Researchers from the University of Tokyo's Institute of Industrial Science have developed a machine-learning model for predicting the bonding properties of materials. Image: Institute of Industrial Science, the University of Tokyo.
Researchers from the University of Tokyo's Institute of Industrial Science have developed a machine-learning model for predicting the bonding properties of materials. Image: Institute of Industrial Science, the University of Tokyo.

Designing materials with the necessary properties to fulfil specific functions is a challenge faced by researchers working in areas from catalysis to solar cells. To speed up development of novel materials, modeling approaches can be used to predict information to help guide the design.

Researchers from the University of Tokyo's Institute of Industrial Science in Japan have now developed a machine-learning model to determine the characteristics of bonded and adsorbed materials based on features of their individual components. The researchers report their findings in a paper in Applied Physics Express.

Factors such as the length and strength of bonds in materials play crucial roles in determining the structures and properties of those materials at the macroscopic scale. The ability to easily predict these characteristics is therefore valuable when designing new materials.

The density of states (DOS) is a feature that can be calculated for individual atoms, molecules and materials. Put simply, it describes the options available to the electrons when arranging themselves in a material. A modeling approach that can take this information for selected components and produce useful data for the desired material – with no need to make and analyze the material – would be an attractive tool.

The researchers used a machine-learning approach – where the model refines its response without human intervention – to predict four different properties of materials from DOS information about their individual components. Although the DOS has been used as a descriptor to determine single features before, this is the first time multiple different properties have been predicted.

"We were able to quantitatively predict the binding energy, bond length, number of covalent electrons and the Fermi energy after bonding for three different general types of system," explains study first author Eiki Suzuki. "And our predictions were very accurate across all of the properties."

Because the calculation of DOS for an isolated state is less complex than for bonded systems, the analysis is relatively efficient. In addition, the specific machine-learning approach they used, known as a neural network model, performed well even when only 20% of the dataset was used for training.

"A significant advantage of our model is that it is general and can be applied to a wide variety of systems," explains corresponding author Teruyasu Mizoguchi. "We believe that our findings could make a significant contribution to numerous development processes, for example in catalysis, and could be particularly useful in newer research areas such as nano clusters and nanowires."

This story is adapted from material from the University of Tokyo, with editorial changes made by Materials Today. The views expressed in this article do not necessarily represent those of Elsevier. Link to original source.