Authors

Abstract

The detection of pesticide residues in white tea fresh leaves is an important step to ensure the quality safety of white tea finished products. Traditional detection methods are costly and inefficient to realize the demand for fast, low-cost, and accurate detection of pesticide residues in white tea fresh leaves. In this study, five types of white tea fresh leaf pesticide residue sample data were obtained using hyperspectral imaging technology for the high-frequency detected pesticides Glyphosate and Bifenthrin, and the SVM and 1D-CNN models were established to detect the samples after noise reduction processing and feature band screening methods. The study shows that the 1D-CNN model has better feature extraction ability, in which the SG-CARS-1D-CNN model has the highest detection accuracy, which is 94.62%, 95.12%, 94.35%, 94.95%, and 95.27% for the five type of species samples, respectively. This study provides pesticide residue detection for white tea fresh leaves based on the combination of hyperspectral data and an artificial intelligence model, which provides an intelligent, nondestructive, efficient, and high-precision pesticide residue detection model for white tea fresh leaves.

Abstract in Chinese

白茶鲜叶农药残留检测是保证白茶成品茶质量安全的重要环节。传统检测方法成本高、效率低，为了实现对白茶鲜叶农药残留的快捷、低成本、准确的检测需求。本研究针对高频次被检出农药草甘膦和联苯菊酯,利用高光谱成像技术获得5类白茶鲜叶农药残留样本数据，经过降噪处理和特征波段筛选方法，建立支持向量机（SVM）和一维卷积神经网络模型（1D-CNN）对样本进行检测。研究表明，1D-CNN模型具有更好的特征提取能力，其中SG-CARS-1D-CNN模型的检测精度最高，对5类种样本检测精度分别为94.62%、95.12%、94.35%、94.95%和95.27%。本研究提供了一种基于高光谱数据与人工智能模型相结合的白茶鲜叶农药残留检测手段，为白茶鲜叶提供一种智能、无损、高效、高精度的农药残留检测模型。