Sustainable biobased packaging via integrated robotics/machine learning workflow for improved postharvest preservation
Year: 2026
Type: article
Abstract: Reliance on petroleum-derived plastic packaging exacerbates environmental burdens and lacks intrinsic antimicrobial protection against food spoilage. While biobased materials offer a sustainable alternative, optimizing their formulations is hindered by vast component libraries, inefficient trial-and-error experimentation, and complex multiproperty requirements. Herein, we develop an integrated workflow combining robotic automation, machine learning predictions, density functional theory, and life cycle assessment to accelerate biobased packaging discovery. Leveraging data augmentation and ensemble modeling, we use a hierarchical neural network to predict ∼1 billion candidate formulations, balancing mechanical properties, optical transparency, and environmental footprint. The resulting biobased packaging demonstrates enhanced hydrostability, effective antimicrobial activity, and high barrier performance, significantly extending the shelf life of cucumbers and avocados. Last, we release a data-sharing platform featuring forward prediction, inverse design, and environmental impact functions to support community use. This integrative framework provides sustainable, antimicrobial packaging materials alternative to conventional plastic films.
Source: Science Advances
Language: English
Subfield: Materials Chemistry
Field: Materials Science
Domain: Physical Sciences
Keywords: bio-based packaging, antimicrobial packaging, postharvest preservation, inverse design, life cycle assessment, density functional theory, hierarchical neural networks, data augmentation, ensemble learning, water stability, barrier properties, optical transparency, cucumber, avocado, data sharing platform
Open Access status: gold
Estimated APC paid: $4,500
Award: G1460986946
OpenAlex ID: W7224106936
