Machine learning-assisted cross-domain prediction of ionic conductivity in sodium and lithium-based superionic conductors using facile descriptors

Abstract

Solid state lithium-and sodium-ion batteries utilize solid ionically conducting compounds as electrolytes. However, the ionic conductivity of such materials tends to be lower than their liquid counterparts, necessitating research efforts into finding suitable alternatives. The process of electrolyte screening is often based on a mixture of domain expertise and trial-and-error, both of which are time and resource-intensive. In this work, we present a novel machine-learning based approach to predict the ionic conductivity of sodium and lithium-based SICON compounds. Using primarily theoretical elemental feature descriptors derivable from tabulated information on the unit cell and the atomic properties of the components of a target compound on a limited dataset of 70 NASICON-examples, we have designed a logistic regression-based model capable of distinguishing between poor and good superionic conductors with a validation accuracy of over 84%. Moreover, we demonstrate how such a system is capable of cross-domain classification on lithium-based examples with the same accuracy, despite being introduced to zero lithium-based compounds during training. Through a systematic permutation-based evaluation process, we reduced the number of considered features from 47 to 7, reduction of over 83%, while simultaneously improving model performance. The contributions of different electronic and structural features to overall ionic conductivity is also discussed, and contrasted with accepted theories in literature. Our results demonstrate the utility of such a facile tool in providing opportunities for initial screening of potential candidates as solid-state electrolytes through the use of existing data examples and simple tabulated or calculated features, reducing the time-to-market of such materials by helping to focus efforts on promising candidates. Given enough data utilizing suitable descriptors, high accurate cross-domain classifiers could be created for experimentalists, improving laboratory and computational efficiency.

High‐Throughput Data‐Driven Prediction of Stable High‐Performance Na‐Ion Sulfide Solid Electrolytes

“…It is noted that the electrostatic, the free space, the geometrical, and the lattice-dynamics descriptors were suggested in the literature for σ Na,T (σ Li,T ) and/or E a (see Table S4, Supporting Information). [36][37][38][39][40][41][42][43][44][51][52][53][54][55][56][57] For the statistical validation of the "important" descriptors, we leveraged on our D Na,300K -values accumulated from the multi-stage DFT-MD sampling workflow. Our descriptors are readily accessible from any given cell structures.…”

Machine learning-assisted materials development and device management in batteries and supercapacitors: performance comparison and challenges

“…58 Some researchers have even bypassed performing DFT calculations by using easily accessible material properties from previous experiments or materials databases to make predictions for other properties, reducing the computational cost of the materials screening process by several orders of magnitude. 59,60 A hierarchy demonstrating materials design through a combination of ML, first-principles methods, and experimentation is illustrated in Fig. 5.…”

Model-based evaluation and data requirements for parallel kinetic experimentation and data-driven reaction identification and optimization

“…Data-driven guidance is already applied in multiple cases to help chemists, chemical engineers or automated machines make decisions. [2][3][4][5][6][7] Furthermore, high-throughput experimentation and automation are rapidly gaining popularity in chemistry, focusing the entire field on the adoption of novel data-driven methodologies and workflows. [8][9][10] To design a data-driven workflow, it is important to know what data quantity and quality is required.…”