Underwater hyperspectral imaging for in situ underwater microplastic detection

Microplastics (MPs) on the seabed threatening marine ecology or human health have drawn much attention. Most research focuses on the in situ detection of MPs in air, while the underwater environment, including light absorption and scattering of the water body, makes in situ MP detection challenging. This study proposed a method for in situ detection of underwater MPs (0.5–5 mm) using underwater VIS hyperspectral imaging (400–720 nm). The underwater spectral image correction model of the water body was calibrated by comparing the images of swatches in air and underwater. Different classifiers, including support vector machine (SVM), neural network (NN), least squares–support vector machine (LS–SVM), and partial least squares–discriminant analysis (PLS–DA), were investigated to identify MPs in air and underwater. Combined with the underwater spectral image correction model, all classifiers achieved promising results, and SVM outperformed all the other classifiers, with average precision (PR) = 0.9839, recall (RE) = 0.9859, and F1-score (F1) = 0.9849, for the identification of six types of MPs, where F1 increased by 3.01% over the raw underwater condition. The effects of particle size, color, and shape were studied, among which a detection limit of 0.5 mm was observed and proved to be possible to extend. MP identification on the lakebed verifies the potential of underwater hyperspectral imaging for in situ underwater MP detection, which may translate to seabed detection. Microplastics (MPs) on seabed can be detected using underwater hyperspectral imageries in turbid water, with the assistance of spectral image correction. [Display omitted] •Microplastics (MPs) were identified using underwater hyperspectral imageries.•Spectral image correction could assist the in situ detection of MPs.•SVM is the most suggested classifier for MPs detection with different sizes.