Benchmarking machine-learning interatomic potentials using classical force fields

Johannes Sandberg; Geneviève Dusson; Julien Lam

Home/Archive/arXiv

arXiv · 2610.14239

Benchmarking machine-learning interatomic potentials using classical force fields

Johannes Sandberg·Geneviève Dusson·Julien Lam

View original source ↗Read source document ↗Export metadata ↓

Abstract

We propose a rational comparison between several well-known machine-learning interatomic potentials (linear atomic cluster expansion, the Behler-Parrinello high-dimensional neural network potential, and the graph neural network-based MACE potential) by testing their performance for fitting classical potentials such as the Lennard-Jones and Stillinger-Weber potential. With this we assess their advantages and limitations regarding several aspects: varying training dataset size, robustness to noise, carbon footprint, as well as the ability to reproduce the radial distribution function as an example observable. Overall the MACE models are shown to most accurately reproduce the potential energy surface, with little sign of overfitting, but at a significant computational cost, highlighting important questions regarding the choice of models in computational materials science.

Explore related subjects

cond-mat.mtrl-sci

Keep this discovery

Explore connections, maps & timelines

BibTeX RIS

Johannes Sandberg, Geneviève Dusson, Julien Lam. 2026-10-09. Benchmarking machine-learning interatomic potentials using classical force fields. https://arxiv.org/abs/2610.14239

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

Partially reactive force field for the UiO-66 metal-organic framework

UiO-66 is the most widely studied metal-organic framework, on account of its structural tunability given by its capacity of sustaining high amounts of point defects in its structure. Its synthesis mechanism is largely unknown, with only a few works mostly focused on the formation of the Zr-oxide cluster. In this work, a partially reactive force field to model UiO-66, nb-UiO-FF, is introduced. This force field incorporates node--ligand reactivity via a Morse potential and the introduction of dummy atoms to reproduce the anisotropic charge distribution of the Zr atoms in the node. nb-UiO-FF reproduces structural features of both UiO-66 and its isoreticular analog UiO-67 as well as framework stability with or without defects, activated or filled with N,N-dimethylformamide or ethanol. Defect generation and node--ligand binding energies are comparable with density functional theory values. The force field is further employed within a molecular dynamics scheme to study the early stages of solvothermal node--ligand binding. Species with structures corresponding to motifs present in UiO-66 are observed, along with other metastable species. This force field enables studying the self-assembly of UiO-66, as well as the formation of its point defects.

cond-mat.mtrl-sci↗

arXiv2026

Electronic Properties of Ladder-Type Phenylenes Studied by Thermally-Assisted-Occupation Density Functional Theory

Accurate prediction of the electronic properties of extended $π$-conjugated systems with radical character remains a major theoretical challenge. To overcome this challenge, thermally-assisted-occupation density functional theory (TAO-DFT) has been developed in recent years. In this study, we employ TAO-DFT to systematically explore the electronic properties of ladder-type phenylenes ($n$-LPs), containing $n$ linearly fused four-membered carbon rings. Our calculations reveal that all investigated $n$-LPs (with $n$ = 1 ~ 40) possess singlet ground states. With increasing $n$-LP length, we observe a transition from the nonradical character of shorter $n$-LPs to the polyradical character of longer $n$-LPs. Notably, we identify a distinct damped periodic oscillation in the radical character of $n$-LPs, featuring highly correlated hotspots at specific lengths ($n = 3k - 1$, where $k$ are positive integers). The real-space representation of active orbitals confirms this global electronic behavior is governed by the intrinsic structural periodicity and completely delocalized nature of the active orbitals along the central ladder framework. These findings provide fundamental insights into the size-dependent electronic properties of $n$-LPs, guiding their rational design for future nanomaterial applications.

cond-mat.mtrl-sci↗

arXiv2026

Knowledge-Guided Construction of Machine Learning Potentials for Reactive Behavior in Energetic Materials

Energetic materials involve multiple interactions, making reliable machine-learning potentials (MLPs) difficult to construct without extensive datasets. Here, we enhance the ability of the neural network interatomic potential (NNAP) to describe molecular systems using sphmulti, a refined spherical-harmonic basis set that combines extra radial basis with element-specific chemical weighting in each radial channel. We further integrate hyperactive learning, farthest-point sampling, and iterative sufficiency criteria with knowledge-guided key events, enabling the NNAP to retain essential information for describing the material system. For 3,3'-diamino-4,4'-azoxyfurazan, the resulting NNAP is trained on only 13,680 configurations yet captures key properties, including the isomerization barrier, pyrolysis activation energy, and shock Hugoniot behavior. NNAP-driven molecular dynamics simulations further reveal that pyrolysis proceeds through furazan-ring opening followed by chain reactions, whereas shock loading induces anisotropic hydrogen transfer driven by interlayer structural deformations. This work enables efficient and reliable MLPs for energetic materials.

cond-mat.mtrl-sci↗