Skip to content
Preprint

Isotope Effects at Classical Cost through Mass-Differentiable Machine Learning

Oct 2026 · 0 citations · 55 references
Physics

TL;DR

Iso-EPIGS makes accurate isotope-effect simulations feasible for complex systems and lays the groundwork for foundation models of isotope effects across chemical space.

Abstract

Isotope effects govern fractionation and modulate reactivity, with applications from hydrogen energy to environmental science and catalysis, yet predicting them requires resolving small isotope-dependent free-energy differences that remain very challenging for conventional path-integral simulations in complex systems. Here we introduce iso-EPIGS, a path-integral coarse-graining framework built on a mass-differentiable neural network that reconstructs the mass- and temperature-dependent path integral centroid free-energy surface. Classical molecular dynamics on the learned surface yields rigorous isotope-resolved thermodynamics without explicit path-integral sampling. Benchmarks spanning gas, liquid, and crystalline phases, including liquid water and oxalic acid crystal, reproduce reference path-integral isotope free-energy differences, enthalpies, and lattice parameters at near classical computational cost. Crucially, iso-EPIGS trained solely on all-H and all-D isotopologues retains high accuracy for unseen partially deuterated isotopologues, demonstrating robust transferability across nuclear masses. Iso-EPIGS makes accurate isotope-effect simulations feasible for complex systems and lays the groundwork for foundation models of isotope effects across chemical space.

View source

Similar papers

Preprint Nov 2026

Subtle Energy Corrections Reshape Condensed-Phase Property Predictions from a Machine-Learning Interatomic Potential

Accurate reproduction of electronic-structure labels by machine-learning interatomic potentials does not necessarily ensure reliable condensed-phase properties. We investigate the effects of basis-set superposition error (BSSE) and an explicit Axilrod-Teller-Muto (ATM) three-body dispersion contribution on molecular-li...

Hai-Hui Wang, Xin-Yan Wang, Jia-Shu Liang et al. · 0 citations
Oct 2026

Local Correlation-Based Machine Learning Enables Coupled-Cluster-Level Energetics for Thousand-Atom Molecular Systems.

Data-intensive molecular workflows increasingly require consistent energies for many molecules and configurations. High-accuracy data are much scarcer because the small energy differences governing conformational preferences and molecular recognition can require an accurate treatment of electron correlation. Coupled-cl...

Hua Feng, Shu-Hua Li, Jing Ma et al. · 0 citations
Preprint Oct 2026

A thermodynamic correction layer for machine learning interatomic potentials

Machine learning interatomic potentials enable atomistic simulations with near \textit{ab initio} accuracy over large length and time scales. Foundation models extend this capability across the periodic table but inherit the thermodynamic description of the electronic structure methods used to generate their training d...

Sarath Menon, Braulio Sanchez Ortega, R. Drautz · 0 citations

Machine Learning of First Principles Observables

This new efficiency finally allows to heads-on tackle the highly dynamic evolution of working interfaces in ECS systems, where the targeted functionality like catalytic activity or ion mobility both inherently drives and results from ongoing substantial structural, compositional and morphological changes.

E. Gelžinytė, Gábor Csányi, Janine George et al. · 0 citations
Preprint Oct 2026

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 th...

Guan-Chen Dong, Huan-Rong Liu, Lin Wang et al. · 1 citation
Review Oct 2026

Specialized machine learning force fields for materials dynamics

Machine learning interatomic potentials (MLIPs) are transforming atomistic simulations by accessing unprecedented length and time scales. While pretrained equivariant graph neural networks achieve robust zero-shot performance for near-equilibrium properties across broad chemical spaces, their translation to complex mat...

Yue Wu, Hao-Yu Wan, Yuan Tian et al. · 0 citations

We use cookies to run the site and, with your consent, for analytics and to show ads. See our Cookie Policy.