Litcius/Paper detail

Making free-energy calculations routine: Combining first principles with machine learning

Ryosuke Jinnouchi, Ferenc Karsai, Georg Kresse

2020Physical review. B./Physical review. B63 citationsDOI

Abstract

The chemical potentials of atoms and molecules in condensed matter are fundamental properties that allow one to predict a wide variety of thermodynamic properties. However, predictions using first principles are challenging. Here, an efficient and accurate method using machine-learned force fields is presented. A key point is that it requires training only at the end points of the thermodynamic pathway, rendering the training simple and efficient. Applications to liquid Si, and Li and F ions hydrated by water show that the method can predict accurate chemical potentials at low computational cost.

Topics & Concepts

Computer scienceRendering (computer graphics)Key (lock)Simple (philosophy)Statistical physicsMachine learningArtificial intelligencePhysicsComputer securityPhilosophyEpistemologyMachine Learning in Materials ScienceSpectroscopy and Quantum Chemical StudiesAdvanced Chemical Physics Studies
Making free-energy calculations routine: Combining first principles with machine learning | Litcius