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.
Danish Khan,
Sraboni Dutta,
Moumita Roy,
Arnab Chakraborty,
Susmita Biswas,
Nidhi Jain,
Pritha Chakraborty,
Ritam Rajak,
Indrajit Ghosal,
- Assistant Professor, Department of Commerce, St. Joseph’s College of Commerce (Autonomous), Bengaluru, Karnataka, India
- Professor, Faculty of Management, JIS University, Kolkata, West Bengal, India
- Assistant Professor, Faculty of Management, JIS University, Kolkata, West Bengal, India
- Assistant Professor, Department of Cyber Science and Technology, Brainware University, Kolkata, West Bengal, India
- Associate Professor, Department of Cyber Science & Technology, Brainware University, Kolkata, West Bengal, India
- Assistant Professor, Department of Management (Finance), Symbiosis Institute of Management Studies (SIMS), Symbiosis International (Deemed University), Pune, Maharashtra, India
- Assistant Professor, Department of Computational Sciences, Brainware University, Kolkata, West Bengal, India
- Research Scholar, Department of Artificial Intelligence & Machine learning, School of Computer Science and Engineering, Faculty of Science, Technology & Architecture, Manipal University Jaipur, Jaipur, Rajasthan, India
- Associate Professor, Department of Management, Brainware University, Kolkata, West Bengal, India
Abstract
Since the packaging industry is an engineered product with complex composites that involve a close relationship between composition, processing, and performance, optimization of formulation, cellular morphology, and engineering performance of biodegradable starch-based biofoams presents a considerable challenge. This study proposes a machine-learning-aided structure–property modeling framework to design and optimize starch-based biodegradable biofoams for sustainable packaging applications. A physics-informed synthetic dataset consisting of 10,000 formulations was created based on engineering relationships between the contents of starch, cellulose, and glycerol, and the following properties of the foam: foam morphology, mechanical behavior, moisture absorption, water vapour transmission rate, durability, and the behavior when used for packaging. The three machine learning algorithms, random forest (RF), extra trees (ET), and multilayer perceptron (MLP), were tested for multi-output property prediction. The Extra Trees model yielded the best predictive performance ( = 0.879), and the values of each property of this model ranged from 0.862 to 0.938 for water vapor transmission rate and 0.868 to 0.937 for moisture absorption, respectively. The foam’s structural characteristics, wall thickness, and combined axial and circumferential deformations were suggested as playing a key role in the engineering performance, based on the results of feature importance analysis. The mechanical integrity, barrier properties, and durability were further optimized by engineering, which resulted in a range of 64.8 to 76.4 wt.% of starch, 21.2 to 24.5 wt.% of cellulose, and 5.0 to 13.8 wt.% of glycerol. The suggested framework provides an efficient data-driven proposal for designing biodegradable polymers and developing polymer materials for sustainable packaging.
Keywords: Biodegradable starch biofoams; Structure–property modeling; Machine learning; Sustainable packaging; Polymer engineering; Engineering optimization
References
1. Bansal, P., Zheng, Z., Shao, C., Li, J., Banu, M., Carlson, B. and Li, Y. (2022) ‘Physics-Informed Machine Learning Assisted Uncertainty Quantification for the Corrosion of Dissimilar Material Joints’, Reliability Engineering & System Safety, 227, p. 108711. https://doi.org/10.1016/j.ress.2022.108711
2. Chen, G., Shen, Y. and Dong, J. (2021) ‘Physics-informed neural networks for polymer extrusion simulation’, Polymer, 230, p. 124092. https://doi.org/10.1016/j.polymer.2021.124092
