Distinguished Lecturer

Dr. Jeff Boisvert is a professor in Civil and Environmental Engineering, School of Mining and Petroleum Engineering, at the University of Alberta and co-director of the Centre for Computational Geostatistics (CCG). His research focuses on spatial modeling and geostatistics in the fields of mining, energy, and wildfire. He uses spatial numerical models to improve decisions in mine design, resource/reserve estimation, wildland fire management/response, and well planning/placement/management.

The earth sciences are being transformed by advances in machine learning (ML) and artificial intelligence. From optimizing mineral exploration and hydrocarbon production to improving wildfire prediction and management, these methods offer exciting opportunities for modeling and decision-making. However, these advances bring challenges with model validation, which is critical for ensuring that predictions are robust, reasonable, and actionable.

This lecture will delve into the evolving role of ML in the mining, hydrocarbon, or wildfire industry, highlighting successes, pitfalls, and future prospects. “The Good” will explore case studies and implementations where ML has significantly improved modeling, decision making, and inference. “The Bad” will examine common pitfalls, including data biases, overfitting, and the misuse of algorithms without understanding domain constraints. Finally, “The Ugly” will confront the ethical and operational risks posed by poorly validated models, emphasizing the importance of transparency and domain experts.

We will discuss best practices for integrating ML into earth sciences while addressing the complexities of model validation. At the request of the attendees, the focus of this lecture will be on mining, hydrocarbon, or wildfire applications.

Lecture 2: Understanding, incorporating, and assessing the impact of uncertainty in our decisions: Why are we still so reluctant?
Uncertainty is an inherent aspect of decision-making in the earth sciences, particularly in mining, hydrocarbon, and wildfire domains. Whether estimating ore reserves, forecasting hydrocarbon production, or predicting wildfire behavior, uncertainties arise from data limitations, model assumptions, and complex natural processes. However, often there is still a reluctance to fully embrace uncertainty in decision-making frameworks. Why do we hesitate to quantify, incorporate, and communicate uncertainty? What are the consequences of this reluctance? What opportunities are we missing?

This lecture explores the technical, psychological, and organizational barriers to addressing uncertainty in earth sciences. We will examine real-world examples where underestimating uncertainty led to costly errors, as well as cases where effectively managing uncertainty improved outcomes. By contrasting these scenarios, we will highlight and quantify the critical role uncertainty plays in making informed decisions. Key themes include strategies for quantifying and visualizing uncertainty, integrating uncertainty into predictive models, and fostering a cultural shift toward embracing probabilistic thinking. At the request of the attendees, the focus will be on applications in mining or wildfire management.

Professor Renguang Zuo received his B.S. and Ph.D. degrees from the China University of Geosciences (CUG), Wuhan, China, in 2004 and 2009, respectively. He is currently a full professor at the State Key Laboratory of Geological Processes and Mineral Resources, CUG. In 2014, he was a senior visiting fellow at the James Cook University, Australia.

His research focuses on big data analytics and machine learning-based mineral prospectivity mapping and geochemical anomalies identification. Dr. Zuo has published over 160 peer-reviewed journal papers, 6 books, and book chapters. He has served as the Gust Editor for 8 special issues in international high-quality journals. His publications have amassed over 9,000 citations (Google scholar) across a range of esteemed international journals. In 2023, Dr. Zuo was awarded the Gold Medal, which is the highest award by the Association of Applied Geochemists (AAG). In addition, he was the inaugural recipient of the Kharaka Award by the International Association for GeoChemistry in 2015. Meanwhile, He was recognized as the Elsevier highly cited Chinese scholar and the World’s Top 2% Scientist.

Dr. Zuo is the Vice President of AAG (2025-2026), and was a council of IAMG (2020-2024). He has received fellowships from AAG, Society of Economic Geologists, and Geological Society of London. He has been heavily involved in the editorial boards of many SCI-indexed journals, including Journal of Geochemical Exploration, Geochemistry: Exploration, Environment, Analysis, Computers & Geosciences, Natural Resources Research, Ore Geology Reviews, and Journal of Earth Science.

E-mails: zrguang@cug.edu.cn; zrguang1981@126.com

Googel scholar: https://scholar.google.com/citations?hl=zh-CN&user=8zvKIyAAAAAJ

 

Lecture 1: Data-knowledge dual-driven mineral prospectivity mapping
Mineral prospectivity mapping (MPM), as a computer-based approach to delineate target areas for a specific type of mineral deposits. MPM typically comprises knowledge-driven and data-driven models. Knowledge-driven MPM relies on expert knowledge, which is based on causal relationships but is not readily adaptable to dynamic changes. Data-driven MPM is capable of identifying underlying data patterns but involves poorly interpretable decision logic. This lecture will focus on the state-of-art big data analytics and AI in MPM to devise a data-knowledge dual-driven model coupling AI with a mineral systems approach to MPM.

Lecture 2: Big data analytics and AI-driven geochemical mapping
Geochemical mapping plays a crucial role in mineral exploration and environmental monitoring by providing insights into geological events and processes such as mineralization and environmental pollution. With the advent of the big data era, how to apply big data analytics and AI to mine geochemical exploration or environmental data from a variety of geological and environmental settings to extract subtle and complex geochemical anomalies associated with mineralization or pollution has become even more challenging. This lecture will focus on the state-of-art big data analytics and AI in geochemical mapping and document successful case studies.