返回列表
高光谱成像技术结合堆叠机器学习模型测定高粱中马拉硫磷含量
农业监测
2026/09/21
摘要：农药残留的快速、精确检测仍然是食品工业中一个紧迫的安全问题。本研究将高光谱成像技术与叠加集成学习模 型相结合，建立了一种快速分析高粱中农药残留的方法。使用多元散射校正（MSC）算法对 HSI 光谱数据进行预处理。 采用梯度提升决策树（GBDT）、极端梯度提升（XGBoost）、光梯度提升机（LGBM）和分类提升（CatBoost）算法识别 对预测模型贡献大的特征波长，比较 SEL、GBDT、XGBoost、LGBM 和 CatBoost 算法对高粱样品农药残留的准确预测 性能。采用CatBoost选取的特征波长构建的SEL模型预测效果最好，RMSEP、R 2和RPD值分别为0.6940 mg/kg、0.9798 P 和 7.029。该研究表明，HSI 和 SEL 的结合能够准确分析高粱中的农药残留，为利用 HSI 方法准确测定高粱等食品中的 农药残留浓度提供了参考。
关键词：农药残留；高粱；高光谱成像；堆叠集合学习
期刊：Journal of Food Composition and Analysis
DOI：https://doi.org/10.1016/j.jfca.2024.106635
设备：GaiaField
Determination of malathion content in sorghum grains using hyperspectral imaging technology combined with stacked machine learning models
Abstract：The rapid and precise detection of pesticide residues remains a pressing safety issue in the food industry. In this study, a rapid method for analyzing pesticide residues in sorghum was developed, combining hyperspectral imaging (HSI) technology with stacking ensemble learning (SEL) models. The HSI spectral data were pre processed using the multivariate scatter correction (MSC) algorithm. The gradient boosting decision tree (GBDT), extreme gradient boosting (XGBoost), light gradient boosting machine (LGBM), and categorical boosting (Cat Boost) algorithms were employed to identify the feature wavelengths with high contributions to the predictive model, and the performances of SEL, GBDT, XGBoost, LGBM, and CatBoost to accurately predict the pesticide residues in sorghum samples were compared. The SEL model constructed using the characteristic wavelength selected by CatBoost has the best predictive performance, with RMSE , R 2, and RPD values of 0.6940 mg/kg, 0.9798, and 7.029, P P respectively. The study demonstrated that the combination of HSI and SEL enabled the ac curate analysis of pesticide residues in sorghum, providing a reference for the utilization of HSI methods to accurately measure the concentrations of pesticide residues in sorghum and other food products.
Keywords：Pesticide residues, Sorghum, Hyperspectral imaging, Stacking ensemble learning