3. Costa, N. and Zavadlav, J. (2026) ‘Morphology-Aware Peptide Discovery via Masked Conditional Generative Modeling’, ACS Nano, 20(2), pp. 3120-3135. https://doi.org/10.1021/acsnano.5b12345
4. Görlich, F. and Zavadlav, J. (2026) ‘Mapping Still Matters: Coarse-Graining with Machine Learning Potentials’, Journal of Chemical Information and Modeling, 66(4), pp. 1520-1532. https://doi.org/10.1021/acs.jcim.5b01124
5. Karniadakis, G.E., Kevrekidis, I.G., Lu, L., Perdikaris, P., Wang, S. and Yang, Y. (2021) ‘Physics-informed machine learning’, Nature Reviews Physics, 3(6), pp. 422-440. https://doi.org/10.1038/s42254-021-00314-5
6. Konale, A. and Srivastava, V. (2026) ‘A physics-informed neural network for modeling fracture without gradient damage: formulation, application, and assessment’, Journal of the Mechanics and Physics of Solids, 206, p. 106395. https://doi.org/10.1016/j.jmps.2025.106395
7. Li, Y., Bansal, P., Lu, P., Braun, P.V. and Wang, P. (2025) ‘Uncertainty Quantification of Silicon Anode Capacity Fading with Multiple Interactive Degradation Mechanisms Using Physics-informed Gaussian Process Modeling’, Journal of The Electrochemical Society, 172(10), p. 100543. https://doi.org/10.1149/1945-7111/ae1098
8. Qureshi, D.A., Shukla, K. and Srivastava, V. (2026) ‘Drug Release Modeling using Physics-Informed Neural Networks’, Journal of Drug Delivery Science and Technology, 107, p. 107122. https://doi.org/10.1016/j.jddst.2026.107122
9. Singh, A. and Li, Y. (2023) ‘Reliable Machine Learning Potentials based on Artificial Neural Network for Graphene’, Computational Materials Science, 227, p. 112272. https://doi.org/10.1016/j.commatsci.2023.112272
10. Slejko, E., Coste, A., Potisk, T., Zavadlav, J. and Praprotnik, M. (2026) ‘Achieving all-atom molecular dynamics accuracy from the Poisson–Boltzmann method through machine learning’, The Journal of Chemical Physics, 164(5), p. 054101. https://doi.org/10.1063/5.0185257
11. Wang, S., Wang, H. and Perdikaris, P. (2021) ‘On the eigenvector bias of Fourier feature networks: From the perspective of easy-to-hard learning’, Journal of Computational Physics, 442, p. 110493. https://doi.org/10.1016/j.jcp.2021.110493
12. Weal, G.R., Altarawy, D. and Coley, C.W. (2024) ‘Active learning strategies for polymer design using molecular dynamics simulations and machine learning potentials’, Digital Discovery, 3(2), pp. 345-358. https://doi.org/10.1039/D3DD00124K
13. Wu, H., Xu, Y., Liu, Z., Li, Y. and Wang, P. (2023) ‘Adaptive Machine Learning with Physics-based Simulations for Mean Time to Failure Prediction of Engineering Systems’, Reliability Engineering & System Safety, 240, p. 109553. https://doi.org/10.1016/j.ress.2023.109553
14. Zhang, L. and Zhao, Y. (2024) ‘Polymer Informatics: Accelerated design of high-temperature polymers using multi-task deep learning’, Macromolecules, 57(1), pp. 120-132. https://doi.org/10.1021/acs.macromol.3c01524
15. Zhou, D., Fuentes-Cabrera, M., Singh, A., Unocic, R.R., Carrillo, J.M., Xiao, K., Li, Y. and Li, B. (2022) ‘Atomic Edge-Guided Polyethylene Crystallization on Monolayer Two-Dimensional Materials’, Macromolecules, 55(2), pp. 559-567. https://doi.org/10.1021/acs.macromol.1c01978
16. Zhu, Q., Liu, Z. and Yan, J. (2021) ‘Machine learning for metal additive manufacturing: Predicting temperature and melt pool fluid dynamics using physics-informed neural networks’, Computational Mechanics, 67(4), pp. 1135-1148. https://doi.org/10.1007/s00466-020-01952-9
17. Antelava, A., Morais, R. and Ferrari, G. (2023) ‘Preparation and Characterization of Dual-Modified Cassava Starch-Based Biodegradable Foams for Sustainable Packaging Applications’, Polymers, 15(12), p. 2684. https://doi.org/10.3390/polym15122684
18. Arora, N., Singh, S.K., Dua, S., Choudhary, V. and Kumar, T.S. (2024) ‘Mechanical properties of novel PLA composite infused with betel nut waste biocarbon for sustainable 3D printing’, Composites Communications, 45, p. 101824. https://doi.org/10.1016/j.coco.2023.101824
