Abhishek Kumar Singh『

¹ Materials Research Centre, Indian Institute of Science, Bangalore 560012 INDIAINDIA

EXTENDED ABSTRACT: Data driven machine learning methods in materials science are emerging as one of the promising tools for expanding the discovery domain of materials to unravel useful knowledge. In the first of this talk, the power of these methods will be illustrated by covering three major aspects, namely, development of prediction models, establishment of hidden connections and scope of new algorithmic developments. For the first aspect, we have developed accurate prediction models for various computationally expensive physical properties such as band gap, band edges and lattice thermal conductivity. The prediction model for band gap and band edges are developed on 2D family of materials -MXene, which are very promising for a wide range of electronic to energy applications, which rely on accurate estimation of band gap and band edges. These models are developed with GW level accuracy, and hence can accelerate the screening of desired materials by estimating the band gaps and band edges in a matter of minutes. For the lattice thermal conductivity prediction model, an exhaustive database of bulk materials is prepared. By employing the high-throughput approach, several ultra-low and ultra- high lattice thermal conductivity compounds are predicted. The property map is generated from the high-throughput approach and four simple features directly related to the physics of lattice thermal conductivity are proposed. The performance of the model is far superior than the physics-based Slack model, highlighting the simplicity and power of the proposed machine learning models. For the second aspect, we have connected the otherwise independent electronic and thermal transport properties. The role of bonding attributes in establishing this relationship is unraveled by machine learning. An accurate machine learning model for thermal transport properties is proposed, where electronic transport and bonding characteristics are employed as descriptors. In the third aspect, we have proposed a new algorithm to develop highly transferable prediction models. The approach is named as guided patchwork kriging, which is applied for prediction of lattice thermal conductivity. In the second part of my talk, I will discuss the application of ML applied to establish the structure-property relations in alloys and catalysis.

Keywords: Machine Learning; Physics Learned Descriptors; Functional Materials

REFERENCES

1 .Chemistry of Materials 30, 4031, 2019

2.   Chemistry of Materials, 31, 5145,2019

3.   Journal of Materials Chemistry A 8, 8716,2020

4.    Journal of Physics: Materials 3, 024006,2020

5.    npj Comput. Mater., 7, 197 (2021)

6.    Acta Mater., 196,295-303, (2020).