Work

PIL-Net: a physics-informed graph convolutional network for predicting atomic multipoles

Year: 2025

Type: article

Abstract: PIL-Net is a physics-informed graph convolutional network capable of predicting atomic multipole moments quickly and with high accuracy.

Source: Digital Discovery

DOI: 10.1039/d5dd00228a

Authors: Caitlin Whitter, Alex Pothen, Aurora Clark

Institutions: Purdue University West Lafayette, University of Utah

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: diamond

Funders: U.S. Department of Energy, Purdue University, Office of Science, Lawrence Berkeley National Laboratory

Awards: DATA SUMMARIZATION AND INFERENCE AT SCALE, DOE COMPUTATIONAL SCIENCE GRADUATE FELLOWSHIP (CSGF) GRANT 2019 COHORT, DOE COMPUTATIONAL SCIENCE GRADUATE FELLOWSHIP (CSGF) GRANT 2019 COHORT

OpenAlex ID: W4412475837

FWCI:

Cites: 48

Cited by:

Related to: 10