Lean CNNs for mapping electron charge density fields to material properties

Fuente: arXiv
Gespeichert in:
Bibliographische Detailangaben
Hauptverfasser: Ray, Pranoy, Choudhury, Kamal, Kalidindi, Surya R.
Format: Preprint
Veröffentlicht: 2025
Schlagworte:
Online-Zugang:
Tags: Tag hinzufügen
Keine Tags, Fügen Sie den ersten Tag hinzu!
_version_ 1866910944784809984
author Ray, Pranoy
Choudhury, Kamal
Kalidindi, Surya R.
author_facet Ray, Pranoy
Choudhury, Kamal
Kalidindi, Surya R.
contents This work introduces a lean CNN (convolutional neural network) framework, with a drastically reduced number of fittable parameters (<81K) compared to the benchmarks in current literature, to capture the underlying low-computational cost (i.e., surrogate) relationships between the electron charge density (ECD) fields and their associated effective properties. These lean CNNs are made possible by adding a pre-processing step (i.e., a feature engineering step) that involves the computation of the ECD fields' spatial correlations (specifically, 2-point spatial correlations). The viability and benefits of the proposed lean CNN framework are demonstrated by establishing robust structure-property relationships involving the prediction of effective material properties using the feature-engineered ECD fields as the only input. The framework is evaluated on a dataset of crystalline cubic systems consisting of 1410 molecular structures spanning 62 different elemental species and 3 space groups.
format Preprint
id arxiv_https___arxiv_org_abs_2505_09826
institution arXiv
publishDate 2025
record_format arxiv
spellingShingle Lean CNNs for mapping electron charge density fields to material properties
Ray, Pranoy
Choudhury, Kamal
Kalidindi, Surya R.
Materials Science
Disordered Systems and Neural Networks
Applied Physics
This work introduces a lean CNN (convolutional neural network) framework, with a drastically reduced number of fittable parameters (<81K) compared to the benchmarks in current literature, to capture the underlying low-computational cost (i.e., surrogate) relationships between the electron charge density (ECD) fields and their associated effective properties. These lean CNNs are made possible by adding a pre-processing step (i.e., a feature engineering step) that involves the computation of the ECD fields' spatial correlations (specifically, 2-point spatial correlations). The viability and benefits of the proposed lean CNN framework are demonstrated by establishing robust structure-property relationships involving the prediction of effective material properties using the feature-engineered ECD fields as the only input. The framework is evaluated on a dataset of crystalline cubic systems consisting of 1410 molecular structures spanning 62 different elemental species and 3 space groups.
title Lean CNNs for mapping electron charge density fields to material properties
topic Materials Science
Disordered Systems and Neural Networks
Applied Physics
url https://arxiv.org/abs/2505.09826