Tanner Kirk, a materials design engineer at QuesTek, was interviewed for an article in AI Business titled, “Stronger, Better: AI and the Discovery of New Materials.” Tanner shared insights about how artificial intelligence can be combined with ICME to unlock new innovations in materials engineering. 

 A section of the article on AI for new materials draws on Tanner’s interview: 

Designing new alloys is a complex task. The creators must decide on various factors, such as which elements to use, their amounts and the right combination of temperature and time for processing to get the best structure and features, Tanner Kirk, a materials design engineer at QuesTek, a materials consulting firm, said in an interview. 

Researchers must ensure the alloys meet all essential properties, including strength, flexibility, weight, resistance to corrosion and wear, lifespan and cost. AI can search this vast space more efficiently than humans to find the best possible alloys.

Many scientists are now combining computer models that simulate material behavior, known as Integrated Computational Materials Engineering, or ICME, with AI optimization methods to explore vast ranges of materials for the best designs, Kirk said.

These AI-enhanced techniques allow designers to consider more variables simultaneously, often leading to better designs. Some AI methods, like Bayesian Optimization, can even recommend the next experiment to conduct, usually one that might reduce uncertainty in the model or increase the chances of finding a superior design.

 Another increasingly popular way AI is used in materials design is through creating surrogate models. These models mimic the accuracy of detailed, first-principle models but need much less computing power. For instance, calculating the behavior of certain materials might typically take hours or days, but with these AI models, it can be done in just a few seconds. This speed-up is valuable in the design process, as it lets designers quickly evaluate many more potential designs. 

 Tanner’s expertise was once again used to provide an explanation for symbolic regression. The article then closes with a direct quote from Tanner. 

 One way to make AI models more understandable is through symbolic regression, Kirk said. 

This technique produces standard analytical equations with terms that have real-world physical relevance. The equations are similar to the phenomenological ones that scientists and engineers have used for a long time. Because these equations are more familiar, they will likely be more widely accepted and used in the field.

 “With the advent of large language models or LLMs that can write executable code, it is foreseeable that future AI models of materials can produce interpretable logic for models of even the most complex behavior,” Kirk added. 

 AI models of material behavior are being used more commonly, but they traditionally lack physics-based features that make them difficult to apply to problems outside of their training data.

 The lack of physical understanding in these models also leads to a lack of trust in AI models and the potential for erratic behavior. The incorporation of physical understanding into AI materials models is a hot topic of research that will lead to more adoption of AI models by materials researchers and engineers.