A multimodal learning system based on maximum variance convolutional neural networks and laser-induced breakdown spectroscopy for in situ online analysis of heavy metal contamination from atmospheric polyamide microplastics

Advanced Microplastic Identification in Marine Environments via Hybrid Deep Learning

AI summary · Read the abstract

Researchers propose a hybrid deep learning architecture combining 3D convolutional neural networks and Vision Transformers applied to hyperspectral imagery to detect and classify microplastics in turbid marine environments, capturing both local spectral signatures and global contextual patterns that single-model approaches miss.

Deep Learning Approaches for Microplastic Identification in Microscopic Water Samples

Harnessing Artificial Intelligence for the Detection and Analysis of Microplastics and Associated Chemicals in the Atmosphere

AI summary · Read the abstract

Researchers reviewed how artificial intelligence can improve detection and analysis of atmospheric microplastics, which travel long distances and pose unavoidable human exposure risks. AI-based tools offer promising advances in identifying plastic particles and associated chemical contaminants across diverse environmental matrices.

Laser induced fluorescence and machine learning: a novel approach to microplastic identification

AI summary · Read the abstract

Researchers combined laser-induced fluorescence with machine learning to identify microplastics in water in real time, achieving 97.6% accuracy in distinguishing plastics from other organic matter and 88.3% accuracy in identifying specific plastic types — a promising step toward automated ocean monitoring.

A Novel Approach for Fast Microplastic Quantification in Sediments Using Machine Learning—Spectrometer Combinations

AI summary · Read the abstract

Researchers combined visible near-infrared and FTIR spectroscopy with machine learning models (SVR, PLSR, BPNN) to rapidly estimate concentrations of PE, PP, PS, and PVC microplastics in river and loess sediments without extraction or manual counting. Faster, non-destructive quantification methods are crucial for scaling up microplastic monitoring across diverse environmental matrices and enabling consistent cross-study comparisons of pollution levels.