Many challenges in material science are accompanied by relatively small data sets of thousands or fewer data points that pose unique challenges for statistical approaches. Collecting significantly more data is frequently not an option due to the time required or high expense per data point. I will discuss our efforts to augment such small data sets with approximate physics-based models to performholistic computational structure screening of more than 12,000 solid lithium-ion conductor material candidates for batteries.[1] We double the number of known solid materials that exhibit high Li conductivity at room T by developing a new type of large-scale computational screening approach for identifying solid state electrolytes for lithium ion batteries that is capable of screening all known lithium containing solids. To be useful for batteries, high performance solid state electrolyte materials must satisfy many requirements at once, an optimization that is difficult to perform experimentally or with computationally expensive ab-initio techniques. We first screen 12,831 lithium containing crystalline solids for those with high structural and chemical stability, low electronic conductivity, and low cost. We then develop a data-driven ionic conductivity classification model for identifying which candidate structures are likely to exhibit fast lithium conduction based on experimental measurements reported in the literature. The screening reduces the list of candidate materials from 12,831 down to 21 structures that show promise as electrolytes and are 3 times more likely to be good ion conductors than randomly chosen structures. I will discuss our approach to feature selection and careful model validation for small data.

Statistical learning for small data materials challenges: Solid lithium-ion conductors for batteries

2019 Spring National Meeting

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