NEP-MB-pol: A unified machine-learned framework for fast and accurate prediction of water's thermodynamic and transport properties

TL;DR

The paper introduces NEP-MB-pol, a machine-learned framework that accurately and efficiently predicts water's structural, thermodynamic, and transport properties across various conditions by integrating advanced potentials with quantum effects.

Contribution

It presents a novel unified machine learning framework trained on high-level reference data, capable of simultaneously predicting multiple water properties with high accuracy.

Findings

Reproduces experimental water properties across temperature ranges

Achieves high accuracy in predicting diffusion, viscosity, and thermal conductivity

Offers a fast, robust tool for water property exploration

Abstract

Water's unique hydrogen-bonding network and anomalous properties pose significant challenges for accurately modeling its structural, thermodynamic, and transport behavior across varied conditions. Although machine-learned potentials have advanced the prediction of individual properties, a unified computational framework capable of simultaneously capturing water's complex and subtle properties with high accuracy has remained elusive. Here, we address this challenge by introducing NEP-MB-pol, a highly accurate and efficient neuroevolution potential (NEP) trained on extensive many-body polarization (MB-pol) reference data approaching coupled-cluster-level accuracy, combined with path-integral molecular dynamics and quantum-correction techniques to incorporate nuclear quantum effects. This NEP-MB-pol framework reproduces experimentally measured structural, thermodynamic, and transport properties of water across a broad temperature range, achieving simultaneous, fast, and accurate prediction of self-diffusion coefficient, viscosity, and thermal conductivity. Our approach provides a unified and robust tool for exploring thermodynamic and transport properties of water under diverse conditions, with significant potential for broader applications across research fields.