蒙古黄芪不同栽培方式的高光谱识别与分类

doi:10.3964/j.issn.1000-0593(2025)07-1842-06

Abstract
References
Related Citation (15)

Download: PDF (2255 KB)
Export: BibTeX | EndNote (RIS)

Abstract Huangqi is an important medicinal herb, specifically the dried root of either Astragalus membranaceus (Fisch.) Bge. var. Mongholicus (Bge.) Hsiao (A. mongholicus) or Astragalus membranaceus (Fisch.) Bge. Generally, simulated wild cultivation of A. mongholicus tends to result in higher active compound content compared to horizontal cultivation. However, these differences are challenging to distinguish by visual inspection alone. Traditional methods like High-Performance Liquid Chromatography (HPLC) are accurate for measuring these compounds but are costly and time-consuming. This study aims to develop a rapid, cost-effective, and accurate method to differentiate between simulated wild and horizontally cultivated A. mongholicus. Using a spectroradiometer, we measured the active compound content in ground root samples using HPLC and obtained hyperspectral reflectance data within the 350～2 500 nm wavelength range (SVC-HR1024). The study focused on the spectral characteristics in the visible (VIS, 350～700 nm), near-infrared (NIR, 700～1 100 nm), and shortwave infrared (SWIR, 1 100～2 500 nm) regions. Four machine learning models—Random Forest (RF), K-Nearest Neighbors (KNN), Naive Bayes (NB), and Support Vector Machine (SVM)—were employed for classification. An importance analysis of SHAP features was conducted on the best-performing RF model. The findings reveal that: (1) Simulated wild cultivation had significantly higher active compound content in A. mongholicus than horizontal cultivation; (2) Distinct spectral differences exist between simulated wild and horizontally cultivated A. mongholicus in the NIR and SWIR regions, indicating the impact of the diverse simulated wild environment on pigment synthesis, tissue structure, and chemical composition; (3) The RF model achieved the best performance with an accuracy, precision, F1 score, Kappa, and MCC coefficients of 97.14%, 97.42%, 0.971 3, 0.942 9, and 0.945 6, respectively; (4) SHAP analysis identified key wavelengths associated with moisture, protein, and cellulose content. This study demonstrates the effectiveness of hyperspectral reflectance in distinguishing between simulated wild and horizontally cultivated A. mongholicus samples, providing a novel, non-destructive, and rapid detection method for the quality control and identification of medicinal herbs. This approach has the potential to play a significant role in the quality assessment and market regulation of medicinal herbs.

Key words：A. mongholicus;Hyperspectral reflectance;Simulated wild cultivation;Horizontal cultivation;Machine learning;SHAP analysis

Received: 2024-09-05 Accepted: 2025-02-15

ZTFLH:

O433.4

Corresponding Authors: FAN Bo-bo, LIU Jie E-mail: fanbobo19@126.com；tunriyaoyun@126.com

Cite this article:

WU Qiang,LU Ling,FENG Xiao-juan, et al. Hyperspectral Identification and Classification of Different Cultivation Methods of A. mongholicus[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(07): 1842-1847.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2025)07-1842-06 OR https://www.gpxygpfx.com/EN/Y2025/V45/I07/1842

[1] MA Yan-chun，HU Jian-hui，WU Wen-xuan，et al（马艳春，胡建辉，吴文轩，等）. Acta Chinese Medicine and Pharmacology（中医药学报），2022，50（4）：92.
[2] Wang X M，Wang Y L，Huang D M，et al. International Immunopharmacology，2022，112：109186.
[3] Tsai C C，Wu H H，Chang C P，et al. Journal of the Formosan Medical Association，2019，118（3）：730.
[4] KANG Chuan-zhi，ZHANG Yan，WANG Sheng，et al（康传志，张燕，王升，等）. China Journal of Chinese Materia Medica（中国中药杂志），2021，46（8）：1858.
[5] LUO Yang-yang，ZHANG Xuan，ZHANG Fu-sheng，et al（雒阳阳，张璇，张福生，等）. China Journal of Chinese Materia Medica（中国中药杂志），2022，47（13）：3463.
[6] WANG Zong-quan，HUANG Chao-qing，HUANG Zhi-hui，et al（王宗权，黄朝情，黄志辉，等）. Chinese Journal of Pharmaceutical Analysis（药物分析杂志），2021，41（7）：1148.
[7] LIU Jie，GUO Jia-hua，ZHAO Peng，et al（刘杰，郭嘉华，赵鹏，等）. Northern Horticulture（北方园艺），2024，（2）：100.
[8] FEI Shuai-peng，YU Xiao-long，LAN Ming，et al（费帅鹏，禹小龙，兰铭，等）. Scientia Agricultura Sinica（中国农业科学），2021，54（16）：3417.
[9] WANG He，LIU Shi-yu，WANG Hui，et al（王翯，刘诗雨，王慧，等）. China Journal of Chinese Materia Medica（中国中药杂志），2023，48（16）：4320.
[10] LI Meng，ZHANG Xiao-bo，LIU Shao-bo，et al（李梦，张小波，刘绍波，等）. Spectroscopy and Spectral Analysis（光谱学与光谱分析），2022，42（4）：1217.
[11] Zhou W，Yan Z X，Zhang L T. Scientific Reports，2024，14（1）：5905.
[12] ZHAO Gui-ping，WU Jie，CHEN Jia-ying，et al（赵贵萍，邬洁，陈佳颖，等）. Chinese Journal of Experimental Traditional Medical Formulae（中国实验方剂学杂志），2022，28（22）：239.
[13] National Pharmacopoeia Committee（国家药典委员会）. Pharmacopoeia of the People's Republic of China（中华人民共和国药典）. Beijing：China Medical Science and Technology Press（北京：中国医药科技出版社），2020.
[14] Wu Q，Zhang Y P，Zhao Z W，et al. Agronomy，2023，13（1）：211.
[15] GUO Lan-ping，ZHOU Liang-yun，KANG Chuan-zhi，et al（郭兰萍，周良云，康传志，等）. China Journal of Chinese Materia Medica（中国中药杂志），2020，45（9）：1969.
[16] Cozzolino D. Plant Medica, 2009, 75(7): 746.
[17] Yang L，Wen K S，Ruan X，et al. Molecules，2018，23（4）：762.
[18] Belgiu M，Drǎguţ L. ISPRS Journal of Photogrammetry and Remote Sensing，2016，114：24.
[19] Mountrakis G，Im J，Ogole C. ISPRS Journal of Photogrammetry and Remote Sensing，2011，66（3）：247.
[20] Liu P，Zhang H，Eom K B. IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing，2018，10（2）：712.
[21] Kokaly R F. Remote Sensing of Environment，2001，75（2）：153.
[22] Blackburn G A. Journal of Experimental Botany，2007，58（4）：855.
[23] Wu Z Z，Xu E B，Long J，et al. Food Control，2015，50：405.
[24] MEI Guang-yuan，LI Rong，MEI Xin，et al（梅广源，李荣，梅新，等）. Scientia Agricultura Sinica（中国农业科学），2024，57（3）：484.
[25] Li S Y，Yuan W，Deng G B，et al. Pharmaceutical Crops，2011，2（1）：28.