Assessing the Accuracy of Machine Learning Thermodynamic Perturbation Theory: Density Functional Theory and Beyond.

  title={Assessing the Accuracy of Machine Learning Thermodynamic Perturbation Theory: Density Functional Theory and Beyond.},
  author={Basile Herzog and Maur{\'i}cio Chagas da Silva and Bastien Casier and Michael Badawi and Fabien Pascale and Tom{\'a}{\vs} Bu{\vc}ko and S{\'e}bastien Leb{\`e}gue and Dario Rocca},
  journal={Journal of chemical theory and computation},
Machine learning thermodynamic perturbation theory (MLPT) is a promising approach to compute finite temperature properties when the goal is to compare several different levels of ab initio theory and/or to apply highly expensive computational methods. Indeed, starting from a production molecular dynamics trajectory, this method can estimate properties at one or more target levels of theory from only a small number of additional fixed-geometry calculations, which are used to train a machine… 

Figures and Tables from this paper


Ab initio calculations of free energy of activation at multiple electronic structure levels made affordable: An effective combination of perturbation theory and machine learning.
This work paves the route to quick free energy calculations using different levels of theory or approximations that would be too computationally expensive to be directly employed in molecular dynamics or Monte Carlo simulations.
Computing RPA adsorption enthalpies by machine learning thermodynamic perturbation theory.
This work proposes a method that couples machine learning techniques with thermodynamic perturbation theory to estimate finite-temperature properties using correlated approximations and applies this approach to compute the enthalpies of adsorption in zeolites and shows that reliable estimates can be obtained by training a machine learning model with as few as 10 RPA energies.
Big Data Meets Quantum Chemistry Approximations: The Δ-Machine Learning Approach.
The transferability of the approach is demonstrated, using semiempirical quantum chemistry and machine learning models trained on 1 and 10% of 134k organic molecules, to reproduce enthalpies of all remaining molecules at density functional theory level of accuracy.
Machine learning of accurate energy-conserving molecular force fields
The GDML approach enables quantitative molecular dynamics simulations for molecules at a fraction of cost of explicit AIMD calculations, thereby allowing the construction of efficient force fields with the accuracy and transferability of high-level ab initio methods.
Towards exact molecular dynamics simulations with machine-learned force fields
A flexible machine-learning force-field with high-level accuracy for molecular dynamics simulations is developed, for flexible molecules with up to a few dozen atoms and insights into the dynamical behavior of these molecules are provided.
Chemical diversity in molecular orbital energy predictions with kernel ridge regression.
This work investigates the performance of machine learning with kernel ridge regression (KRR) for the prediction of molecular orbital energies on three large datasets: the standard QM9 small organic molecules set, amino acid and dipeptide conformers, and organic crystal-forming molecules extracted from the Cambridge Structural Database.
Communication: Random phase approximation renormalized many-body perturbation theory.
This RPA-renormalized perturbation theory is an accurate, non-empirical, and robust tool to assess and improve semi-local density functional theory for a wide range of systems previously inaccessible to first-principles electronic structure calculations.
Accurate first-principles structures and energies of diversely bonded systems from an efficient density functional.
It is shown that the recently developed non-empirical strongly constrained and appropriately normed SCAN meta-generalized gradient approximation (meta-GGA) within the density functional theory framework predicts accurate geometries and energies of diversely bonded molecules and materials.