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

@inproceedings{Herzog2021AssessingTA, 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}, year={2021} }

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

## References

SHOWING 1-10 OF 78 REFERENCES

Ab initio calculations of free energy of activation at multiple electronic structure levels made affordable: An effective combination of perturbation theory and machine learning.

- Medicine, PhysicsJournal of chemical theory and computation
- 2020

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.

- Physics, MedicineJournal of chemical theory and computation
- 2019

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.

- Physics, MedicineJournal of chemical theory and computation
- 2015

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

- Physics, MedicineScience Advances
- 2017

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.

Methanol carbonylation over acid mordenite: Insights from ab initio molecular dynamics and machine learning thermodynamic perturbation theory

- Chemistry
- 2021

Abstract In this work we present a detailed ab initio study of the carbonylation reaction of methoxy groups in the zeolite mordenite, as it is the rate determining step in a series of elementary…

Chemical diversity in molecular orbital energy predictions with kernel ridge regression.

- Physics, MedicineThe Journal of chemical physics
- 2019

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.

Towards exact molecular dynamics simulations with machine-learned force fields

- Materials Science, PhysicsNature Communications
- 2018

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.

Communication: Random phase approximation renormalized many-body perturbation theory.

- Physics, MedicineThe Journal of chemical physics
- 2013

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.

Free-energy calculations

- Chemistry
- 1991

The techniques that can be used to study phase diagrams numerically depend on the character of the phase transitions. In particular, there is quite a difference among the tools used to study…

Correlation energy within exact-exchange adiabatic connection fluctuation-dissipation theory: Systematic development and simple approximations

- Physics
- 2014

We have calculated the correlation energy of the homogeneous electron gas (HEG) and the dissociation energy curves of molecules with covalent bonds from a novel implementation of the adiabatic…