We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Faster Calculations of Optical Trapping Using Neural Networks Trained by T-Matrix Data: An Application to Micro- and Nanoplastics
AI summary Read the abstract
Researchers developed a neural network approach to speed up calculations of how laser beams interact with micro- and nanoplastic particles, a technique relevant to detecting and trapping these pollutants. The method trains on a small set of precise physics-based calculations and then accurately predicts results across a much wider range of particle sizes and properties. This computational tool could make it faster and cheaper to study microplastics using optical detection methods.
We employ neural networks to improve and speed up optical force calculations for dielectric particles. The network is first trained on a limited set of data obtained through accurate light scattering calculations, based on the transition matrix (T-matrix) method, and then is used to explore a wider range of particle dimensions, refractive indices, and excitation wavelengths. This computational approach is very general and flexible. Here, we focus on its application in the context of micro- and nanoplastics, a topic of growing interest in the past decade due to their widespread presence in the environment and potential impact on human health and the ecosystem.
More Papers Like This
Identifying Multicomponent Microplastics in Complex Matrices Using a Fast Fourier Convolutional Neural Network with Hierarchical Feature Mapping
AI summary Read the abstract
Scientists developed a smart computer program that uses laser light to quickly identify different types of microplastics, even when they're mixed together with other materials in real-world samples like soil or water. This matters because knowing exactly which plastics are contaminating our environment is a key step toward understanding how we're exposed to them through food, water, and air—and this tool made accurate identifications 100% of the time in environmental samples tested, making pollution tracking faster and more reliable.
Field-enhancement calculations in plasmonic tagged nanoplastics improved by machine learning
AI summary Read the abstract
Researchers used computer modeling and machine learning to predict how tiny metal particles attached to nanoplastics enhance light signals, a method used to detect plastic particles. The combined approach let them test many combinations of plastic and metal particle sizes and materials faster than standard calculations, aiming to help improve detection techniques.
Trapping and chemical characterization of sub-microplastics using Raman optical tweezers with machine learning
AI summary Read the abstract
Researchers combined optical tweezers Raman spectroscopy with machine learning-driven PCA to identify and classify individual sub-micron plastic particles (PE, PP, PS) from environmental matrices. By analyzing 35 Raman spectra, the platform demonstrated accurate single-particle identification without complex sample preparation.
Rapid identification of microplastic particles in water using geometric polarization characterization and quantum neural networks
AI summary Read the abstract
Scientists have developed a fast, AI-powered method to detect microplastics in water by analyzing how light bends and scatters off tiny plastic particles, achieving about 95% accuracy in under 12 milliseconds per sample. This matters because microplastics are increasingly found in drinking water and their health effects are still being studied — faster, more reliable detection tools could help researchers and water treatment facilities monitor contamination more effectively, which is a key step toward better understanding and reducing our exposure to these particles.
Rapid Mass Conversion for Environmental Microplastics of Diverse Shapes
AI summary Read the abstract
Researchers developed a faster and more accurate method for converting microplastic counts into mass estimates, which is critical for calculating how much plastic rivers carry to the ocean. Using deep learning to classify microplastic shapes and a new approach to estimating thickness, the models reduced estimation errors by sevenfold compared to previous methods while saving about two hours per hundred particles analyzed.
Research digests by email
When a large batch of papers lands in the Atlas, we read through it and send a short write-up of what stood out.