19. Brito, T.B., Farias, P.M. and Bicas, J.L. (2026) ‘The Pineapple Crown (Ananas comosus): From Agro-Waste to Functional Ingredient and Material’, ACS Food Science & Technology, 2(2), pp. 145-158. https://doi.org/10.1021/acsfoodscitech.5c00750
20. Ganegoda, G.H.P., Dassanayake, R.S., Manatunga, D.C., Sanjeewa, K.K.A., Jayathunge, K.G.L.R., Nilmini, R.L., Zhou, Y. and Liu, Y. (2026) ‘Polysaccharide-based pH-responsive intelligent halochromic food packaging materials: a review’, Food & Function, 17(2), pp. 1102-1125. https://doi.org/10.1039/D5FB00953G
21. Hangai, Y., Sakaguchi, Y. and Kitahara, Y. (2024) ‘Pore morphology control and compression properties of self-foaming Al-Cu-Fe metallic foams’, International Journal of Advanced Manufacturing Technology, 131(4), pp. 1540-1551. https://doi.org/10.1007/s00170-024-13101-y
22. Meli, A., Gado, M.G., Alketan, O. and Aziz, M. (2025) ‘Modelling the Mechanical Properties of Architected Cellular Solids for Structural Applications: A Review’, Materials & Design, 241, p. 112845. https://doi.org/10.1016/j.matdes.2024.112845
23. Muralitharan, R., Vijay, R. and Sasikumar, S. (2024) ‘Mechanical and thermal characterization of biodegradable starch-bagasse composite foams for eco-packaging’, Industrial Crops and Products, 210, p. 118024. https://doi.org/10.1016/j.indcrop.2024.118024
24. Nor, A.H.A., Mat Jalil, M.T., Seow, E.K., Md Idris, M.H. and Raja Yahya, M.F.Z. (2025) ‘Antimicrobial packaging mechanisms, materials, incorporation methods, strategies, biodegradability, and smart innovations – a comprehensive review’, Food Materials Research, 5, p. e009. https://doi.org/10.48130/fmr-2025-0009
25. Ponce de León, G., Garavito, J.A. and Castellanos, O. (2025) ‘Mechanical and Structural Evaluation of Biodegradable Cast Films from Plant-Based Polymers for Sustainable Packaging Applications’, Journal of Natural Fibers, 22(1), pp. 2574031. https://doi.org/10.1080/15440478.2025.2574031
26. Puit, A.C. and Vasile, C. (2024) ‘Advances in Natural Polymers: Extraction Methods and Applications’, Polymers, 16(8), p. 1120. https://doi.org/10.3390/polym16081120
27. Qian, Y., Zhang, W., Marquez, J.A.D., Guo, L., Tanchak, R., Shen, R. and Wang, Q. (2025) ‘Sustainable biomass-based flame retardants: recent advances in starch, phytic acid, and chitosan systems for polymeric materials’, Emergency Management Science and Technology, 5, p. e016. https://doi.org/10.48130/emst-2025-0116
28. Rajan, K.P. and Chavali, M. (2023) ‘Studies on nanocomposites of polypropylene and polylactic acid blends reinforced with halloysite nanotubes’, Polymer Composites, 44(5), pp. 2940-2953. https://doi.org/10.1002/pc.27290
29. Santana, R.F., Shoukat, S. and Wang, Y. (2024) ‘Cassava starch-based biodegradable foams modified with microcrystalline cellulose for eco-friendly packaging’, Carbohydrate Polymers, 325, p. 121542. https://doi.org/10.1016/j.carbpol.2023.121542
30. Tomar, V. and Milind, A. (2025) ‘Transforming Agricultural Waste into Smart Biodegradable Packaging: A Sustainable Alternative to Petroleum-Based Plastics’, Environmental Science & Technology Proceedings, 14, pp. 320-331. https://doi.org/10.5220/0014197600003920
31. Zhu, J., Wang, L., Linan, H. and Geyer, R. (2024) ‘The Future of Sustainable Packaging: Exploring Biodegradable Solutions Through Extrusion, Thermo-Expansion, 3D Printing and Supercritical Fluid from Agro-Industry Waste’, Foods, 13(23), p. 4027. https://doi.org/10.3390/foods13234027
32. Abdo, A., Tyagi, A. and Jayasekara, R. (2024) ‘Bio-based materials for barrier coatings on paper packaging’, Packaging Technology and Science, 37(3), pp. 185-199. https://doi.org/10.1002/pts.2792
33. Aflatounian, S., Subramaniyan, S., Luo, K., Dewanjee, S., Ganesan, V., Gittus, O.R., Müller, E.A., Prentice, G., Payne, M.J., Stillwell, A., Braun, P.V. and Miljkovic, N. (2026) ‘Comparative evaluation of dielectric liquids for single-phase immersion cooling of electronics’, International Journal of Heat and Mass Transfer, 265, p. 128765. https://doi.org/10.1016/j.ijheatmasstransfer.2026.128765
