Cornell University is at the forefront of the development of artificial intelligence and materials science. New projects by Fengqi You, the Roxanne E. and Michael J. Zak Professor in Energy Systems Engineering, demonstrate this promising development. You recently published a novel comprehensive study with leadership from grad student Rahul Sheshanarayana. For the development of new molecules and materials, AI has been nothing short of revolutionary, as exemplified by this piece of research.
You recently have developed a new, graduate-level course called AI for Materials. This new strategic initiative seeks to inspire and train the next generation of environmental scientists and advocates. This course prepares students to innovate better, cheaper, safer and more sustainable materials. Its primary focus is applying deep learning to energy storage, optimizing the synthesis of materials, and modeling their behavior. The course aims to equip students with the skills needed to navigate the complex intersection of artificial intelligence and materials science.
We focus on transformative applications & hurdles, focusing on real development of AI to help accelerate materials design. You stated.
For one of the chapters of this educational venture, you collaborated with doctoral student Wenhao Yuan. Collectively, you co-authored the review paper, published in the journal Advanced Materials. This paper explores one of the most exciting new classes of AI systems, generalist materials intelligence. These results underscore the potential of artificial intelligence to improve the efficiency and accuracy of materials design. It does so without losing sight of some very basic scientific tenets.
Our work shows that AI can learn to reason across chemical and structural domains, generate realistic materials, and model molecular behaviors with efficiency and precision—all while aligning closely with the fundamental principles of materials science, You explained.
Today, her and Eric and Wendy Schmidt AI in Science Postdoctoral Fellow Zhilong Wang have joined forces with you. Individually and together, you published a popular paper in Nature Computational Science. In this paper, we present a novel framework for generative inverse design of crystalline materials. This includes demonstrating how AI can serve as an independent research assistant in scientific research processes.
Our intention is to make sure that materials generated by AI actually are scientifically significant, Wang remarked. He added, “We’re encoding physical principles and operating conditions directly into the learning framework, so instead of relying on massive trial-and-error, we’re guiding the AI with domain knowledge.”
The implications of this research are significant. Our scientists and other experts are using advanced AI systems rooted in science. Their mission is to accelerate breakthroughs in materials science. “To accelerate discovery in materials science, we need AI systems that are not just powerful, but scientifically grounded,” you emphasized.
“What’s exciting is the idea that AI can start to engage with science more holistically,” he said.