Recently, artificial Intelligence (AI) and machine learning are unlocking the potentials with accelerated prediction of material properties for novel catalyst discovery and design. We have developed the machine learning workflow to overcome two challenges. First, we report a fast machine-learning method for predicting the DOS patterns of multi-component alloy systems based on a principal component analysis. Thus, true acceleration can be realized. This reveals that our learning method will be an alternative that can break the trade-off relationship between accuracy and speed that is well known in the field of electronic structure calculations. Second, the introduction of graph network in our machine learning makes the model highly tolerant of data of different crystal structures, surfaces, and adsorbates for the catalyst discovery. Therefore, universal utilization can be realized.

Material discovery by accelerated and universal learning for novel catalysis

2019 Spring National Meeting

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.