ORION: Unifying Top-Down and Bottom-Up Chemical Space Sampling for a Universal Organic Force Field

TL;DR

ORION is a universal machine-learning force field that combines top-down and bottom-up strategies to accurately and efficiently simulate complex organic systems, outperforming existing methods in speed and accuracy.

Contribution

This work introduces ORION, a novel transferable force field trained on a diverse dataset, achieving near-DFT accuracy with significantly improved computational efficiency.

Findings

ORION predicts atomic forces with higher accuracy than ReaxFF.

ORION runs 215.5 times faster than ReaxFF under identical hardware.

ORION effectively models a wide range of chemical interactions and systems.

Abstract

Empirical force fields remain the primary tool for large-scale molecular simulation, yet their limited flexibility and transferability often hinder predictive modeling in chemically complex condensed-phase systems. Here we present ORION, a universal machine-learning force field for C, H, O, N, S, and P systems developed within the Neuroevolution Potential (NEP) framework. To enhance transferability across diverse chemical environments, ORION was trained on a chemically rich dataset constructed through an integrated top-down and bottom-up strategy, enabling accurate descriptions of complex organic configurations, reactive intermediates, and weak intermolecular interactions. ORION achieves near-density-functional-theory accuracy while retaining the efficiency required for large-scale molecular dynamics simulations. On the test set, it predicts atomic forces with substantially higher accuracy than ReaxFF while running 215.5 times faster under identical hardware conditions, making simulations on the hundreds-of-nanoseconds timescale readily accessible. The model provides a balanced description of bond breaking and formation, aromatic growth, hydrogen bonding, van der Waals interactions, and {\pi}-stacking, demonstrating strong transferability across both reactive and nonreactive systems. These results establish ORION as a practical and general force field for predictive simulations in chemistry and materials science, and provide an effective route toward universal machine-learning force fields with both high accuracy and broad applicability.