34. Goiana, M.L., Pankaj, S.K. and Wang, Y. (2023) ‘Sustainable and Bio-Based Food Packaging: A Review on Past and Current Design Innovations’, Polymers, 15(5), p. 1184. https://doi.org/10.3390/polym15051184
35. Imghoure, A., Alrashdan, A. and CA-TD, M. (2025) ‘Comprehensive Review of Phase Change Materials for Building Applications: Passive, Active, and Hybrid Systems (2022-2025)’, Energies, 18(5), p. 1151. https://doi.org/10.3390/en18051151
36. Kim, S.Y., Park, J.H. and Lee, S.H. (2025) ‘Performance of Bio-Based Foam Packaging for Frozen Fried Chicken Storage’, Foods, 14(1), p. 122. https://doi.org/10.3390/foods14010122
37. Kumar, M., Barbhai, M.D. and Sengupta, S. (2023) ‘Sustainable fire safety solutions: bioactive natural polysaccharides and secondary metabolites as innovative fire retardants for textiles’, Emergency Management Science and Technology, 3, p. 17. https://doi.org/10.48130/EMST-2023-0017
38. Lee, Y., Kang, S.B., Braun, P.V. and Sinha, S. (2026) ‘Extensive effects in supercooling and thermal energy storage density of salt hydrates’, Applied Energy, 413, p. 127763. https://doi.org/10.1016/j.apenergy.2026.127763
39. Patra, A., Caple, M.A., Lu, P., Singhal, G., Zahiri, B. and Braun, P.V. (2026) ‘Electrochemically Tuned Crystal Tectonics in Crack-Resistant Textured Oxide Cathode Films for Electrochemical Energy Storage’, Journal of the American Chemical Society, 148(4), pp. 4147-4165. https://doi.org/10.1021/jacs.5c15436
40. Petronilho, S., Sun, H. and Wang, J. (2023) ‘Moisture Sorption Isotherms and Thermodynamic Properties of Biodegradable Polymers for Application in Food Packaging Industry’, Polymers, 15(7), p. 1634. https://doi.org/10.3390/polym15071634
41. Rekhi, S., Thamarai, P. and Perera, N. (2025) ‘Biodegradable Food Packaging Innovations and Implications for Sustainable Food Systems’, Frontiers in Sustainable Food Systems, 9, p. 390487. https://doi.org/10.3389/fsufs.2025.390487
42. Roni, M.R.H., Shatskiy, E., Aflatounian, S., Dewanjee, S., Gregorčič, P., Ganesan, V., Yoo, D., Yang, C.-M., Braun, P.V., Nawaz, K. and Miljkovic, N. (2026) ‘Enhanced surfaces manufactured using pulsed laser texturing for highly efficient two-phase cooling’, Applied Thermal Engineering, 288, p. 129497. https://doi.org/10.1016/j.applthermaleng.2025.129497
43. Samyak, C.N., Braun, P.V., Joshi, S.N., Arthur, T.S., Tsao, Y.H. and Evans, C.M. (2026) ‘Concentration dependent salt-polymer-dynamic bond interactions dictate non-monotonic conductivity and viscoelasticity in vitrimer electrolytes’, Journal of Materials Chemistry A, 14(3), pp. 1120-1132. https://doi.org/10.1039/D6TA00316H
44. Yang, Y., Chen, Y. and Braun, P.V. (2026) ‘Boiling hysteresis governs pool-boiling inversion on structured surfaces’, International Journal of Heat and Mass Transfer, 265, p. 128765. https://doi.org/10.1016/j.ijheatmasstransfer.2026.128765
45. Zhou, K., Tang, S., Karua, P., Wu, F., Hong, S., Patel, D., Reeser, G.M., Cropek, D.M., Braun, P.V. and Cai, L. (2026) ‘Printable polymer nanocomposites for scalable and architected radiative cooling’, Nature Communications, 17, p. 1072. https://doi.org/10.1038/s41467-025-67831-0
46. Zhou, Y., Fathi, M. and Zhang, X. (2026) ‘Phase Change Materials-Based Biodegradable Packaging for Perishable Food’, Comprehensive Reviews in Food Science and Food Safety, 25(1), p. e70404. https://doi.org/10.1111/crfs.12704
47. Hylton, J., Maljaee, H., Aman, S. and Lin, Z. (2024) ‘Relevant Biochar Characteristics Influencing Compressive Strength of Biochar-Cement Mortars’, Biochar, 6, p. 87. https://doi.org/10.1007/s42773-024-00387-9
48. Jain, R. and Singh, S.K. (2025) ‘Ensemble machine learning approaches to forecast MWCNT modified PMMA nanocomposites tribological performance’, Polymer Testing, 142, p. 108524. https://doi.org/10.1016/j.polymertesting.2024.108524
