Neuromorphic, physics-informed spiking neural network for molecular dynamics
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 sim...
Saved in:
| Main Authors: | , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
IOP Publishing
2025-01-01
|
| Series: | Machine Learning: Science and Technology |
| Subjects: | |
| Online Access: | https://doi.org/10.1088/2632-2153/ada220 |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| _version_ | 1841558799758917632 |
|---|---|
| author | Vuong Van Pham Temoor Muther Amirmasoud Kalantari Dahaghi |
| author_facet | Vuong Van Pham Temoor Muther Amirmasoud Kalantari Dahaghi |
| author_sort | Vuong Van Pham |
| collection | DOAJ |
| description | 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. |
| format | Article |
| id | doaj-art-d5bc1c30e2f44adcb1c7846f8cb6a06b |
| institution | Kabale University |
| issn | 2632-2153 |
| language | English |
| publishDate | 2025-01-01 |
| publisher | IOP Publishing |
| record_format | Article |
| series | Machine Learning: Science and Technology |
| spelling | doaj-art-d5bc1c30e2f44adcb1c7846f8cb6a06b2025-01-06T05:26:21ZengIOP PublishingMachine Learning: Science and Technology2632-21532025-01-015404507910.1088/2632-2153/ada220Neuromorphic, physics-informed spiking neural network for molecular dynamicsVuong Van Pham0https://orcid.org/0009-0007-5367-5369Temoor Muther1https://orcid.org/0000-0001-9008-1358Amirmasoud Kalantari Dahaghi2https://orcid.org/0009-0005-6187-817XCenter for Net Carbon Zero GeoEnergy Intelligence and Sustainability (C0GEiS), University of Kansas , Lawrence, KS 66045, United States of America; Department of Chemical and Petroleum Engineering, University of Kansas , Lawrence, KS 66045, United States of AmericaCenter for Net Carbon Zero GeoEnergy Intelligence and Sustainability (C0GEiS), University of Kansas , Lawrence, KS 66045, United States of America; Department of Chemical and Petroleum Engineering, University of Kansas , Lawrence, KS 66045, United States of AmericaCenter for Net Carbon Zero GeoEnergy Intelligence and Sustainability (C0GEiS), University of Kansas , Lawrence, KS 66045, United States of America; Department of Chemical and Petroleum Engineering, University of Kansas , Lawrence, KS 66045, United States of AmericaMolecular 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.https://doi.org/10.1088/2632-2153/ada220physics-informed machine learningneuromorphic neural networkscientific machine learningmolecular energy systems modelingmolecular dynamics |
| spellingShingle | Vuong Van Pham Temoor Muther Amirmasoud Kalantari Dahaghi Neuromorphic, physics-informed spiking neural network for molecular dynamics Machine Learning: Science and Technology physics-informed machine learning neuromorphic neural network scientific machine learning molecular energy systems modeling molecular dynamics |
| title | Neuromorphic, physics-informed spiking neural network for molecular dynamics |
| title_full | Neuromorphic, physics-informed spiking neural network for molecular dynamics |
| title_fullStr | Neuromorphic, physics-informed spiking neural network for molecular dynamics |
| title_full_unstemmed | Neuromorphic, physics-informed spiking neural network for molecular dynamics |
| title_short | Neuromorphic, physics-informed spiking neural network for molecular dynamics |
| title_sort | neuromorphic physics informed spiking neural network for molecular dynamics |
| topic | physics-informed machine learning neuromorphic neural network scientific machine learning molecular energy systems modeling molecular dynamics |
| url | https://doi.org/10.1088/2632-2153/ada220 |
| work_keys_str_mv | AT vuongvanpham neuromorphicphysicsinformedspikingneuralnetworkformoleculardynamics AT temoormuther neuromorphicphysicsinformedspikingneuralnetworkformoleculardynamics AT amirmasoudkalantaridahaghi neuromorphicphysicsinformedspikingneuralnetworkformoleculardynamics |