A machine-learned kinetic energy model for light weight metals and compounds of group III-V elements
- 21 October 2024
- journal article
- research article
- Published by IOP Publishing in Electronic Structure
- Vol. 6 (4) , 045002
Abstract
We present a machine-learned (ML) model of kinetic energy for orbital-free density functional theory (OF-DFT) suitable for bulk light weight metals and compounds made of group III–V elements. The functional is machine-learned with Gaussian process regression (GPR) from data computed with Kohn-Sham DFT with plane wave bases and local pseudopotentials. The dataset includes multiple phases of unary, binary, and ternary compounds containing Li, Al, Mg, Si, As, Ga, Sb, Na, Sn, P, and In. A total of 433 materials were used for training, and 18 strained structures were used for each material. Averaged (over the unit cell) kinetic energy density is fitted as a function of averaged terms of the 4th order gradient expansion and the product of the density and effective potential. The kinetic energy predicted by the model allows reproducing energy-volume curves around equilibrium geometry with good accuracy. We show that the GPR model beats linear and polynomial regressions. We also find that unary compounds sample a wider region of the descriptor space than binary and ternary compounds, and it is therefore important to include them in the training set; a GPR model trained on a small number of unary compounds is able to extrapolate relatively well to binary and ternary compounds but not vice versa.Keywords
All Related Versions
Funding Information
- National Science and Technology Council (110-2112-M-110-025-MY3)
- JST-Mirai Program (JPMJMI22H1)
This publication has 75 references indexed in Scilit:
- Beyond energetic and scalar measures: Next generation quantum theory of atoms in moleculesWIREs Computational Molecular Science, 2022
- CONUNDrum: A program for orbital-free density functional theory calculationsComputer Physics Communications, 2020
- DFTpy: An efficient and object‐oriented platform for orbital‐free DFT simulationsWIREs Computational Molecular Science, 2020
- Semi-local machine-learned kinetic energy density functional demonstrating smooth potential energy curvesChemical Physics Letters, 2019
- libKEDF: An accelerated library of kinetic energy density functionalsJournal of Computational Chemistry, 2017
- Recent developments in the ABINIT software packageComputer Physics Communications, 2016
- Understanding kernel ridge regression: Common behaviors from simple functions to density functionalsInternational Journal of Quantum Chemistry, 2015
- Highly accurate local pseudopotentials of Li, Na, and Mg for orbital free density functional theoryChemical Physics Letters, 2015
- Orbital-free density functional theory: Linear scaling methods for kinetic potentials, and applications to solid Al and SiChemical Physics Letters, 2009
- Eine statistische Methode zur Bestimmung einiger Eigenschaften des Atoms und ihre Anwendung auf die Theorie des periodischen Systems der ElementeThe European Physical Journal A, 1928