Multi-Scale Feature Attention Network for Polymer Classification using THz Dual-Comb Spectroscopy

2026-06-04

AI Summary

This study addresses the challenge of accurately identifying complex polymeric materials—such as multilayer films and blends—using conventional spectroscopic techniques. To overcome this limitation, the authors propose a Multi-Scale Feature Attention Network (MSFAN) tailored for terahertz dual-comb spectroscopy (THz-DCS). The model integrates feature gating, multi-scale parallel convolutions, cross-feature attention, and attention-based pooling to effectively extract and enhance discriminative spectral information. Evaluated on a 12-class polymer classification task, MSFAN achieves an accuracy of 85.2%, significantly outperforming existing methods. Beyond improving classification performance for intricate polymeric systems, this work also advances the interpretability of deep learning models in spectral analysis.

Abstract

Reliable polymer identification is essential for ensuring the quality and safety of recycled plastics, yet conventional sorting and spectroscopic techniques often struggle to deliver robust discrimination. Terahertz Dual-Comb Spectroscopy (THz-DCS) offers a promising alternative, providing rapid, high-resolution, and non-destructive measurements. In this work, we leverage THz-DCS to classify 12 types of polymers, including pure polymers, multilayer films, commercial blends, and biopolymers. To handle the complexity of these spectral signals, we propose the Multi-Scale Feature Attention Network (MSFAN), a novel deep learning architecture tailored for THz-DCS data. The framework integrates feature gating for signal recalibration and multi-scale parallel convolutions to capture diverse frequency patterns. These features are further refined through cross-feature attention and attention pooling, enabling the model to intrinsically highlight the most informative THz regions. MSFAN consistently outperforms state-of-the-art models, reaching a classification accuracy of 85.2%. This study demonstrates the potential of combining THz-DCS with deep learning techniques for effective, scalable, and interpretable polymer classification.

Problem

• polymer classification
• THz dual-comb spectroscopy
• recycled plastics
• spectral discrimination
• material identification

Innovation

• Multi-Scale Feature Attention Network
• Terahertz Dual-Comb Spectroscopy
• Feature Gating
• Cross-Feature Attention
• Polymer Classification