Work

Machine Learning-Assisted Designing and Screening of Polymers with a High Melting Point: Database Visualization and Synthetic Feasibility Assessment

Year: 2024

Type: article

Abstract: In this study, a novel approach leveraging machine learning (ML) techniques for the design and screening of polymers with high melting points is introduced. More than 40 ML models are trained for the prediction of the melting point. One best model is selected for further analysis. 10,000 polymers are generated using an automatic approach. The generated database of polymers is visualized and analyzed to find the hidden trends. Synthetic feasibility assessment is conducted to prioritize candidate polymers for future experimental work. Chemical similarity of chosen polymers is analyzed using cluster analysis and a heatmap. This research contributes to the advancement of polymer design methodologies, offering insights into the development of heat-resistant polymers for a wide range of industrial applications.

Source: ACS Omega

DOI: 10.1021/acsomega.4c05878

Authors: Zaheer Ahmed Dayo, Jiang Guosong, Mohamed A. El-Tayeb, Syed Shoaib Ahmad Shah, Sumaira Naeem

Institutions: Huanggang Normal University, King Saud University, National University of Sciences and Technology, Baba Guru Nanak University

Language: English

Topic: Machine Learning in Materials Science

Subfield: Materials Chemistry

Field: Materials Science

Domain: Physical Sciences

Open Access status: gold

Estimated APC paid: $1,935

Funder: King Saud University