From DFT to machine learning: recent approaches to materials science–a review

GR Schleder, ACM Padilha, CM Acosta… - Journal of Physics …, 2019 - iopscience.iop.org
Recent advances in experimental and computational methods are increasing the quantity
and complexity of generated data. This massive amount of raw data needs to be stored and …

Atomistic line graph neural network for improved materials property predictions

K Choudhary, B DeCost - npj Computational Materials, 2021 - nature.com
Graph neural networks (GNN) have been shown to provide substantial performance
improvements for atomistic material representation and modeling compared with descriptor …

Rational Design of Earth‐Abundant Catalysts toward Sustainability

J Guo, Y Haghshenas, Y Jiao, P Kumar… - Advanced …, 2024 - Wiley Online Library
Catalysis is crucial for clean energy, green chemistry, and environmental remediation, but
traditional methods rely on expensive and scarce precious metals. This review addresses …

The joint automated repository for various integrated simulations (JARVIS) for data-driven materials design

K Choudhary, KF Garrity, ACE Reid, B DeCost… - npj computational …, 2020 - nature.com
Abstract The Joint Automated Repository for Various Integrated Simulations (JARVIS) is an
integrated infrastructure to accelerate materials discovery and design using density …

Enhancing materials property prediction by leveraging computational and experimental data using deep transfer learning

D Jha, K Choudhary, F Tavazza, W Liao… - Nature …, 2019 - nature.com
The current predictive modeling techniques applied to Density Functional Theory (DFT)
computations have helped accelerate the process of materials discovery by providing …

Group-IV (A) Janus dichalcogenide monolayers and their interfaces straddle gigantic shear and in-plane piezoelectricity

P Nandi, A Rawat, R Ahammed, N Jena, A De Sarkar - Nanoscale, 2021 - pubs.rsc.org
Inversion symmetry in the 1T-phase of pristine dichalcogenide monolayer MX2 (M= Ge, Sn;
X= S, Se) is broken in their Janus structures, MXY (M= Ge, Sn; X≠ Y= S, Se), which induces …

Materials science in the artificial intelligence age: high-throughput library generation, machine learning, and a pathway from correlations to the underpinning physics

RK Vasudevan, K Choudhary, A Mehta… - MRS …, 2019 - cambridge.org
The use of statistical/machine learning (ML) approaches to materials science is
experiencing explosive growth. Here, we review recent work focusing on the generation and …

MechElastic: A Python library for analysis of mechanical and elastic properties of bulk and 2D materials

S Singh, L Lang, V Dovale-Farelo, U Herath… - Computer Physics …, 2021 - Elsevier
Abstract The MechElastic Python package evaluates the mechanical and elastic properties
of bulk and 2D materials using the elastic coefficient matrix (C ij) obtained from any ab-initio …

Designing high-TC superconductors with BCS-inspired screening, density functional theory, and deep-learning

K Choudhary, K Garrity - npj Computational Materials, 2022 - nature.com
We develop a multi-step workflow for the discovery of conventional superconductors, starting
with a Bardeen–Cooper–Schrieffer inspired pre-screening of 1736 materials with high …

Nanoscale interfaces of Janus monolayers of transition metal dichalcogenides for 2D photovoltaic and piezoelectric applications

A Rawat, MK Mohanta, N Jena, Dimple… - The Journal of …, 2020 - ACS Publications
Using first-principles calculations, we demonstrate a combination of two emergent fields,
type II van der Waals heterostructures and Janus structures, for the purpose of optimizing the …