Neuromorphic, physics-informed spiking neural network for molecular dynamics

Abstract

Molecular dynamics (MD) simulations are used across many fields from chemical science to engineering. In recent years, Scientific Machine Learning (Sci-ML) in MD attracted significant attention and has become a new direction of scientific research. However, effectively integrating Sci-ML with MD simulations remains challenging. Compliance with the physical principles, comparable performance to a numerical method, and integration of start-of-the-art ML architectures are top-concerned examples of those gaps. This work addresses these challenges by introducing, for the first time, the neuromorphic physics-informed spiking neural network (NP-SNN) architecture to solve Newton’s equations of motion for MD systems. Unlike conventional Sci-ML methods that heavily rely on prior training data, NP-SNN performs without needing pre-existing data by embedding MD fundamentals directly into its learning process. It also leverages the enhanced representation of real biological neural systems through spiking neural network integration with molecular dynamic physical principles, offering greater efficiency compared to conventional AI algorithms. NP-SNN integrates three core components: (1) embedding MD principles directly into the training, (2) employing best practices for training physics-informed ML systems, and (3) utilizing a highly advanced and efficient SNN architecture. By integrating these core components, this proposed architecture proves its efficacy through testing across various molecular dynamics systems. In contrast to traditional MD numerical methods, NP-SNN is trained and deployed within a continuous time framework, effectively mitigating common issues related to time step stability. The results indicate that NP-SNN provides a robust Sci-ML framework that can make accurate predictions across diverse scientific molecular applications. This architecture accelerates and enhances molecular simulations, facilitating deeper insights into interactions and system dynamics at the molecular level. The proposed NP-SNN paves the way for foundational advancements across various domains of chemical and material sciences especially in energy, environment, and sustainability fields.

Keywords

• physics-informed machine learning
• neuromorphic neural network
• scientific machine learning
• molecular energy systems modeling
• molecular dynamics