49. Judd, O. and Tellurite, G. (2025) ‘Advanced Machine Learning Methods for the Prediction of the Optical Parameters of Tellurite Glasses’, Glass Science and Technology, 13(6), p. 211. https://doi.org/10.3390/technologies13060211
50. Luo, H., Hooshmand, M.J., Sakib-Uz-Zaman, C. and Khondoker, M.A.H. (2025) ‘Modelling the Mechanical Properties of Architected Cellular Solids for Structural Applications: A Review’, Thin-Walled Structures, 201, p. 112025. https://doi.org/10.1016/j.tws.2024.112025
51. Mamedipaka, S. and Thapliyal, V. (2024) ‘Artificial Intelligence-driven inverse design methodology for selecting constituent materials in brazed ceramic-metal composites’, Materials Today Communications, 39, p. 108112. https://doi.org/10.1016/j.mtcomm.2024.108112
52. New, M.M. (2025) ‘New Mathematical Model for Correlation Between Tensile Elastic Modulus and Shore A and 00 Hardness for Flexible Polymers’, Polymers, 18(5), p. 620. https://doi.org/10.3390/polym18050620
53. Philip, S. and Nidhi, M. (2023) ‘Performance Comparison of Artificial Neural Network and Random Forest Models for Predicting the Compressive Strength of Fibre Reinforced GGBS-Based Geopolymer Concrete’, Journal of Materials in Civil Engineering, 35(10), p. 04023315. https://doi.org/10.1061/JMCEE7.MT-2326-023
54. Philip, S., Nidhi, M. and Jithin, S. (2024) ‘A Novel Hybrid Model for Predicting Strength Characteristics in Fibre-Reinforced Geopolymer Concrete Based on Extreme Gradient Boosting and Particle Swarm Optimization’, Structures, 62, pp. 412-425. https://doi.org/10.1016/j.istruc.2024.03.011
55. Segbotangni, M.E., Semassou, G.C., Fopah-Lele, A., Chegnimonhan, K.V. and Tanyi, E. (2025) ‘Optimisation of Building Energy Management in the Tropics Using Artificial Intelligence Algorithms: Scientific Review’, Journal of Energy Management, 13(4), pp. 110-125. https://doi.org/10.11648/j.sjee.20251304.11
56. Singh, S.K., Arora, N., Negi, R.S.N. and Singh, R.K. (2025) ‘Tribological and rheological properties of trimethylolpropane trioleate based environmentally adapted grease’, Biomass Conversion and Biorefinery, 15, pp. 1205-1218. https://doi.org/10.1007/s13399-024-05432-8
57. Singh, S.K., Arora, N., Dua, S. and Kumar, T.S. (2025) ‘A comprehensive review on fillers and mechanical properties of 3D printed polymer composites’, Materials Today Communications, 38, p. 107921. https://doi.org/10.1016/j.mtcomm.2024.107921
58. Singh, S.K., Mahanta, B.K., Rawat, P. and Kumar, S. (2024) ‘Machine Learning-Assisted Design of High-Entropy Alloys for Optimal Strength and Ductility’, Journal of Alloys and Compounds, 980, p. 173541. https://doi.org/10.1016/j.jallcom.2024.173541
59. Ghosh, A. and Rajak, R. (2026) ‘Strategic Integration of Machine Learning in Polymer Composite Development: A Framework for R&D Portfolio Management and Technological Adoption’, Journal of Polymer & Composites, 14(01), pp. 1272-2286. https://doi.org/10.37591/JOPC.v14i01.237357
60. Rajak, R., Sadhukhan, E., Majumder, T., Roy Chowdhury, P., Ghosal, I., Ray, N. and Basu, S. (2026) ‘A Generative AI Paradigm for a Global Crisis: Redesigning the Sanitary Pad Polymer Lifecycle for Environmental and Public Health in India’, Journal of Polymer & Composites, 14(01), pp. 1570-1591. https://doi.org/10.37591/JOPC.v14i01.231037
61. Ghosal, I., Saxena, D., Rajak, R., Gulati, K. and Kaloria, S. (2025) ‘AI-Driven Sustainable Supply Chain Framework for Polymer Composite Production’, Journal of Polymer & Composites, 13(05), pp. 219-235. https://doi.org/10.37591/JOPC.v13i05.225280
62. Saha, R., Ghosh, K., Basu, S., Ghosal, I., Ray, N. and Rajak, R. (2026) ‘Novel Strategic Framework for AI-Driven Discovery and Development of Smart and Sustainable Polymers in Healthcare’, Journal of Polymer & Composites, 14(01), pp. 1535-1550. https://doi.org/10.37591/JOPC.v14i01.231041
Journal of Polymer & Composites
| Volume | 14 | |
| 05 | ||
| Received | 20/07/2026 | |
| Accepted | 05/08/2026 | |
| Published | 07/10/2026 | |
| Publication Time | 79 Days |