We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Hyperspectral detection of soil microplastics via multimodal feature fusion and a dual-path attention residual convolutional network
Summary
A hyperspectral imaging approach combined with multimodal deep learning was developed to detect microplastics in soil, achieving high accuracy in identifying plastic particles against complex soil backgrounds. The method offers a faster, less destructive alternative to traditional chemical extraction and spectroscopy for soil monitoring.
Rapid and precise detection of soil microplastics is crucial for environmental risk assessment but is challenged by complex matrices and low concentrations. To overcome the limitations of single-modal analysis, we developed a novel multimodal hyperspectral framework. This method integrates features from both one-dimensional (1D) spectral data and their two-dimensional (2D) image representations using a Multi-view Probabilistic Feature Fusion (MPFF) strategy, followed by classification with a Dual-path Attention Residual Convolutional Network (DAR-CNN). The integrated model achieved a classification accuracy of 96.75 %, outperforming conventional models. Notably, the framework maintained robust performance even at a low concentration of 0.5 %. This work provides an effective framework for monitoring soil microplastics and advances the application of multimodal information fusion in hyperspectral analysis.
Sign in to start a discussion.
More Papers Like This
Application of hyperspectral and deep learning in farmland soil microplastic detection
Hyperspectral imaging combined with deep learning was applied to detect and classify microplastics in farmland soil, offering a non-destructive, rapid alternative to time-consuming chemical extraction methods. The model achieved high classification accuracy across polymer types, demonstrating the potential for field-deployable microplastic monitoring in agricultural settings.
Application of hyperspectral imaging technology in the rapid identification of microplastics in farmland soil
Researchers applied hyperspectral imaging technology combined with machine learning to rapidly screen and classify microplastics in farmland soil samples, demonstrating an efficient non-destructive identification method for soil microplastic contamination.
Coupling hyperspectral imaging with machine learning algorithms for detecting polyethylene (PE) and polyamide (PA) in soils.
Researchers combined hyperspectral imaging with machine learning algorithms to detect polyethylene and polyamide microplastics in soil samples. This rapid detection approach could support large-scale soil monitoring for microplastic contamination, which is important given that agricultural soils may accumulate plastics from mulch films, irrigation water, and sewage sludge.
Accurate detection of low concentrations of microplastics in soils via short-wave infrared hyperspectral imaging
Researchers combined short-wave infrared hyperspectral imaging with machine learning algorithms to detect low concentrations of polyamide and polyethylene microplastics in soil samples, achieving accurate classification with implications for fast, non-destructive screening of agricultural land for plastic contamination.
Study on detection method of microplastics in farmland soil based on hyperspectral imaging technology
Researchers developed a method using hyperspectral imaging and machine learning to rapidly detect and classify different types of microplastics in farmland soil. The technology achieved high accuracy in identifying common plastic types like polyethylene and polypropylene in soil samples. Better detection tools like this are essential for monitoring microplastic contamination in agricultural land and understanding its potential impact on food safety.