A collaborative team of researchers has developed a method to detect the presence of microplastics in marine and freshwater environments using optical analysis and machine learning techniques. The method eliminates time-consuming separation techniques and can help enhance future environmental monitoring programs.
Microplastics have historically proved challenging to detect and monitor due to their structural similarities to many natural compounds found in water samples. Current monitoring techniques rely on separation analysis that, while accurate, are time-consuming and costly to perform.
Our new method can simultaneously separate and measure the abundance of six key types of microplastics—polystyrene, polyethylene, polymethylmethacrylate, polytetrafluoroethylene, nylon and polyethylene terephthalate," said Dr. Olga Guselnikova of the National Institute for Materials Science (NIMS).
The method, published in Nature Communications, relies on a low-cost porous metal foam to capture the microplastics before being optically detected by surface-enhanced Raman spectroscopy (SERS). "The SERS data obtained is highly complex," said Dr. Joel Henzie of NIMS, "but it contains discernible patterns that can be interpreted using modern machine learning techniques."
To aid in this data analysis the team developed a neural network computer algorithm called SpecATNet that relies on machine learning to interpret patterns in the data to quickly identify target microplastics.
"Our procedure holds immense potential for monitoring microplastics in samples obtained directly from the environment, with no pretreatment required, while being unaffected by possible contaminants that could interfere with other methods," said Professor Yusuke Yamauchi of Nagoya University.
The team believes that the method could offer a low-cost accurate method for detecting the presence of target microplastics within environmental samples. In its current state, the method provides a cost savings of nearly 95% over commercially available alternatives and the team believes by further optimizing the method, that cost savings could continue to grow.