Microplastic abundance quantification via a computer-vision-based chemometrics-assisted approach

How natural and anthropogenic factors should drive microplastic behavior and fate: The scenario of Brazilian urban freshwater

Brazil maintains its position at the top of the global ranking of plastic producers, yet recycling efforts have been incipient. Recent data reveals an annual production of approximately 14 million tons of plastic waste, not accounting for the surge in the usage of plastic masks and related materials due to the COVID-19 pandemic. However, what remains largely unreported is that over half of post-consumer plastic packaging in Brazil is managed without any monitoring, and it remains unclear how this will contribute to the occurrence of plastic waste and microplastics in Brazilian freshwaters. This scenario requires the consideration of several other crucial factors. Studies have been carried out mainly in marine and estuarine waters, while data on freshwaters are lacking. Brazil has continental dimensions and the highest water availability on the planet, yet the demand for water is greatest in regions with medium to low supply. Many densely populated Brazilian urban areas face chronic flood problems, possess inadequate levels of wastewater treatment, and display inadequate solid waste management practices. Consequently, urban freshwater with tropical characteristics in Brazil presents an intriguing scenario and is complementary to the most commonly studied marine environments. In this study, we explore the nuances of pollution in Brazilian urban freshwater and discuss how various parameters, such as organic matter, suspended solids, temperature, and pH, among others, influence the behavior of microplastics and their interactions with organic and inorganic contaminants. Furthermore, we address how microplastic conditions, such as biofouling, the type of plastic, or degradation level, may impact their behavior. By analyzing how these conditions change, we propose priority themes for investigating the occurrence of microplastics in Brazilian urban freshwater systems under different degrees of human impact. Ultimately, this study aims to establish a network dedicated to standardized monitoring of microplastic pollution in Brazilian urban freshwaters.

Deep learning based approach for automated characterization of large marine microplastic particles

The rapidly growing concern of marine microplastic pollution has drawn attentions globally. Microplastic particles are normally subjected to visual characterization prior to more sophisticated chemical analyses. However, the misidentification rate of current visual inspection approaches remains high. This study proposed a state-of-the-art deep learning-based approach, Mask R-CNN, to locate, classify, and segment large marine microplastic particles with various shapes (fiber, fragment, pellet, and rod). A microplastic dataset including 3000 images was established to train and validate this Mask R-CNN algorithm, which was backboned by a Resnet 101 architecture and could be tuned in less than 8 h. The fully trained Mask R-CNN algorithm was compared with U-Net in characterizing microplastics against various backgrounds. The results showed that the algorithm could achieve Precision = 93.30%, Recall = 95.40%, F1 score = 94.34%, AP^bb (Average precision of bounding box) = 92.7%, and AP^m (Average precision of mask) = 82.6% in a 250 images test dataset. The algorithm could also achieve a processing speed of 12.5 FPS. The results obtained in this study implied that the Mask R-CNN algorithm is a promising microplastic characterization method that can be potentially used in the future for large-scale surveys.