We can't find the internet
Attempting to reconnect
Something went wrong!
Hang in there while we get back on track
Recognition of microplastic aging features based on multimodal data fusion and attention mechanisms
Summary
Researchers developed a deep learning model integrating SEM images and FT-IR spectral data via multimodal fusion and attention mechanisms to recognize aging features in 1,371 microplastic samples across seven aging types, achieving 96.4% validation accuracy compared to 85.3% for image-only and 47.8% for spectroscopy-only models.
Microplastics undergo complex physicochemical changes during aging, which traditional single-modality methods struggle to explain. We analyzed 1371 samples across seven aging types using a deep learning model integrating SEM images and FT-IR data via multimodal fusion and attention mechanisms. The model achieved 96.4 % validation accuracy, surpassing single-image (85.3 %) and single-spectroscopy (47.8 %) models. Attention mechanisms highlighted key features: chemical aging linked the CO peak (1700-1750 cm⁻¹) to surface etching; UV aging associated the O-H peak (3300-3500 cm⁻¹) with dense cracks; physical aging connected CC vibrations (1650-1680 cm⁻¹) to wear marks. The model performed robustly on complex aging samples, achieving an 80.9 % dual-attribution success rate in UV scenarios. It identified UV degradation as the primary factor in natural aging (78.6 % frequency) and indicated potential chemical degradation risks in paddy fields. Joint features were visualized via t-SNE and validated using Mahalanobis distance-based metric learning. This approach enhances our understanding of microplastic aging mechanisms and provides a foundation for linking laboratory observations with natural environmental conditions, supporting the development of methods for lifecycle management and ecological risk assessment of microplastics.
Sign in to start a discussion.
More Papers Like This
Tracing Microplastic Aging Processes Using Multimodal Deep Learning: A Predictive Model for Enhanced Traceability
Researchers developed a multimodal deep learning model that combines surface imaging and infrared spectroscopy data to trace the aging history of microplastics. The model achieved 93% accuracy in predicting the major aging factors that weathered the particles, outperforming single-data approaches by 5 to 20%. When applied to naturally aged microplastics from real environments, the predictions aligned with known environmental conditions, offering a new tool for environmental risk assessment.
Hybrid deep learning framework for environmental microplastic classification: Integrating CNN-based spectral feature extraction and transformer models
Researchers developed a hybrid deep learning framework combining convolutional and attention-based architectures to classify environmental microplastics from FTIR spectra, achieving improved accuracy on weathered and contaminated samples that challenge conventional spectral library approaches.
Deep convolutional neural networks for aged microplastics identification by Fourier transform infrared spectra classification
This study developed a deep learning model using convolutional neural networks to automatically identify aged microplastics from their infrared spectra. Aging changes the chemical signature of plastics, making them harder to identify with conventional spectral databases. The AI approach achieved high accuracy and could significantly speed up the analysis of environmental samples where weathered microplastics are the norm.
Optimized recognition of microplastic ATR-FTIR spectra with deep learning
Researchers developed an optimized deep learning method for identifying microplastics from ATR-FTIR spectra, improving classification accuracy for weathered and environmentally contaminated MP samples that challenge standard spectral library matching approaches.
A New Chemometric Approach for Automatic Identification of Microplastics from Environmental Compartments Based on FT-IR Spectroscopy
Researchers developed a new chemometric approach for automatic identification of microplastics from environmental samples, designed to handle the challenges of biofilm contamination and surface aging that typically impede standard spectroscopic characterisation methods.