Machine learning approaches to identify and design low thermal conductivity oxides for thermoelectric applications

Abstract

Abstract The search space for new thermoelectric oxides has been limited to the alloys of a few known systems, such as ZnO, SrTiO3, and CaMnO3. Notwithstanding the high power factor, their high thermal conductivity is a roadblock in achieving higher efficiency. In this paper, we apply machine learning (ML) models for discovering novel transition metal oxides with low lattice thermal conductivity ( $ {k}_L $ ). A two-step process is proposed to address the problem of small datasets frequently encountered in material informatics. First, a gradient-boosted tree classifier is learnt to categorize unknown compounds into three categories of $ {k}_L $ : low, medium, and high. In the second step, we fit regression models on the targeted class (i.e., low $ {k}_L $ ) to estimate $ {k}_L $ with an $ {R}^2>0.9 $ . Gradient boosted tree model was also used to identify key material properties influencing classification of $ {k}_L $ , namely lattice energy per atom, atom density, band gap, mass density, and ratio of oxygen by transition metal atoms. Only fundamental materials properties describing the crystal symmetry, compound chemistry, and interatomic bonding were used in the classification process, which can be readily used in the initial phases of materials design. The proposed two-step process addresses the problem of small datasets and improves the predictive accuracy. The ML approach adopted in the present work is generic in nature and can be combined with high-throughput computing for the rapid discovery of new materials for specific applications. Impact Statement Discovery of new materials is a complex and challenging task. Sequential nature of experimental route of investigating new materials makes it tedious and resource expensive. Application of data centric methods have shown a lot of promise in the recent past in the rapid discovery of new materials. Machine learning (ML) algorithms do not only predict the properties of interest, but also provide insight into the complex correlations between properties of materials. But the availability of large materials database is a challenge, which are usually required for these methods to attain high levels of predictive accuracy. In this work, a two-step ML process has been proposed to overcome the aforementioned challenge. The proposed method has been demonstrated using a dataset of transition metal oxides to predict their lattice thermal conductivity. Low thermal conductivity transition metal oxides are specially attractive for high temperature thermoelectric application because they exhibit excellent high temperature stability and have tunable electrical properties. The proposed method was able to provide most influencing fundamental materials properties, which can be readily used as design parameters in the early stages of materials selection. The method can be combined with high throughput computations to discover novel materials for specific applications.