Machine-Learning-Guided Experimental Prioritization of Seaweed-Derived Bioplastic Films Toward an LDPE-like Mechanical Target Using Sparse Literature Data

Gatica, Nicolas Rafael Andrés Gallardo; Rivera, José Luis Valin; Abreu, María Elena Fernández; Diaz, Francisco Rolando Valenzuela; Fernandez, Meyli Valin; Ketterer, Cristóbal Ignacio Galleguillos; Palomera, Daniel Francisco Leiva; Amorim, Wanderley Ferreira de

doi:10.3390/polym18172145

This is an early access version, the complete PDF, HTML, and XML versions will be available soon.

Open AccessArticle

Machine-Learning-Guided Experimental Prioritization of Seaweed-Derived Bioplastic Films Toward an LDPE-like Mechanical Target Using Sparse Literature Data

by

Nicolas Rafael Andrés Gallardo Gatica

¹,

José Luis Valin Rivera

^1,*

,

María Elena Fernández Abreu

¹,

Francisco Rolando Valenzuela Diaz

^2,*,

Meyli Valin Fernandez

³

,

Cristóbal Ignacio Galleguillos Ketterer

¹

,

Daniel Francisco Leiva Palomera

¹ and

Wanderley Ferreira de Amorim, Jr.

⁴

¹

Escuela de Ingeniería Mecánica, Pontificia Universidad Católica de Valparaíso, Valparaiso 2340025, Chile

²

Departamento de Engenharia Metalúrgica e de Materiais, Escola Politécnica, Universidade de São Paulo, Av. Prof. Mello Moraes 2463, Sao Paulo 05508-010, SP, Brazil

³

Department of Mechanical Engineering (DIM), Faculty of Engineering (FI), Universidad de Concepción, Concepcion 4030000, Chile

⁴

Mechanical Engineering Department, Federal University of Campina Grande, Campina Grande 58429-900, PB, Brazil

^*

Authors to whom correspondence should be addressed.

Polymers 2026, 18(17), 2145; https://doi.org/10.3390/polym18172145

Submission received: 27 July 2026 / Revised: 25 August 2026 / Accepted: 27 August 2026 / Published: 2 September 2026

(This article belongs to the Section Artificial Intelligence in Polymer Science)

Download Versions Notes

Abstract

Seaweed polysaccharide films are potential alternatives to petroleum-derived flexible packaging, but literature data are sparse and heterogeneous. This study evaluates whether composition-only machine-learning models can prioritize reported seaweed formulations for experimental follow-up near a nominal low-density polyethylene (LDPE) mechanical target of 15 MPa tensile strength and 300% elongation at break. A published dataset of 115 formulations with 41 compositional predictors was analyzed using a regularized linear baseline (ridge regression), random forest, and a deliberately shallow, regularized XGBoost model. Model performance was estimated using repeated five-fold cross-validation (10 repeats; 50 test-fold evaluations). For tensile strength, mean

R^{2}

was 0.617 ± 0.174 for random forest and 0.628 ± 0.150 for XGBoost, with corresponding RMSE values of 12.35 ± 3.52 and 12.27 ± 3.84 MPa. For elongation, random forest and XGBoost reached mean

R^{2}

values of 0.498 ± 0.194 and 0.470 ± 0.188, respectively. The linear baseline was materially less stable, indicating that the available composition-property relations are not adequately represented by a global linear model. The maximum observed elongation was 172.5%, which is 42.5% below the 300% screening target; equivalently, the target lies 73.9% above the dataset maximum. Consequently, the model cannot establish LDPE equivalence or credible extrapolation to the target. Residual diagnostics, learning curves, and SHAP analyses were added to bound interpretation. The defensible outcome is experimental prioritization within the observed domain, not inverse design or material substitution.

Keywords: seaweed bioplastics; agar; alginate; carrageenan; machine learning; experimental prioritization; LDPE; mechanical properties; sparse data; repeated cross-validation

Share and Cite

MDPI and ACS Style

Gatica, N.R.A.G.; Rivera, J.L.V.; Abreu, M.E.F.; Diaz, F.R.V.; Fernandez, M.V.; Ketterer, C.I.G.; Palomera, D.F.L.; Amorim, W.F.d., Jr. Machine-Learning-Guided Experimental Prioritization of Seaweed-Derived Bioplastic Films Toward an LDPE-like Mechanical Target Using Sparse Literature Data. Polymers 2026, 18, 2145. https://doi.org/10.3390/polym18172145

AMA Style

Gatica NRAG, Rivera JLV, Abreu MEF, Diaz FRV, Fernandez MV, Ketterer CIG, Palomera DFL, Amorim WFd Jr. Machine-Learning-Guided Experimental Prioritization of Seaweed-Derived Bioplastic Films Toward an LDPE-like Mechanical Target Using Sparse Literature Data. Polymers. 2026; 18(17):2145. https://doi.org/10.3390/polym18172145

Chicago/Turabian Style

Gatica, Nicolas Rafael Andrés Gallardo, José Luis Valin Rivera, María Elena Fernández Abreu, Francisco Rolando Valenzuela Diaz, Meyli Valin Fernandez, Cristóbal Ignacio Galleguillos Ketterer, Daniel Francisco Leiva Palomera, and Wanderley Ferreira de Amorim, Jr. 2026. "Machine-Learning-Guided Experimental Prioritization of Seaweed-Derived Bioplastic Films Toward an LDPE-like Mechanical Target Using Sparse Literature Data" Polymers 18, no. 17: 2145. https://doi.org/10.3390/polym18172145

APA Style

Gatica, N. R. A. G., Rivera, J. L. V., Abreu, M. E. F., Diaz, F. R. V., Fernandez, M. V., Ketterer, C. I. G., Palomera, D. F. L., & Amorim, W. F. d., Jr. (2026). Machine-Learning-Guided Experimental Prioritization of Seaweed-Derived Bioplastic Films Toward an LDPE-like Mechanical Target Using Sparse Literature Data. Polymers, 18(17), 2145. https://doi.org/10.3390/polym18172145

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Article metric data becomes available approximately 24 hours after publication online.

Article Menu

Machine-Learning-Guided Experimental Prioritization of Seaweed-Derived Bioplastic Films Toward an LDPE-like Mechanical Target Using Sparse Literature Data

Abstract

Share and Cite

Article Metrics

Further Information

Guidelines

MDPI Initiatives

Follow MDPI