Generative AI-Based Inverse Design of Sustainable Biodegradable Polymers with Target Mechanical and Thermal Properties

Notice

This is an unedited manuscript accepted for publication and provided as an Article in Press for early access at the author’s request. The article will undergo copyediting, typesetting, and galley proof review before final publication. Please be aware that errors may be identified during production that could affect the content. All legal disclaimers of the journal apply.

Year : 2026 | Volume : 14 | 03 | Page :
    By

    Darapu Uma,

  • Manas Kumar Yogi,

  • Pendyala Devi Sravanthi,

  • N. Prasanthi,

  1. Associate Professor, Department of Computer Science and Engineering, Pragati Engineering College (A), Surampalem, Andhra Pradesh, India
  2. Assistant Professor, Department of Computer Science and Engineering, Pragati Engineering College (A), Surampalem, Andhra Pradesh, India
  3. Assistant Professor, Department of Computer Science and Engineering, Pragati Engineering College (A), Surampalem, Andhra Pradesh, India
  4. Associate Professor, Department of Basic Sciences and Humanities, Pragati Engineering College (A), Surampalem, Andhra Pradesh, India

Abstract

The escalating global plastic pollution crisis has intensified the urgent need for sustainable biodegradable polymer alternatives that can match or exceed the performance of conventional petroleum-based plastics while minimizing environmental impact. However, traditional polymer discovery approaches are severely constrained by high experimental costs, protracted development cycles spanning years, and fundamental inability to simultaneously optimize multiple conflicting material properties such as mechanical strength, thermal stability, and degradation kinetics. This study presents a rigorously validated Generative Artificial Intelligence (GenAI) framework for the inverse design of biodegradable polymers that concurrently satisfies mechanical, thermal, and environmental sustainability requirements through an integrated computational pipeline. The proposed framework combines molecular graph representations that capture atomic-level structural information with denoising diffusion probabilistic models (DDPM) operating in continuous embedding space for novel polymer generation. A graph attention network (GAT) serves as the property predictor with multi-task learning capabilities, while NSGA-III multi-objective optimization drives the search toward Pareto-optimal candidates across competing performance criteria. Life-cycle carbon footprint assessment is embedded as a formal optimization objective rather than a post-hoc filter, enabling sustainability-driven molecular design from inception. Comprehensive computational experiments conducted on the PolyInfo and PI1M polymer databases demonstrate that the proposed framework achieves molecular validity rate of 94.8%, novelty rate of 88.3%, and tensile strength prediction RMSE of 2.87 MPa—representing substantial improvements of 13.4%, 19.4%, and 43% over the best competing baseline methods, respectively. The generated polymer candidates exhibit exceptional property profiles with tensile strengths ranging from 60 to 78 MPa, glass transition temperatures of 220 to 255°C, and biodegradation completion within 6 to 12 months, substantially outperforming conventional biodegradable polymers in all performance dimensions. This framework addresses five critical research gaps including single-property optimization limitations, absence of sustainability constraints, low molecular validity rates, dataset scarcity challenges, and interpretability deficits.

Keywords: Polymers, Biodegradable, Generative, Diffusion, Optimization, Sustainability.

How to cite this article:
Darapu Uma, Manas Kumar Yogi, Pendyala Devi Sravanthi, N. Prasanthi. Generative AI-Based Inverse Design of Sustainable Biodegradable Polymers with Target Mechanical and Thermal Properties. Journal of Polymer & Composites. 2026; 14(03):-.
How to cite this URL:
Darapu Uma, Manas Kumar Yogi, Pendyala Devi Sravanthi, N. Prasanthi. Generative AI-Based Inverse Design of Sustainable Biodegradable Polymers with Target Mechanical and Thermal Properties. Journal of Polymer & Composites. 2026; 14(03):-. Available from: https://journals.stmjournals.com/jopc/article=2026/view=249483


