We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Study on marine microplastics monitoring based on infrared spectroscopy technology
Summary
Researchers developed an infrared spectroscopy-based monitoring system for marine microplastics, applying support vector machine algorithms to hyperspectral images to identify plastic types and abundances in seawater. The study found microplastic abundances ranging from roughly 5 to 39 particles per litre across sampling sites, with fibers (53-68%) and debris (23-34%) as dominant shapes, demonstrating the method's feasibility for rapid environmental monitoring.
In recent years, microplastics particles have been detected in many sea areas around the world. Microplastics has done great harm to marine and terrestrial seawater ecosystems, so it is necessary to obtain the effective statistical data of microplastics in the environment accurately and quickly for the further study of pollution in microplastics. In this paper, based on IR (Infrared Spectroscopy) technology, hyperspectral images of marine microplastics samples containing different materials were obtained. SVM (Support Vector Machine) algorithm is used to identify microplastics in hyperspectral images. The results show that the microplastics abundance ranges from 5.193 to 20.281 N/L, 6.087 to 38.679 N/L and 7.498 to 11.084 N/L, respectively, and the average abundance is 11.83 N/L, 24.84 N/L and 19.27 N/L, respectively. The types of microplastics in the bottom water of the bay in the study area are mainly fibers (53–68%) and debris (23–34%). NIR (Near Infrared) analysis shows that the characteristic curves of microplastics spectra of the same species with different particle sizes are different. IR technology combined with chemometrics algorithm has great potential for the detection of microplastics in seawater surface and seawater. This method is simple and feasible, and has the feasibility of popularization.
Sign in to start a discussion.
More Papers Like This
Training and evaluating machine learning algorithms for ocean microplastics classification through vibrational spectroscopy
Researchers evaluated multiple machine learning algorithms for automatically classifying ocean microplastics using infrared spectroscopy data across 13 polymer types. The study found that Support Vector Machine classifiers provided the best balance of simplicity and accuracy, offering a practical tool for faster and more reliable identification of microplastic contaminants.
Development of robust models for rapid classification of microplastic polymer types based on near infrared hyperspectral images
Researchers used near-infrared hyperspectral imaging combined with machine learning to classify nine types of microplastic particles, finding reliable results even for small particles on wet filters. This method could enable faster, automated identification of diverse microplastic types in environmental water samples.
An effective strategy for the monitoring of microplastics in complex aquatic matrices: Exploiting the potential of near infrared hyperspectral imaging (NIR-HSI)
Researchers developed a near infrared hyperspectral imaging (NIR-HSI) method for rapid monitoring of microplastics in complex marine matrices, demonstrating effective detection and polymer identification that overcomes the time and cost limitations of conventional spectroscopic analysis approaches.
Rapid shipboard measurement of net-collected marine microplastic polymer types using near-infrared hyperspectral imaging
Researchers developed a rapid near-infrared hyperspectral imaging method for identifying polymer types in ship-collected marine microplastic samples, achieving results in minutes compared to hours for conventional methods and enabling higher-throughput ocean monitoring.
Spectrometric Detection Of Microplastics In The Environment: A Novel Approach Using Hyperspectral Imaging System
This study developed a novel spectrometric approach to detect microplastics in environmental samples, combining spectral analysis with machine learning classification. The method enabled rapid, accurate identification of multiple polymer types without extensive sample preparation.