When the rule to determine the target property is known a priori, and the computational cost for the predictors with the DFT accuracy is not too high to cover the whole library within the practical time frame, “high throughput screening” of first principles (DFT) database is a straightforward strategy for materials discovery. Otherwise we need to adopt learning methods using predictors that can cover the whole library. The learning techniques make a model to estimate the target property, which can be used for “virtual screening” of the library.Here,we show a few examples how such techniques have been used for materials discovery.
CITATION STYLE
Tanaka, I., & Seko, A. (2015). Toward materials discovery with first-principles datasets and learning methods. In Springer Series in Materials Science (Vol. 225, pp. 173–186). Springer Verlag. https://doi.org/10.1007/978-3-319-23871-5_9
Mendeley helps you to discover research relevant for your work.