Machine learning can tackle plastic pollution

Compostable plastics, including wrappers and packaging, can contaminate conventional plastic waste in the recycling process.

Now, scientists have developed machine learning methods that can identify compostable plastics among conventional types.

Study results showed high success rates, although some materials were identified more reliably than others, reports Frontiers. Disposable plastics are everywhere: Food s, coffee cups, plastic bags. Some of these plastics, called compostable plastics, can be engineered to biodegrade under controlled conditions. However, they often look identical to conventional plastics, get recycled incorrectly and, as a result, contaminate plastic waste streams and reduce recycling efficiency. Similarly, recyclable plastics are often mistaken for compostable ones, resulting in polluted compost. Researchers at University College London (UCL) have published a paper in Frontiers in Sustainability in which they used machine learning to automatically sort different types of compostable and biodegradable plastics and differentiate them from conventional plastics. “The accuracy is very high and allows the technique to be feasibly used in industrial recycling and composting facilities in the future,” said Prof Mark Miodownik, corresponding author of the study.