References

  1. Alshehri R, et al. Graph Neural Networks for Polymer Property Prediction. npj Computational Materials. 2023;9(1):1-11.
  2. Antoniou A, et al. Federated Learning for Collaborative Materials Discovery without Data Sharing. Nature Machine Intelligence. 2024;6(2):134-145.
  3. Batra R, et al. Emerging Materials Intelligence Ecosystems Propelled by Machine Learning. Nature Reviews Materials. 2021;6(11):655-678.
  4. Bhatt P, et al. QSPR Models for Predicting Tensile Strength of Biodegradable Polymers. Polymer. 2022;241:124508.
  5. Chen G, et al. Diffusion Models for Molecular Design: A Review. Chemical Reviews. 2023;123(14):8949-8975.
  6. Doan Tran H, et al. Inverse Design of Functional Polymers via Active Learning. ACS Applied Materials & Interfaces. 2022;14(19):22128-22139.
  7. Gao W, et al. Generative and Reinforcement Learning Approaches for Polymer Chain Conformation Sampling. Macromolecules. 2022;55(7):2575-2588.
  8. Gupta H, et al. A Diffusion-Based Generative Model for Polymer Structure Synthesis. Advanced Materials. 2023;35(21):2211789.
  9. Hu J, et al. Explainable Artificial Intelligence in Materials Science. npj Computational Materials. 2022;8(1):247.
  10. Jadhav O, et al. Sustainability-Aware Multi-Objective Optimization of Biopolymers Using NSGA-III. Sustainable Materials and Technologies. 2023;36:e00625.
  11. Kim C, et al. Polymer Genome: A Data-Powered Platform for Property Prediction and Material Design. Chemistry of Materials. 2021;33(11):4107-4121.
  12. Li X, et al. Variational Autoencoders for Molecular Graph Generation and Property Prediction. Journal of Chemical Information and Modeling. 2023;63(4):1152-1165.
  13. Liu Y, et al. Deep Learning-Enabled Inverse Design of Sustainable Packaging Materials. ACS Sustainable Chemistry & Engineering. 2023;11(9):3720-3731.
  14. Ma R, et al. Machine Learning Prediction of Glass Transition Temperature for Polymers. Macromolecules. 2022;55(12):5065-5074.
  15. Nigam A, et al. Generating Molecules Using Adversarial Training to Optimize Properties. npj Computational Materials. 2021;7(1):49.
  16. Oliveira A, et al. Life Cycle Assessment Integration into AI-Driven Polymer Design. Green Chemistry. 2023;25(3):986-1001.
  17. Park S, et al. Transfer Learning Approaches for Small-Scale Polymer Datasets in Property Prediction. Journal of Materials Chemistry A. 2023;11(8):4018-4032.
  18. Podryabinkin E, et al. Accelerating Crystal Structure Prediction by Machine-Learning Interatomic Potentials with Active Learning. Physical Review B. 2022;105(21):214111.
  19. Ramprasad R, et al. Machine Learning in Materials Informatics: Recent Applications and Prospects. npj Computational Materials. 2017;3(1):54.
  20. Sanchez-Lengeling B, Aspuru-Guzik A. Inverse Molecular Design Using Machine Learning: Generative Models for Matter Engineering. Science. 2018;361(6400):360-365.
  21. Sha W, et al. Artificial Intelligence to Accelerate the Development of Biodegradable Polymers. Chemistry of Materials. 2021;33(5):1907-1917.
  22. Shi C, et al. Molecular Graph Transformer for Property Prediction of Polymers. ACS Nano. 2023;17(4):3620-3631.
  23. Sridharan M, et al. Physics-Informed Neural Networks for Thermoset Polymer Cure Kinetics. Composites Science and Technology. 2022;226:109552.
  24. Stuyver T, et al. Reaction Energy Predictions via Equivariant Graph Neural Networks. Journal of Chemical Physics. 2022;156(8):084104.
  25. Tao L, et al. Machine Learning for Perovskite Solar Cell Design. Advanced Energy Materials. 2021;11(32):2100157.
  26. Manickaraj, K., Karthik , A., Palanisamy, S., Jayamani, M., Ali, S. K., Lakshmi Sankar, S., and Al-Farraj, S. A. (2025). “Improving mechanical performance of hybrid polymer composites: Incorporating banana stem leaf and jute fibers with tamarind shell powder,” BioResources 20(1), 1998–2025.
  27. Palaniappan, M., Palanisamy, S., Murugesan, T., Tadepalli, S., Khan, R., Ataya, S., and Santulli, C. (2024). “Influence of washing with sodium lauryl sulphate (SLS) surfactant on different properties of ramie fibres,”BioResources 19(2), 2609-2625.
  28. Sivasubramanian Palanisamy et al 2023  Res. Express 10 085503
  29. Kar, A., Saikia, D., Palanisamy, S. et al.Calamus tenuis fiber reinforced epoxy composites: effect of fiber loading on the tensile, structural, crystalline, thermal and morphological characteristics. J Polym Res 31, 323 (2024). https://doi.org/10.1007/s10965-024-04162-6
  30. Kar A, Saikia D, Palanisamy S, Pandiarajan N. Effect of fiber loading on the mechanical, morphological, and dynamic mechanical characteristics of Calamus tenuis fiber reinforced epoxy composites. J Vinyl Addit Technol. 2025;31(1):224-240. doi:10.1002/vnl.22167
  31. Bachtiar, D., Mohammed, A.A., Palanisamy, S. et al.Effect of alkaline treatment on the thermal and mechanical properties of sugar palm fibre reinforced thermoplastic polyurethane composites. Sci Rep 15, 14085 (2025). https://doi.org/10.1038/s41598-025-99227-x
Ahead of Print Subscription Original Research
Volume 14
03
Received 27/06/2026
Accepted 08/07/2026
Published 11/07/2026
Publication Time 14 Days
1

Login


My IP

PlumX Metrics