We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Application of a modified set of GoogLeNet and ResNet-18 convolutional neural networks towards the identification of environmentally derived-MPLs in the Yadkin-pee dee river basin
Summary
Transfer learning applied to GoogLeNet and ResNet-18 convolutional neural networks achieved over 90% accuracy in identifying environmentally derived microplastics from Raman spectroscopy images collected in the Yadkin-Pee Dee River Basin.
Microplastic (MPL) abundance is a well-elucidated problem in the marine environment but not so much in the terrestrial environment. In order to contribute to this research gap, a field study was performed in the Yadkin-Pee Dee River Basin. Due to their heterogenous nature and difficulty in characterization, a diverse set of pictorial training data from µ-Raman was used to perform transfer learning on 2 CNNs of interest: GoogLeNet (GN) and ResNet-18 (RN). In the first trial, using 10% of the initial training dataset, the CNNs exhibited high levels of accuracy rates, generally above 90%. Irrespective of spectroscopic mode, marginal improvements in accuracy rates were seen, with the best improvements occurring in the Raman-based models (U[GN(FTIR), RN(Raman), GN(FTIR), and RN(Raman)]: 39, 42, 38.5, and 34.5; p-value: 1, .6753, .9719, and .4978). However, for the external trial, pictorial data from Primpke (FTIR) and DongMiller (Raman) was predicted less accurately, with the largest loss occurring across the following sets: U[GN(Raman) and RN(FTIR)], 45.5 and 35; p-value:, .3268 and .5476. However, set RN fared marginally better, and due to the usage of µ-Raman, and its performance in the 10% trial, RN18_ADAM_.0011 was selected as the champion model for the field study data. In the unknown microparticle (MP) trial, generally, the most ID’d polymer type was CA, PET, and PE representing a relative concentration range for a given water source and area (MPL/MP) of 4.17–37.5%, 4.17–8.33%, and 4.17–8.33% for CNN and OpenSpecy (OS). A FEDS algorithm, equipped with natural and synthetic polymer standards and biological material, used to compare the strength of each model determined similar frequency in ascertaining positive MPL results across both models with corroboration between the CNN and OS around 1/3 of the time. Results indicate the models detect MPLs with similar frequency elucidating comparable strength of the CNN as well as a focus on particle type distribution rather than individual identification. Moreover, the largest influential factor in this study appears to be either laundry wastewater effluent or atmospheric deposition, which is stressed as a primary focus of remediating MPLs in similar freshwater environments. Lastly, it appears that these MPL are of primary origin as opposed to secondary in the oceanic and coastal environments.
Sign in to start a discussion.
More Papers Like This
Quantitative analysis of microplastics in water environments based on Raman spectroscopy and convolutional neural network
Researchers developed a method combining Raman spectroscopy with a convolutional neural network to measure microplastic concentrations in water. The approach achieved high accuracy across six different sizes of polyethylene particles in five real-world water environments, outperforming other machine learning models and offering a practical tool for quantitative microplastic monitoring.
Detection of Microplastics in Freshwater Sediments Based on Raman Spectroscopy and Convolutional Neural Networks
Researchers developed a method combining Raman spectroscopy and convolutional neural networks to detect and classify microplastics in complex freshwater sediment samples, training the CNN on mixed spectra from extracted sediment fractions to improve detection accuracy.
Identification of microplastics using a convolutional neural network based on micro-Raman spectroscopy
Researchers combined micro-Raman spectroscopy with a neural network to identify microplastics, achieving over 99% accuracy across 10 different plastic types. The system was also tested on real environmental samples and performed well at classifying unknown particles. This AI-powered approach could make microplastic identification faster and more reliable for environmental monitoring.
Raman Spectroscopy Enhanced By Machine Learning For Effective Microplastic Detection In Aquatic Systems
Researchers explored combining Raman spectroscopy with machine learning techniques to improve microplastic detection and classification in aquatic systems. The study found that deep learning models, particularly convolutional neural networks, achieved high classification accuracy and significantly reduced reliance on labor-intensive manual spectral analysis for real-time environmental monitoring.
GoogLeNet-Based Deep Learning Framework for Underwater Microplastic Classification in Marine Environments
Researchers trained a GoogLeNet deep learning model on underwater images to classify microplastics into four categories, achieving strong classification performance for primary microplastics, secondary microplastics, non-microplastic debris, and marine biota in turbid coastal waters.