PROPhet (short for PROPerty Prophet) couples neural networks with first-principles physics and chemistry codes to allow sophisticated prediction of material properties. In general, PROPhet is used to find mappings between a set of material or system properties and other properties. Some specific uses of PROPhet are to: Find a mapping between atomic configuration and other properties, including the total energy, creating an analytical potential, which can be used for molecular dynamics with the LAMMPS code Construct density functionals for exchange-correlation energy, kinetic energy, or just about anything else Find a mapping between a set of descriptors (an arbitrary combination of material properties) and other properties See the PROPhet project page for more details.
Kolb, B., Lentz, L.C. & Kolpak, A.M. Discovering charge density functionals and structure-property relationships with PROPhet: A general framework for coupling machine learning and first-principles methods. Sci Rep 7, 1192 (2017). https://doi.org/10.1038/s41598-017-01251-z
Density functional theory, Computational chemistry, Electronic structure Software,
Curator: laiwei.cool@gmail.com