Concern about marine pollution caused by microplastics - plastic particles measuring up to 5mm – continues to increase, as awareness grows about their adverse impact on not only the ecosystem but on the human body, as well: through the food chain.
To adequately address this issue, insight is first urgently needed into the actual scope of the problem. What is the volume of microplastics in the various areas of the seas? What size are they and what type? In addition, the source, route, and destination of the outflow must be identified and analysed.
Until now, it has been common practice to scoop seawater and sediment with fine mesh, then to use a microscope to pick and analyze each particle manually. However, this is not only time-consuming and labour-intensive, but it also leads to the underestimation of the volume of small particles - 300μm or less - that pass through the mesh.
In a bid to help advance the research in this area, NEC Corporation worked with the Japan Agency for Marine-Earth Science and Technology (JAMSTEC) on the development of a system to automatically detect microplastics from seawater and sediment samples at high speed with the help of AI-based image recognition techniques.
For this project, NEC supplied a system to detect microplastics at high speed and with high accuracy using image recognition technology based on RAPID Machine- Learning, which incorporates the deep learning technology of its AI technology portfolio "NEC the WISE."
The system incorporates software that leverages JAMSTEC's R&D expertise for staining microplastics in samples with fluorescent dyes, allowing a video to be made of the microplastics with a fluorescence microscope while flowing at an optimum speed for detection. The software automatically extracts image data for each microplastic particle that appears in these videos. Utilizing AI-based image recognition technology, these are then automatically sorted and aggregated according to size and shape at a processing speed of 60 particles per minute.
JAMSTEC expects to be able to use this method to gain a deeper understanding of the extent of the microplastic pollution problem in the oceans and how this may be tackled.
“We will be able to contribute to the formulation of appropriate emission regulations," said Dr. Masashi Tsuchiya, Deputy Group Leader, Marine Plastics Research Group, JAMSTEC.