A Physics-Embedded AI Framework for Predictive Polymer Thermodynamics: Methodology, System Design, and Validation

Oreoluwa Alade; Onuh Matthew Ijiga

doi:10.71097/IJSAT.v16.i4.9928

A Physics-Embedded AI Framework for Predictive Polymer Thermodynamics: Methodology, System Design, and Validation

Author(s)	Oreoluwa Alade, Onuh Matthew Ijiga
Country	United States
Abstract	This research presents a Physics-Embedded Artificial Intelligence (AI) Framework for Predictive Polymer Thermodynamics, integrating machine learning models with fundamental thermodynamic equations to generate accurate, real-time predictions of polymer behavior across diverse temperature and pressure conditions. The system combines Graph Neural Networks, Physics-Informed Neural Networks, and ensemble predictive techniques with embedded constraints such as heat capacity derivatives and Gibbs free energy relationships, ensuring scientific consistency and preventing non-physical outputs. A fully interactive Graphical User Interface (GUI) was developed to support user-driven simulations, database management, explainability visualization, and uncertainty quantification. Comprehensive evaluations demonstrate that the physics-embedded AI model outperforms traditional thermodynamic methods in accuracy, stability, and computational efficiency. The predictive engine delivers smooth thermodynamic curves, low error rates, and reliable uncertainty bounds, while maintaining robustness under extreme and boundary conditions. The visualization and interaction modules enable intuitive exploration of thermodynamic trends through dynamic plots, tables, history logs, and feature importance analytics. The system contributes significantly to polymer science by accelerating computational workflows, improving interpretability, and reducing reliance on resource-intensive laboratory and simulation procedures. Industrial applications include polymer formulation, process optimization, and materials design, while academic and educational users benefit from its clarity, interactivity, and reproducibility. Despite limitations related to dataset availability, computational training costs, and interpretability complexity, the framework establishes a powerful foundation for future advances in AI-driven thermodynamic modeling. The findings highlight the potential of hybrid physics–AI approaches to transform material analysis and support next-generation digital tools for polymer engineering.
Keywords	Physics-Informed Artificial Intelligence, Polymer Thermodynamics, Graph Neural Networks (GNNs), Thermodynamic Modeling, Predictive Computational Framework.
Field	Engineering
Published In	Volume 16, Issue 4, October-December 2025
Published On	2025-12-21
DOI	https://doi.org/10.71097/IJSAT.v16.i4.9928
Short DOI	https://doi.org/hbgzf9

View / Download PDF File

doi

CrossRef DOI is assigned to each research paper published in our journal.

IJSAT DOI prefix is
10.71097/IJSAT

Downloads

Research Paper Format Copyright Permission Form and Undertaking Form Cover Page Vol 16 Isu 3 Cover Page Vol 16 Isu 2 Cover Page Vol 16 Isu 1

All research papers published on this website are licensed under Creative Commons Attribution-ShareAlike 4.0 International License, and all rights belong to their respective authors/researchers.

CC-BY-SA

About IJSAT Fees & Payment Current Issue Publication Archive	Submit Research Paper Track Submission Status Publication Guidelines Publication Ethics Peer Review & Plagiarism	Join as a Reviewer Editors & Reviewers Reviewer Referral Program Get Reviewer Membership Certi.	Website/Journal Policies Usage Policy Content Policies Privacy Policy

Contact Us	Message on WhatsApp	+91-9687-182-185	editor@ijsat.org

International Journal on Science and Technology

A Widely Indexed Open Access Peer Reviewed Multidisciplinary Bi-monthly Scholarly International Journal

A Physics-Embedded AI Framework for Predictive Polymer Thermodynamics: Methodology, System Design, and Validation

Share this