Canada Spends Logo

Explorez notre analyse du budget 2026

Grant: Discovery Grants Program - Individual

The University of British Columbia

$50,000.00

Prediction of the quantity and quality of mine waste rock drainage using a physics-informed machine learning approach

EF 2024-25

Résumé
The current global tonnage of waste rock and tailings generated after valuable minerals and metals are extracted is estimated to be over 2 x1010 tonnes per year. In the open environment, a diverse range of metals and metalloids may be released from waste rock piles into the surrounding environment, posing serious environmental risks. Extreme weather events caused by climate change could exacerbate the risks.         To effectively manage this type of pollution, it is crucial to accurately predict the quantity and quality of drainage generated from waste rock piles. Reactive transport models have been extensively used to simulate the behavior of contaminant release from waste rock piles, which are highly heterogeneous in physical and chemical properties. However, it is challenging for these models to capture the influence of heterogeneities on the drainage properties, leading to unreliable predictions.         Machine learning (ML) models have advantages over traditional reactive transport models because they are primarily algorithm-driven and tend to be faster to develop. For example, two neural networks have been applied to predict the drainage properties at the Equity Silver Mine. My team has developed a ML model to predict drainage properties in areas with spring freshet. However, the current ML models rely on limited inputs such as weather data or a few measurable chemical indicators. Critical waste rock pile properties, which significantly influence drainage quantity and quality, are overlooked. This is because waste rock piles are typically not instrumented and these properties are not monitored.         To address these challenges, the long-term objective of this research program is to apply physics-informed ML models to predict quantity and quality of mine waste rock drainage. To overcome data scarcity resulting from the lack of instrumentation and monitoring, this research proposes to use 5G-enabled wireless sensor networks to monitor crucial characteristics of mine waste rock piles, such as moisture, oxygen content, and temperature. Subsequently, the monitoring data will be transmitted via 5G networks (supported by Rogers) to a centralized data server, where ML techniques will be applied to analyze the data to predict quantity and quality of waste rock drainage. The short-term objective for the next five years is to demonstrate the feasibility of the physics-informed ML approach using laboratory-scale, fully instrumented waste rock piles. This research will ultimately establish an industry-standard framework that integrates 5G-enabled sensor networks and ML approach for monitoring, predicting, and managing mine waste rock pollution. The use of 5G aligns with the industry's initiatives to bring mining into the digital age and will help the industry develop world-leading technologies to make mining safer, smarter and more productive. This research program will train HQP in the area of mine waste management.
Programme
Discovery Grants Program - Individual
Emplacement
British Columbia, Canada
Type de bénéficiaire
Academia
Type
Grant
Source
NSERC's Awards Data

Tel que publié

Application id
RGPIN-2024-05117
Name nom
Liu, Wenying
Department département
Materials Engineering
Organization id
2
Institution établissement
The University of British Columbia
Province en
British Columbia
Province fr
Colombie-Britannique
Country en
CANADA
Country fr
CANADA
Fiscal year exercice financier
2024
Competition year année de concours
2024
Award amount
50000
Program id
RGPIN
Program name en
Discovery Grants Program - Individual
Program name fr
Programme de subventions à la découverte - individuelles
Group en
DISCOVERY RESEARCH
Group fr
RECHERCHE AXÉE SUR LA DÉCOUVERTE
Committee code
1509
Committee name en
Civil, Industrial and Systems Engineering
Committee name fr
Génie civil, industriel et des systèmes
Area of application code
902
Area of application group en
Commercial services
Area of application group fr
Services commerciaux
Area of application en
Waste, waste management and recycling
Area of application fr
Déchets, gestion des déchets et recyclage
Research subject code
1500
Research subject group en
Environmental engineering
Research subject group fr
Génie de l'environnement
Research subject en
Environmental engineering
Research subject fr
Génie de l'environnement
Field of research list names en
Not available
Field of research list names fr
Non disponible
Socioeconomic objective list names en
Not available
Socioeconomic objective list names fr
Non disponible
Application title
Prediction of the quantity and quality of mine waste rock drainage using a physics-informed machine learning approach
Keywords
ore extraction; mine waste rock; contaminant release; metal leaching kinetics; fluid flow; monitoring with sensors; data analytics; machine learning; drainage chemistry; remediation
Application summary
The current global tonnage of waste rock and tailings generated after valuable minerals and metals are extracted is estimated to be over 2 x1010 tonnes per year. In the open environment, a diverse range of metals and metalloids may be released from waste rock piles into the surrounding environment, posing serious environmental risks. Extreme weather events caused by climate change could exacerbate the risks.         To effectively manage this type of pollution, it is crucial to accurately predict the quantity and quality of drainage generated from waste rock piles. Reactive transport models have been extensively used to simulate the behavior of contaminant release from waste rock piles, which are highly heterogeneous in physical and chemical properties. However, it is challenging for these models to capture the influence of heterogeneities on the drainage properties, leading to unreliable predictions.         Machine learning (ML) models have advantages over traditional reactive transport models because they are primarily algorithm-driven and tend to be faster to develop. For example, two neural networks have been applied to predict the drainage properties at the Equity Silver Mine. My team has developed a ML model to predict drainage properties in areas with spring freshet. However, the current ML models rely on limited inputs such as weather data or a few measurable chemical indicators. Critical waste rock pile properties, which significantly influence drainage quantity and quality, are overlooked. This is because waste rock piles are typically not instrumented and these properties are not monitored.         To address these challenges, the long-term objective of this research program is to apply physics-informed ML models to predict quantity and quality of mine waste rock drainage. To overcome data scarcity resulting from the lack of instrumentation and monitoring, this research proposes to use 5G-enabled wireless sensor networks to monitor crucial characteristics of mine waste rock piles, such as moisture, oxygen content, and temperature. Subsequently, the monitoring data will be transmitted via 5G networks (supported by Rogers) to a centralized data server, where ML techniques will be applied to analyze the data to predict quantity and quality of waste rock drainage. The short-term objective for the next five years is to demonstrate the feasibility of the physics-informed ML approach using laboratory-scale, fully instrumented waste rock piles. This research will ultimately establish an industry-standard framework that integrates 5G-enabled sensor networks and ML approach for monitoring, predicting, and managing mine waste rock pollution. The use of 5G aligns with the industry's initiatives to bring mining into the digital age and will help the industry develop world-leading technologies to make mining safer, smarter and more productive. This research program will train HQP in the area of mine waste management.