We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Feasibility of Utilizing Machine Learning to Identify a More Sustainable Alternative to Polyester in Textiles
Summary
Researchers used machine learning trained on the PI1M polymer dataset of over one million compounds to identify sustainable alternatives to polyester in textiles, predicting key material properties including glass transition temperature, density, melting temperature, oxygen permeability, and bulk modulus. The study found that artificial neural networks could screen polymer candidates for environmental compatibility while maintaining performance characteristics comparable to polyester.
The mass production of textiles has created several concerns for the environment and its future, with the increase of greenhouse gases that are released during the production of Polyester.Machine learning is a recent technology commonly used in polymer science to consider vast amounts of data, relatively quickly.The aim of the project is to find an alternative polymer that possesses similar characteristics to polyester with a considerably lower environmental impact.In this study, we used a publicly available dataset, PI1M, containing information on over one million polymers to train artificial neural net.We looked into predicting key features for these polymers, including glass transition temperature, density, melting temperature, oxygen permeability, compressibility, and bulk modulus.Through the process of machine learning modeling, several properties of new polymers were successfully predicted.An agreement was found between the true and predicted values for each of these features.The results show the presence of a possibly more sustainable alternative to Polyester in textiles.This study demonstrates the feasibility of using machine learning to discover new, more sustainable polymers.
Sign in to start a discussion.
More Papers Like This
Revealing factors influencing polymer degradation with rank-based machine learning
Researchers developed a machine learning platform using a ranking-based algorithm to predict and compare how easily different polymer materials biodegrade, integrating three different experimental datasets with varying conditions. Analysis revealed key molecular factors that control degradability, offering guidance for designing more environmentally friendly plastics.
Recent Advances in Polymer Design through Machine Learning: A Short Review
This review examines recent advances in applying machine learning — including supervised learning, unsupervised learning, and artificial neural networks — to polymer informatics, covering property prediction, synthesis optimisation, and polymer classification across diverse applications from medicine to aerospace. The authors highlight how growing datasets and improving ML techniques are enabling more systematic and effective polymer design compared to traditional trial-and-error approaches.
Applied machine learning as a driver for polymeric biomaterials design
Researchers reviewed how machine learning could accelerate the design of new medical-grade polymers by predicting properties like biodegradability and biocompatibility, bypassing slow trial-and-error lab work. The main obstacle identified is the lack of standardized, publicly available data on medically relevant polymer characteristics needed to train reliable AI models.
AI-Assisted Design of Chemically Recyclable Polymers for Food Packaging
Researchers applied a machine learning–driven polymer informatics workflow to screen ~7.4 million ring-opening polymerization polymers for sustainable food packaging, experimentally validating poly(p-dioxanone) as a promising candidate with strong water barrier performance and ~95% chemical recyclability, demonstrating how data-driven design can bridge sustainability goals and real-world packaging applications.
Assessment of machine learning-based methods predictive suitability for migration pollutants from microplastics degradation
Researchers assessed the usefulness of machine learning methods for predicting the migration of chemical pollutants from microplastics. The study found that artificial neural networks and support vector methods showed strong potential for modeling and predicting the leaching of plasticizers and other contaminants, which could reduce the need for extensive laboratory analyses.