Introduction

Date	Time	Title	Speaker
Dec. 6th	16:00 - 16:30	Accelerating the High-Throughput Search for new Thermal Insulators with Symbolic Regression	Dr. Thomas Purcell

Abstract

Accurate artificial-intelligence models are key to accelerate the discovery of new functional materials for various applications. However, advancements in this field are often hindered by the scarcity of available data and the significant effort required to acquire new data. For such applications, reliable surrogate models that help guide materials space exploration using easily accessible materials properties are urgently needed. Here, we present a general, data-driven framework that provides quantitative predictions as well as qualitative rules for steering data creation using a combination of symbolic regression and sensitivity analysis. We illustrate the power of this new framework by screening for new thermally insulating materials. By creating a workflow to calculate the structural, harmonic, and anharmonic properties of a material we are able to create a set of physically meaningful descriptors for the thermal conductivity, κL of a material. Using these descriptors, we apply the sure-independence screening and sparsifying operator (SISSO) [1, 2] method to build an analytical model that describes κL and then extract out the most important input properties using a variance-based sensitivity analysis [3]. Using the information gained from the analysis we screen over a set of 732 materials and found the 80 ultra-insulating materials that are in the region of materials space that is likely to contain thermal insulators. Of these materials Finally we confirm four of these predictions by calculating their thermal conductivity using the ab initio Green-Kubo technique [4, 5].

[1] R. Ouyang, S. Curtarolo, E. Ahmetcik, M. Scheffler, and L. M. Ghiringhelli. Phys. Rev. Mat. 2, 083802 (2018)
[2] T. A. R. Purcell, M. Scheffler, C. Carbogno, and L. M. Ghiringhelli. J. Open Source Softw. 7, 3960 (2022)
[3] S. Kucherenko, S. Tarantola, and P. Annoni. Comput. Phys. Commun. 183, 937 (2012)
[4] F. Knoop, T. A. R. Purcell, M. Scheffler, and C. Carbogno. J. Open Source Softw. 5, 2671 (2020)
[5] C. Carbogno, R. Ramprasad, and M. Scheffler. Phys. Rev. Lett. 118, 175901 (2017)