Nature

Learning density functionals with differentiable DFT

Density functional theory (DFT) is a workhorse of quantum chemistry and materials science. Yet its predictive power remains limited by the quality of exchange-correlation (XC) functionals, which are ...
Nature

Algorithmic differentiation for plane-wave DFT: materials design, error control and learning model parameters

We present a differentiation framework for plane-wave density-functional theory (DFT) that combines the strengths of forward-mode algorithmic differentiation (AD) and density-functional perturbation ...
EurekAlert!

An AI–DFT integrated framework accelerates materials discovery and design

Researchers at China University of Petroleum (East China) present a comprehensive AI-driven strategy that enhances the efficiency and reliability of materials research across semiconductors, ...
C&EN

Machine learning helps improve accuracy and efficiency of small-molecule calculations

When experiments are impractical, density functional theory (DFT) calculations can give researchers accurate approximations of chemical properties. The mathematical equations that underpin the ...