Papers

4 results
|
Article Tier 2

Shapes of Hyperspectral Imaged Microplastics

This study developed a standardized classification system for the shapes of microplastics found using hyperspectral imaging, proposing nine clear categories including fiber, rod, sphere, and others. When five experts tested the system on over 11,000 microplastic particles from various environments, the categories proved well-defined and distinguishable. Better shape classification matters because particle shape affects how microplastics interact with living organisms, including how easily they can be inhaled or ingested by humans.

2023 Environmental Science & Technology 32 citations
Article Tier 2

Permeable pavements: A possible sink for tyre wear particles and other microplastics?

Researchers sampled approximately 100 kg of particulate material from seven roads and parking lots to analyze microplastic content including tire wear particles. The study found that tire wear constituted the dominant fraction of microplastics at 0.09% of dry mass, with polypropylene as the most common non-tire plastic type, and that permeable pavements may act as sinks trapping these particles before they reach waterways.

2023 The Science of The Total Environment 70 citations
Article Tier 2

Deep Learning-Based Shape Classification for Hyperspectral-Imaged Microplastics

Researchers tested nine deep learning architectures for automating the shape classification of microplastic particles in hyperspectral images, comparing performance on original and augmented datasets. The best models achieved high classification accuracy, offering a faster and more consistent alternative to labour-intensive manual identification.

2025 Analytical Chemistry
Article Tier 2

Revealing youth-perceived cultural ecosystem services for high-density urban green space management: a deep learning spatial analysis of social media photographs from central Beijing

Researchers used AI-analyzed social media photos from young people in Beijing to map which types of urban green spaces they valued most, finding that social recreation was the top benefit, followed by nature appreciation. The study shows how crowdsourced imagery and deep learning can help city planners understand where green spaces best support youth mental health in densely built environments.

2025 Landscape Ecology 4 citations