At the Resolution Copper mine near Superior, Arizona, engineers face the challenge of predicting underground water flow and temperature to maintain safe working conditions. The mine, which is being developed by Rio Tinto and could become the largest underground copper mine in North America, is critical for meeting growing U.S. demand for copper used in electric vehicles and renewable energy.
Three graduate students from Arizona State University’s School of Computing and Augmented Intelligence are addressing these challenges by creating a digital twin—a virtual replica that combines physics, data, and visualization to forecast how water, heat, and mining operations interact over time.
Sandeep Gupta, professor of computer science and engineering at ASU’s Ira A. Fulton Schools of Engineering, leads the project through the Intelligent Mobile & Pervasive Applications & Communication Technologies Lab (IMPACT Lab). He explains that a digital twin is more than a 3D model or dashboard; it is “a dynamic computational representation of a physical system that updates as conditions change.” By integrating real-world data with simulations and machine learning, the digital twin allows operators to test scenarios and anticipate risks before they occur.
The focus at Resolution Copper is on hydrothermal behavior—specifically how groundwater enters the mine, how pumping changes those flows, and how heat moves through rock and water. Because the mine has only two to three years of historical data available, traditional artificial intelligence models are limited in their ability to generalize. “Two or three years of data is not much for machine learning,” says Ayan Banerjee, research associate professor at Fulton Schools. “It limits the model’s ability to generalize, which is why we can’t rely on data alone and have to bring in physics and domain knowledge.”
Graduate student Saurabh Dingwani worked on making complex subsurface information accessible by developing interactive web-based 3D models that allow users to visualize how pumping systems affect water movement as conditions change. “The web-based models were intended to make it easier to visualize operations,” Dingwani says. “They enable operators to see and simulate what happens if conditions change in the mine.”
Kuntal Thakur focused on forecasting changes in water flow and temperature using statistical models built from limited data. He notes: “Statistical models only work when you have a lot of data.” His work highlighted the need for hybrid approaches that incorporate both physical understanding and available sensor information.
Farhat Shaikh contributed by developing physics-informed digital twins—models that embed known laws such as heat transfer directly into machine learning systems. This approach helps estimate important parameters even when little data exists. Shaikh explains: “It’s our duty to understand the real problem; not just apply a model but understand what’s actually happening in the system.”
Together, these projects form an integrated framework helping mine operators anticipate peak inflows and heat loads while optimizing safety strategies with existing sensors. The project receives partial funding from Rio Tinto.
Gupta emphasizes both industry impact and educational value: “This project shows what’s possible when we combine physics, data and visualization,” he says. “Digital twins let us move beyond reacting to problems and start anticipating them, helping operators make safer, smarter decisions while preparing students to work on systems that truly matter.”
Arizona State University has been recognized for its innovative approach in higher education; it was named number one in innovation for eight consecutive years by U.S. News & World Report according to this report. The university continues contributing advanced research across various fields including engineering solutions like those applied at Resolution Copper.
Additionally, ASU partners with tech startups such as Argos Vision—which develops smart traffic cameras—in efforts unrelated to mining but indicative of broader collaborations between academia and industry as detailed here.
