Managing Expectations and Imbalanced Training Data in Reactive Force Field Development: An Application to Water Adsorption on Alumina

leen — Mon, 22 Apr 2024 10:51:05 +0000

L. Dumortier, C. Chizallet, B. Creton, T. De Bruin, T. Verstraelen

Journal of Chemical Theory and Computation (JCTC)

2024

Abstract

ReaxFF is a computationally efficient model for reactive molecular dynamics simulations that has been applied to a wide variety of chemical systems. When ReaxFF parameters are not yet available for a chemistry of interest, they must be (re)optimized, for which one defines a set of training data that the new ReaxFF parameters should reproduce. ReaxFF training sets typically contain diverse properties with different units, some of which are more abundant (by orders of magnitude) than others. To find the best parameters, one conventionally minimizes a weighted sum of squared errors over all of the data in the training set. One of the challenges in such numerical optimizations is to assign weights so that the optimized parameters represent a good compromise among all the requirements defined in the training set. This work introduces a new loss function, called Balanced Loss, and a workflow that replaces weight assignment with a more manageable procedure. The training data are divided into categories with corresponding “tolerances”, i.e., acceptable root-mean-square errors for the categories, which define the expectations for the optimized ReaxFF parameters. Through the Log-Sum-Exp form of Balanced Loss, the parameter optimization is also a validation of one’s expectations, providing meaningful feedback that can be used to reconfigure the tolerances if needed. The new methodology is demonstrated with a nontrivial parametrization of ReaxFF for water adsorption on alumina. This results in a new force field that reproduces both the rare and frequent properties of a validation set not used for training. We also demonstrate the robustness of the new force field with a molecular dynamics simulation of water desorption from a γ-Al₂O₃ slab model.

This publication is licensed under the terms of your institutional subscription. Request reuse permissions.

DOI

http://dx.doi.org/10.1021/acs.jctc.3c01009

Private attachment

dumortier-et-al-2024-managing-expectations-and-imbalanced-training-data-in-reactive-force-field-development-an.pdf

Model-Informed Training Data Curation for Reactive All-Atom Potentials

mieke — Tue, 08 Jul 2025 11:07:39 +0000

L. Dumortier

Fri, 20/06/2025

iGent tower, Technologiepark, Zwijnaarde

Supervisors

Prof. Dr. ir. Toon Verstraelen, dr. Jelle Vekeman, dr. Theodorus De Bruin and dr. Benoît Creton

Attachment (private)

phd-locdumortier (1).pdf

A Reactive Force Field for Alumina Systems

leen — Tue, 18 Oct 2022 07:42:33 +0000

L. Dumortier, B. Creton, T. De Bruin, T. Verstraelen

ISBN/ISSN:

Poster

Blankenberge (Belgium)

Wednesday, 12 October, 2022 to Friday, 14 October, 2022

Abstract (private)

poster_chemcys.pdf

Conference reference

CRF-ChemCYS 2022

Center for Molecular Modeling - T. De Bruin