采用高光谱成像（HSI）和核磁共振（NMR）技术结合深度学习对枸杞的地理来源和

摘要：枸杞因其营养和药用价值而享誉全球。由于枸杞的营养成分、药效及市场价格因产地不同而存在显著差异，快速 准确地鉴别其地理来源至关重要。本研究提出了一种创新方法，结合高光谱成像（（HSI）、核磁共振（（NMR）和改进的ResNet- 34深度学习模型，以精准识别枸杞的地理来源和地理标志（（ GI）特征。该深度学习模型的准确率达到95.63%，较传统方 法提高了6.26%，并通过基于SHapley加性解释（SHAP）的特征选择将运行时间缩短了29.9%。通过GI特征与HSI特 征波长的Pearson相关性分析，增强了HSI数据的可解释性，并进一步将运行时间减少了33.99%。本研究为便携式多光 谱设备的开发奠定了基础，为枸杞产品的质量保证和市场监管提供了一种快速、准确且经济高效的解决方案。

关键词：相关性分析；深度学习；产地溯源；高光谱成像；宁夏枸杞；核磁共振

期刊：Food Chemistry

DOI：https://doi.org/10.1016/j.foodchem.2024.140903

设备：GaiaField

The combination of HSI and NMR techniques with deep learning for identiffcation of geographical origin and GI markers of Lycium barbarum L.

Abstract：Lycium barbarum L. (L. barbarum) is renowned worldwide for its nutritional and medicinal beneffts. Rapid and accurate identiffcation of L. barbarum's geographic origin is essential because its nutritional content, medicinal efffcacy, and market price signiffcantly vary by region. This study proposes an innovative method combining hyperspectral imaging (HSI), nuclear magnetic resonance (NMR), and an improved ResNet-34 deep learning model to accurately identify the geographical origin and geographical indication (GI) markers of L. barbarum. The deep learning model achieved a 95.63% accuracy, surpassed traditional methods by 6.26% and reduced runtime by 29.9% through SHapley Additive exPlanations (SHAP)-based feature selection. Pearson correlation analysis between GI markers and HSI characteristic wavelengths enhanced the interpretability of HSI data and further reduced runtime by 33.99%. This work lays the foundation for portable multispectral devices, offering a rapid, accurate, and cost-effective solution for quality assurance and market regulation of L. barbarum products.

Keywords：Correlation analysis; Deep learning; Geographical origin identiffcation; Hyperspectral imaging; Lycium barbarum L.; Nuclear magnetic resonance