Machine learning evaluation of structural descriptors for supercooled water

Fuente: arXiv
Salvato in:
Dettagli Bibliografici
Autori principali: Yoshikawa, Kohei, Shikata, Kokoro, Kim, Kang, Matubayasi, Nobuyuki
Natura: Preprint
Pubblicazione: 2026
Soggetti:
Accesso online:
Tags: Aggiungi Tag
Nessun Tag, puoi essere il primo ad aggiungerne!!
_version_ 1866915972106944512
author Yoshikawa, Kohei
Shikata, Kokoro
Kim, Kang
Matubayasi, Nobuyuki
author_facet Yoshikawa, Kohei
Shikata, Kokoro
Kim, Kang
Matubayasi, Nobuyuki
contents The anomalous behavior of liquid water is widely associated with a liquid-liquid phase transition between high- and low-density states in the supercooled regime. At the microscopic level, tetrahedral hydrogen-bond networks govern these properties, motivating structural descriptors that characterize local molecular environments. These structural descriptors quantify features such as tetrahedral order, local density, and the separation between the first and second coordination shells; however, they have largely been proposed independently, with limited systematic comparison. Here we evaluate 16 previously proposed descriptors using a neural-network-based temperature classification framework, enabling an objective assessment of their ability to distinguish temperature-dependent structural changes in supercooled water. We further apply an explainable artificial intelligence method that identifies the structural features responsible for the model predictions. This approach reveals how different descriptors encode local structural information and establishes a data-driven framework for benchmarking structural descriptors in liquid water.
format Preprint
id arxiv_https___arxiv_org_abs_2605_00415
institution arXiv
publishDate 2026
record_format arxiv
spellingShingle Machine learning evaluation of structural descriptors for supercooled water
Yoshikawa, Kohei
Shikata, Kokoro
Kim, Kang
Matubayasi, Nobuyuki
Soft Condensed Matter
Chemical Physics
The anomalous behavior of liquid water is widely associated with a liquid-liquid phase transition between high- and low-density states in the supercooled regime. At the microscopic level, tetrahedral hydrogen-bond networks govern these properties, motivating structural descriptors that characterize local molecular environments. These structural descriptors quantify features such as tetrahedral order, local density, and the separation between the first and second coordination shells; however, they have largely been proposed independently, with limited systematic comparison. Here we evaluate 16 previously proposed descriptors using a neural-network-based temperature classification framework, enabling an objective assessment of their ability to distinguish temperature-dependent structural changes in supercooled water. We further apply an explainable artificial intelligence method that identifies the structural features responsible for the model predictions. This approach reveals how different descriptors encode local structural information and establishes a data-driven framework for benchmarking structural descriptors in liquid water.
title Machine learning evaluation of structural descriptors for supercooled water
topic Soft Condensed Matter
Chemical Physics
url https://arxiv.org/abs/2605.00415