, resource size, and spatially situated risks.
We suggest that this type of geospatial ESG rating is broadly applicable to other CRM and that mapping spatially situated risks prior to mineral exploration has the potential to improve ESG outcomes and government policies that strengthen supply chains. The global transition to renewable energy is expected to be materially intensive, and ensuring the sustainability of CRM supply chains is crucial for achieving climate goals.
Implications for the School Community
The insights and methodologies presented in this article have important implications for the Stanley Park High School community. As the world navigates the complex challenge of transitioning to renewable energy, understanding the role of critical raw materials and the importance of sustainable sourcing becomes increasingly relevant for students and parents.
By exploring the application of geospatial data and deep learning techniques in the context of Earth science, systems, and society, this article provides a valuable resource for students interested in the intersections of technology, environmental science, and resource management. It highlights how emerging tools and techniques can be harnessed to address real-world challenges, fostering a deeper appreciation for the interdisciplinary nature of these critical issues.
For parents, this article offers insights into the evolving landscape of resource security and the importance of ESG considerations in the development of vital technologies. It underscores the need for responsible policies and decision-making that balance economic, environmental, and social factors – a topic that is increasingly relevant for the future of their children’s world.
Overall, this article aims to inspire and educate the Stanley Park High School community, encouraging them to engage with the complex and multifaceted challenges facing our planet, and to explore how the integration of cutting-edge technologies and scientific knowledge can contribute to a more sustainable and equitable future.
Conclusion
In conclusion, this article has demonstrated the power of geospatial data and deep learning techniques in navigating the complex challenges surrounding the supply of critical raw materials for the global transition to renewable energy. By mapping spatially situated risks and applying an ESG rating system, we have exposed trade-offs between the sources of lithium, resource size, and environmental, social, and governance factors.
These insights have broader implications for the management of critical raw material supply chains, with the potential to inform government policies, sustainable investment decisions, and data-driven land-use planning at global and regional scales. As the world continues to grapple with the urgency of the renewable energy transition, the integration of emerging technologies and a holistic understanding of Earth systems will be crucial for ensuring a sustainable and equitable future.
The Stanley Park High School community is well-positioned to engage with these important topics, leveraging the knowledge and resources presented in this article to foster a deeper appreciation for the interdisciplinary nature of Earth science, systems, and society. By empowering students and parents to explore these critical issues, we can inspire the next generation of problem-solvers and decision-makers who will shape the future of our planet.
