Machine learning surrogate models of many-body dispersion interactions in polymer melts

2025-03-19

AI Summary

To address the prohibitively high computational cost of many-body van der Waals dispersion (MBD) interactions in polymer melts—hindering their incorporation into large-scale molecular dynamics simulations—this work introduces an efficient, physics-informed machine learning surrogate model. Methodologically, we design a streamlined SchNet architecture that preserves essential atomic connectivity, incorporates trainable radial basis functions for geometric encoding, and employs atom-centered symmetric descriptors. The model is trained and validated on diverse polymer melt systems, including polyethylene, polypropylene, and polyvinyl chloride. Our approach achieves, for the first time in polymer melts, high-fidelity, strongly generalizable, and physically consistent MBD force predictions—accurately reproducing the characteristic long-range decay behavior of dispersion interactions. Computational efficiency is improved by three to four orders of magnitude relative to ab initio MBD methods, thereby enabling practical integration of MBD effects into large-scale polymer simulations.

Technology Category

• Machine Learning: Learning with Manifolds
• Computer Vision: Multi-modal Vision
• Cognitive Modeling & Cognitive Systems: (Computational) Cognitive Architectures

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

Accurate prediction of many-body dispersion (MBD) interactions is essential for understanding the van der Waals forces that govern the behavior of many complex molecular systems. However, the high computational cost of MBD calculations limits their direct application in large-scale simulations. In this work, we introduce a machine learning surrogate model specifically designed to predict MBD forces in polymer melts, a system that demands accurate MBD description and offers structural advantages for machine learning approaches. Our model is based on a trimmed SchNet architecture that selectively retains the most relevant atomic connections and incorporates trainable radial basis functions for geometric encoding. We validate our surrogate model on datasets from polyethylene, polypropylene, and polyvinyl chloride melts, demonstrating high predictive accuracy and robust generalization across diverse polymer systems. In addition, the model captures key physical features, such as the characteristic decay behavior of MBD interactions, providing valuable insights for optimizing cutoff strategies. Characterized by high computational efficiency, our surrogate model enables practical incorporation of MBD effects into large-scale molecular simulations.

Problem

• High computational cost of many-body dispersion (MBD) calculations.
• Need for accurate MBD prediction in polymer melts.
• Development of efficient machine learning surrogate models.

Innovation

• Machine learning surrogate model for MBD forces
• Trimmed SchNet architecture with radial basis functions
• High accuracy in diverse polymer melt simulations