We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
The Identification of Spherical Engineered Microplastics and Microalgae by Micro-hyperspectral Imaging
Summary
Scientists used hyperspectral imaging combined with machine learning to distinguish between microplastic particles and microalgae in seawater samples. Developing reliable automated methods for identifying microplastics in complex environmental samples is critical for accurate contamination monitoring.
Based on the micro-hyperspectral imaging technique, spherical engineered microplastic (polyethylene, 10-45 μm) and microalgae (Isochrysis galbana) (4-7 μm) were identified. In transmittance mode of MHSI, micro image cubes from 400 to 1000 nm were obtained from slides containing MP and MA in thin seawater. Classifiers like Support Vector Machine (SVM(Radial Basis Function (RBF))), Least Squares Support Vector Machine (LSSVM(RBF)), k-Nearest Neighbors, etc. were adopted and compared to classify MP and MA. In order to expand the imaging range of micro imaging, image stitching technology was adopted. In allusion to the stitched image cube, SVM(RBF) is suggested for the identification of MA and MP, with recall and precision > 0.86. The above results demonstrate that the MHSI is a promising technique, which can detect MPs with particle size Limit of Detection of 10-45 μm, and it is potential to further expand this LOD.