Machine Learning Force Fields for Molecular Liquids - Ethylene Carbonate / Ethyl Methyl Carbonate Binary Solvent

Aug 5, 2026

Upload by Anda

Highly accurate ab initio molecular dynamics is the benchmark for understanding molecular mechanisms in condensed phases, yet it is too costly for properties that converge slowly over long time scales. This work presents a robust machine-learning potential for the EC:EMC binary solvent, a key liquid component of rechargeable Li-ion battery electrolytes. The study determines what ingredients are required to model this molecular mixture, focusing on scale separation between intra- and intermolecular interactions in condensed-phase systems.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages17

Reading Time43 min

AccessFree to download

Abstract

Introduction

Force-field design without explicit scale separation

Application to EC:EMC binary solvent in Li-ion electrolytes

Modeling strategy for interactions and electrostatics

Machine Learning Force Fields for Molecular Liquids: Ethylene Carbonate / Ethyl Methyl Carbonate Binary Solvent Ioan-Bogdan Magd˘au ∗1, Daniel J. Arismendi-Arrieta2 , Holly E. Smith3 , Clare P. Grey3 , Kersti Hermansson2 , and G´abor Cs´anyi 1 1 Engineering Laboratory, University of Cambridge, Trumpington Street, Cambridge, CB2 1PZ, United Kingdom 2 Department of Chemistry–˚Angstr¨om Laboratory, Uppsala University, Box 538, 75121 Uppsala, Sweden 3Yusuf Hamid Department of Chemistry, University of Cambridge, Lensfield Road, Cambridge, CB2 1EW, United Kingdom Abstract Highly accurate ab initio molecular dynamics (MD) methods are the gold standard for studying molecular mechanisms in the condensed phase, however, they are too expensive to capture many key properties that converge slowly with respect to simulation length and time scales. Machine learning (ML) approaches which reach the accuracy of ab initio simulation, and which are, at the same time, sufficiently affordable hold the key to bridging this gap. In this work we present a robust ML potential for the EC:EMC binary solvent, a key component of liquid electrolytes in rechargeable Li-ion batteries. We identify the necessary ingredients needed to successfully model this liquid mixture of organic molecules. In particular, we address the challenge posed by the separation of scale between intraand inter-molecular interactions, which is a general issue in all condensed phase molecular systems. 1 Introduction The development of ML methods for molecular modelling has opened the possibility to simulate large length scales and long time scales with ab initio-level accuracy [1–3] . ML methods have been employed successfully to model isolated molecules [4–8], where the directional intra-molecular interactions dominate, as well as inorganic solids and liquids, where the interactions are homogeneous [9–22] . The molecular condensed phase presents unique challenges owing to a large separation of scales between intra- and intermolecular interactions [23–28] . Molecular mixtures, in particular, present further complications owing to the heterogeneity of the inter-molecular environments. Many important properties of the molecular liquids such as: density, viscosity and dielectric constant; ∗ [i.b.magdau@gmail.com](i.b.magdau@gmail.com) depend specifically, and critically on inter-molecular forces. It is therefore crucial that ML models obtain good accuracies on both intra- and inter-scales. Numerous studies have demonstrated ML potentials for water and aqueous solutions [29–33], methane [26], ionic liquids [28] and, more recently, electrolyte solutions [34–36] . The standard approach to modelling these molecular systems is to create separate force fields for the intra-and inter-contributions [2, 37–39] . This approach is inspired by classical force fields and neatly solves the problem of scale separation. However the approximation breaks down in reactive systems where the molecular identity changes during the course of the simulation. In this work, we intentionally choose to fit ML models on total interactions, without an explicit separation of scales, so our potential are entirely general and could, in principle, capture reactivity [40, 41] . We aim to answer the overarching question: can we develop an accurate and robust ML force field for molecular liquids mixtures without making the scale separation explicit? In particular, can these models generate long and stable molecular dynamics trajectories and reproduce the thermodynamic properties of the reference method? As shown in other studies, even reproducing the density of a molecular system is not a trivial task [42] and merits a meticulous investigation. Here we show that a good fit on the total loss function results in good intra-, but poor inter-relative accuracies. In practice, this makes it difficult to fit the inter-contribution which underlies the thermodynamic properties of the liquid state. Specifica

FAQs

Why are ab initio molecular dynamics methods difficult to use for many molecular-liquid properties?

They are gold-standard accurate but are too expensive to reach the long simulation lengths and time scales required for properties that converge slowly.

What is the main contribution of this work on EC:EMC?

It introduces a robust machine-learning potential for the EC:EMC binary solvent and identifies the ingredients needed to model the mixture accurately.

How does this approach differ from standard force-field modeling that separates intra- and inter-molecular contributions?

Instead of using an explicit scale separation, it fits machine learning models to total interactions, aiming for a more general potential that could capture reactivity.

Aug 5, 2026

Upload by Anda