MBD-ML: Many-body dispersion from machine learning for molecules and materials

2026-02-25

AI Summary

This work addresses the critical challenge of efficiently incorporating many-body dispersion (vdW) interactions into machine learning force fields. We propose MBD-ML, a pre-trained message-passing neural network (MPNN) model that directly predicts atomic C₆ coefficients and polarizabilities from atomic geometries, bypassing the need for costly electronic structure calculations. The model is seamlessly integrated with the libMBD library to enable end-to-end prediction of the total energy, forces, and stress tensor contributions arising from many-body dispersion effects. As the first method capable of directly predicting the required MBD parameters from structure alone, MBD-ML significantly simplifies the deployment of high-accuracy vdW corrections across diverse force fields and electronic structure codes, offering high computational efficiency, strong transferability, and broad applicability in domains such as drug design, catalysis, and battery materials.

Technology Category

• Machine Learning: Graph-based Machine Learning
• Cognitive Modeling & Cognitive Systems: Affective Computing
• Natural Language Processing: (Large) Language Models

Application Category

• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Graph Algorithms and Modeling for the Web: Foundation models and LLMs for Web-related graphs
• User Modeling, Personalization and Recommendation: ML for personalized search and recommendations

Abstract

Van der Waals (vdW) interactions are essential for describing molecules and materials, from drug design and catalysis to battery applications. These omnipresent interactions must also be accurately included in machine-learned force fields. The many-body dispersion (MBD) method stands out as one of the most accurate and transferable approaches to capture vdW interactions, requiring only atomic $C_6$ coefficients and polarizabilities as input. We present MBD-ML, a pretrained message passing neural network that predicts these atomic properties directly from atomic structures. Through seamless integration with libMBD, our method enables the immediate calculation of MBD-inclusive total energies, forces, and stress tensors. By eliminating the need for intermediate electronic structure calculations, MBD-ML offers a practical and streamlined tool that simplifies the incorporation of state-of-the-art vdW interactions into any electronic structure code, as well as empirical and machine-learned force fields.

Problem

• van der Waals interactions
• many-body dispersion
• machine learning
• force fields
• atomic properties

Innovation

• many-body dispersion
• machine learning
• van der Waals interactions
• message passing neural network
• force fields