Researchers Built Machine Learning Tool for Bio-based Polymers
A new framework accelerates the discovery of sustainable alternatives for industrial coatings and adhesives.
Updated on Sept. 29, 2026 in Chemistry
Live Poll
Do you believe AI-driven research will successfully make everyday consumer products more sustainable?
Researchers have developed a machine learning framework that predicts the properties of bio-based monomers to replace conventional industrial formulations. The tool uses neural networks and gradient boosting to streamline the development of eco-friendly coatings and adhesives.
Why it matters
Traditional trial-and-error experimental screening for new bio-based materials is extremely slow and resource-intensive, hindering the industry's shift away from petroleum-based products. This framework addresses that inefficiency by rapidly identifying viable chemical alternatives.
The framework successfully predicts key metrics including propagation rate constants, reactivity ratios, glass transition temperatures, and water solubility. It was validated through two experimental case studies comparing bio-based systems to conventional ones.
The players
Advanced Intelligent Discovery
This is a scientific journal that publishes peer-reviewed research regarding advancements in intelligent systems and computational discovery.
The details
The software suite integrates multiple modeling techniques into a unified selection tool that replaces conventional styrene or methyl methacrylate combinations. It successfully identifies bio-based monomer pairs that match the performance requirements of established industrial applications.
Timeline
The research findings were published in the journal Advanced Intelligent Discovery in 2026.
Global production of bio-based polymers is projected to reach 4 to 5 percent of the total market by 2035.
The Big Picture
This research follows a pattern set by the development of sustainable polymer production technologies aimed at reducing global industrial reliance on petroleum-based chemical feedstocks. It marks a shift toward computational discovery to overcome the speed limitations inherent in bench-top chemical testing.
This development could accelerate the availability of non-toxic, sustainable paints, coatings, and adhesives for consumer use. As these bio-based materials move into production, manufacturers may be able to offer products that are both high-performing and environmentally friendly.
The takeaway
Computational modeling is transforming chemical engineering by turning years of manual lab work into predictive, data-driven workflows. Integrating these tools is essential for companies aiming to meet future sustainability targets while maintaining product performance.
Further reading
For more information on chemical development, visit the Chemistry section.
More information
Read the complete academic study on machine learning models for full methodology details.
Source note: This article includes information reported by European Coatings.
Live Poll
Do you believe AI-driven research will successfully make everyday consumer products more sustainable?
