Towards trajectory-unsupervised physics-informed neural solvers for molecular dynamics

📅 2026-08-07
📈 Citations: 0
Influential: 0
📄 PDF
🤖 AI Summary
This work proposes DINaMo, a novel framework that introduces the first fully unsupervised neural trajectory solver for molecular dynamics. Unlike conventional neural approaches that rely on simulated trajectories, forces, or energies for supervised training and thus remain data-dependent, DINaMo models molecular trajectories as differentiable functions of time and trains exclusively through physical principles—namely Newton’s equations of motion, conservation laws, and analytically defined interaction potentials—without any reference simulation data. The method successfully reproduces key structural and dynamical observables in a Lennard-Jones argon system, including short-time coordinate evolution, energy conservation, and the radial distribution function of the liquid phase, thereby demonstrating the feasibility of learning molecular motion solely from physical constraints.
📝 Abstract
Molecular dynamics (MD) simulations are governed by explicit equations of motion, yet most neural approaches that accelerate or emulate MD rely on simulator-generated trajectories, forces, or energies for training. In this work we ask to what extent can physically meaningful molecular trajectories be recovered from the governing laws. We introduce the Differentiable Newtonian Molecular Solver (DINaMo), a physics-informed neural framework that represents molecular trajectories as differentiable functions of time and is trained exclusively through Newtonian dynamics, conservation laws, and analytic interaction potentials on a given equilibrated initial state. Unlike prior physics-informed MD formulations, DINaMo uses no simulator-generated trajectories, forces, velocities, or energies as supervisory targets. In Lennard--Jones argon systems, the learned trajectories reproduce short-time coordinate, energy, and structural observables, including in a larger and denser liquid-like setting where the radial distribution function is recovered. Although currently limited to short temporal horizons, the results indicate that physically meaningful molecular trajectories can emerge directly from physics-only supervision, supporting the feasibility of trajectory-unsupervised neural solvers for molecular dynamics.
Problem

Research questions and friction points this paper is trying to address.

molecular dynamics
physics-informed neural networks
trajectory-unsupervised learning
Newtonian dynamics
simulation-free modeling
Innovation

Methods, ideas, or system contributions that make the work stand out.

physics-informed neural networks
trajectory-unsupervised learning
molecular dynamics
differentiable simulation
Newtonian dynamics
🔎 Similar Papers
2024-10-09International Conference on Learning RepresentationsCitations: 2
P
Petros Triantafyllos
Department of Informatics, University of Piraeus, 80 Karaoli & Dimitriou Str., Piraeus, 185 34, Attica, Greece
P
Panagiotis Krokidas
Institute of Informatics and Telecommunications, National Centre for Scientific Research “Demokritos”, Patr. Gregoriou E & 27 Neapoleos Str, Agia Paraskevi, 15341, Attica, Greece
C
Christoforos Rekatsinas
Institute of Informatics and Telecommunications, National Centre for Scientific Research “Demokritos”, Patr. Gregoriou E & 27 Neapoleos Str, Agia Paraskevi, 15341, Attica, Greece