We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Polymer bead size revealed via neural network analysis of single-entity electrochemical data
Summary
A neural network was trained to extract microplastic particle size from electrochemical current-spike data recorded when individual polymer beads collide with a microelectrode — a method that avoids the need for optical microscopy. Accurate near-real-time sizing of microplastics in solution is an important analytical advance for water quality monitoring, where detecting and characterizing small plastic particles quickly and affordably remains a major technical challenge.
Single-entity electrochemistry methods for detecting polymer microbeads offer a promising approach to analyzing microplastics. However, conventional methods for determining microparticle size face challenges due to non-uniform current distribution across the surface of a sensing disk microelectrode. In this study, we demonstrate the utility of neural network (NN) analysis for extracting the size information from single-entity electrochemical data (current steps). We developed fully connected regression NN models capable of predicting microparticle radii based on experimental parameters and current-time data. Once trained, the models provide near-real-time predictions with good accuracy for microparticles of the same size, as well as the average size of two different-sized microparticles in solution. Potential future applications include analyzing various bioparticles, such as viruses and bacteria of different sizes and shapes.
Sign in to start a discussion.
More Papers Like This
Approaches to Detect Microplastics in Water Using Electrical Impedance Measurements and Support Vector Machines
Researchers developed an electrical impedance spectroscopy method enhanced with machine learning to detect microplastics in water, achieving over 98% classification accuracy for stationary samples and over 85% for dynamic flow measurements across different plastic materials and particle sizes.
Microplastics detection by impact electrochemistry
This paper explores impact electrochemistry—a technique where individual particles colliding with an electrode generate detectable electrical pulses—as a method for detecting and characterizing microplastics in water. The approach offers the potential for rapid, single-particle detection without the need for complex sample preparation or optical instruments, which could make microplastic monitoring cheaper and more accessible. Developing faster and simpler detection methods is important for scaling up environmental monitoring programs.
Electrochemical Detection of Microplastics in Water Using Ultramicroelectrodes
Researchers developed a new electrochemical method for detecting microplastics in water using ultramicroelectrodes. The technique works by monitoring changes in electrical current when microplastic particles collide with and adsorb onto the electrode surface, and the size distributions obtained closely matched independent measurements, demonstrating its potential as a practical detection tool.
In situ Detection of Microplastics: Single Microparticle‐electrode Impacts
This study developed an electrochemical method using particle-impact techniques to detect and size individual polyethylene microparticles in water solution. The novel analytical approach enables detection of microplastics in aqueous samples in situ, without the need for filtration or sample processing that could introduce contamination.
Microplastic Identification Using Impedance Spectroscopy and Machine Learning Algorithms
Scientists developed a new method to detect and classify microplastics in water using electrical measurements and machine learning. The system can identify different sizes of PET microplastic particles with high accuracy, offering a potential tool for real-time water quality monitoring. Better detection methods like this are important for understanding how much microplastic contamination exists in drinking water and other water sources.