Machine learning for material design

A new approach can train a machine learning model to predict the properties of a material using only data obtained through simple measurements, saving time and money compared with methods currently used.

The approach was designed by researchers at Japan’s National Institute for Materials Science, Asahi Kasei Corp., Mitsubishi Chemical Corp., Mitsui Chemicals Inc. and Sumitomo Chemical Co. Ltd. and reported in the journal “Science and Technology of Advanced Materials: Methods.”

“Machine learning is a powerful tool for predicting the composition of elements and process needed to fabricate a material with specific properties,” said Ryo Tamura, a senior researcher at NIMS who specializes in the field of materials informatics.

A tremendous amount of data usually is needed to train machine learning models for this purpose. Two kinds of data are used. Controllable descriptors are data that can be chosen without making a material, such as the chemical elements and processes used to synthesize it. But uncontrollable descriptors, like X-ray diffraction data, can be obtained only by making the material and conducting experiments on it.

The new approach can predict difficult-to-measure experimental data, such as tensile modulus, using easy-to-measure experimental data like X-ray diffraction. This further helps design new materials or repurpose already known ones. Image courtesy of “Science and Technology of Advanced Materials: Methods”

“We developed an effective experimental design method to more accurately predict material properties using descriptors that cannot be controlled,” Tamura said.