Rapid Machine Learning-Driven Detection of Pesticides and Dyes Using Raman Spectroscopy

2025-11-15

AI Summary

Raman spectroscopy for pesticide and synthetic dye residue detection suffers from fluorescence interference, high noise levels, and severe peak overlap, leading to low identification accuracy. To address these challenges, this paper proposes MLRaman, a multimodal analytical framework integrating ResNet-18 for deep spectral feature extraction, coupled with an XGBoost–SVM hybrid classifier; class separability is rigorously validated using PCA, t-SNE, and UMAP. Furthermore, a real-time spectral prediction system is developed using Streamlit. Evaluated on multi-class pesticide–dye mixtures, the CNN-XGBoost model achieves 97.4% classification accuracy and an AUC of 1.0. It demonstrates robust generalization on both independent experimental datasets and publicly available literature spectra. The framework significantly enhances model generalizability and deployment feasibility, establishing a highly robust, end-to-end intelligent detection paradigm for food safety and environmental monitoring.

Technology Category

• Intelligent Robots: Multimodal Perception & Sensor Fusion
• Machine Learning: Multimodal Learning
• Computer Vision: Multi-modal Vision

Application Category

• Search and Retrieval-Augmented AI: Retrieval-Augmented Generation (RAG) and multi-modal RAG
• Systems and Infrastructure for Web, Mobile and WoT: Applied ML and AI for Web-based mobile applications
• Responsible Web: Machine-in-the-loop, human agency and autonomy

Abstract

The extensive use of pesticides and synthetic dyes poses critical threats to food safety, human health, and environmental sustainability, necessitating rapid and reliable detection methods. Raman spectroscopy offers molecularly specific fingerprints but suffers from spectral noise, fluorescence background, and band overlap, limiting its real-world applicability. Here, we propose a deep learning framework based on ResNet-18 feature extraction, combined with advanced classifiers, including XGBoost, SVM, and their hybrid integration, to detect pesticides and dyes from Raman spectroscopy, called MLRaman. The MLRaman with the CNN-XGBoost model achieved a predictive accuracy of 97.4% and a perfect AUC of 1.0, while it with the CNN-SVM model provided competitive results with robust class-wise discrimination. Dimensionality reduction analyses (PCA, t-SNE, UMAP) confirmed the separability of Raman embeddings across 10 analytes, including 7 pesticides and 3 dyes. Finally, we developed a user-friendly Streamlit application for real-time prediction, which successfully identified unseen Raman spectra from our independent experiments and also literature sources, underscoring strong generalization capacity. This study establishes a scalable, practical MLRaman model for multi-residue contaminant monitoring, with significant potential for deployment in food safety and environmental surveillance.

Problem

• Detecting pesticides and dyes rapidly using Raman spectroscopy
• Overcoming spectral noise and fluorescence in Raman data
• Developing a deep learning model for accurate contaminant identification

Innovation

• Deep learning framework with ResNet-18 feature extraction
• Hybrid CNN-XGBoost model achieving 97.4% accuracy
• User-friendly Streamlit application for real-time prediction