It takes decades to develop new materials. Traditionally, scientists have had to sift through colossal amounts of data and perform extensive trial-and-error testing. Today, however, Artificial Intelligence (AI) can accelerate the process of identifying promising new materials and technologies with high-speed simulations and computer modeling.
Dario Gil, vice president of science and solutions at IBM recently told attendees of the EmTech Digital conference that scientists today can apply algorithms and simulations to extract insights from much larger data sets, white papers, and reports than any individual person could—and that contemporary technology can do it faster. According to MIT’s Tech Review, in mere seconds machine learning software can help extract salient information from numerous scientific papers, facilitating the research process and enabling the creation of knowledge graphs across data fields in weeks rather than decades.
Toyota Motor Corporation is positioning itself to make use of this advancement. The car company announced last week that it plans to invest $35 million in its research division, the Toyota Research Institute (TRI), and will collaborate with a number of academic institutions including the University of Michigan, the Massachusetts Institute of Technology, Stanford University, and British material sciences company Ilika.
TRI scientists plan to merge data sources, machine learning, computer modeling, and artificial intelligence, to streamline projects and reduce the time it takes for new material development.
“Accelerating the pace of materials discovery will help lay the groundwork for the future of clean energy and bring us even closer to achieving Toyota’s vision of reducing global average new-vehicle CO2 emissions by 90 percent by 2050,” said TRI Chief Science Officer Eric Krotkov in a press release.
The research aims to develop a variety of materials related to batteries and functional polymers designed for energy storage. One focus will be fuel cell catalysts and finding a replacement for platinum. “We don’t have a ton of platinum on this planet and it costs a lot of money,” Dr. Brian Storey, an Olin College of Engineering professor and the lead TRI researcher said.
“Simulation in general is a great tool for doing science and engineering,” explained Storey. “There are fundamental reasons that it’s very, very difficult to do it in some of these problems. You can’t make a simulator for an entire battery. Can you do better than we currently do? We think so. Simulation is important, but it can’t be the whole thing. It’s really the integration, but also new sources of experimental data but really bringing these things together is the critical part.”
Toyota’s long-term investment is a forward-thinking effort to advance the use of machine learning methods and a step toward reducing vehicle CO2 emissions.