文献类型: 外文期刊
作者: He, Gang 1 ; Yang, Shao-bing 1 ; Wang, Yuan-zhong 1 ;
作者机构: 1.Yunnan Acad Agr Sci, Med Plants Res Inst, Kunming 650200, Peoples R China
2.Yunnan Agr Univ, Coll Food Sci & Technol, Kunming 650201, Peoples R China
关键词: Medicinal plant; FT-NIR spectroscopy; Machine learning; Suitable habitats; Origin identification
期刊名称:COMPUTERS AND ELECTRONICS IN AGRICULTURE ( 影响因子:7.7; 五年影响因子:8.4 )
ISSN: 0168-1699
年卷期: 2024 年 223 卷
页码:
收录情况: SCI
摘要: Lanxangia tsao-ko (Crevost & Lemarie) M.F.Newman & Skornick ( L. tsao-ko ) is widely cultivated for its important medicinal and economic values. However, there is a lack of regional planning studies, ecological suitability studies, and incomplete species distribution surveys. In this study, the maximum entropy model was used to simulate the species distribution of L. tsao-ko under current climatic scenarios. On this basis, Fourier transform near infrared (FT-NIR) spectroscopy combined with chemometrics and deep learning was further employed to comprehensively assess the geographical origin of L. tsao-ko . The results showed that under the current climate scenario, the suitable habitats of L. tsao-ko were mainly distributed in the western, northwestern and southeastern regions of Yunnan province, and southeastern areas, with an area of 8.20 x 10(4) km(2) . Absorbance values of FT-NIR spectra of samples from different suitable habitats showed a trend of highly suitable areas > moderate > low. Then, a two-dimensional correlation spectroscopy (2DCOS) images based on FT-NIR spectroscopy combined with a residual convolutional neural network (ResNet) was proposed for recognizing the geographic origin of L. tsao-ko . The training and test sets of synchronous 2DCOS images in the full band had 100 % accuracy, and all samples were correctly recognized in the external validation set. The results showed that the geographical origin of L. tsao-ko could be accurately identified based on full -band synchronous 2DCOS images, but attention should also be paid to the spectral information carried by a single spectral region (10000 -7500 cm(-1) , 7500 -5415 cm(-1) and 5415 -4000 cm (- 1) ).The results of the study provide a reference for the introduction and cultivation of L. tsao-ko .
- 相关文献
作者其他论文 更多>>
-
Applications of chemical fingerprints and machine learning in plant ecology: Recent progress and future perspectives
作者:Zhong, Chen;Wang, Yuan-Zhong;Zhong, Chen;Li, Li
关键词:Chemical fingerprints; Chemometrics; Plant ecology; Analytical techniques; Machine learning algorithms
-
Analysis of Chemical Changes during Maturation of Amomum tsao-ko Based on GC-MS, FT-NIR, and FT-MIR
作者:He, Gang;Yang, Shao-bing;Wang, Yuan-zhong;He, Gang
关键词:
-
Application of spectral image processing with different dimensions combined with large-screen visualization in the identification of boletes species
作者:Li, Jie-Qing;Liu, Hong-Gao;Wang, Yuan-Zhong;Liu, Hong-Gao
关键词:boletes species; 2DCOS images; 3DCOS images; Alexnet; Resnet; large-screen visualization
-
Traditional uses, chemical compositions and pharmacological activities of Dendrobium: A review
作者:Li, Pei-Yuan;Wang, Yuan-Zhong;Li, Pei-Yuan;Li, Li
关键词:Dendrobium; Traditional use; Chemical composition; Pharmacological activity
-
A rapid identification based on FT-NIR spectroscopies and machine learning for drying temperatures of Amomum tsao-ko
作者:He, Gang;Lin, Qi;Yang, Shao-Bing;Wang, Yuan-Zhong;He, Gang;Lin, Qi
关键词:Identification research; FT-NIR spectroscopies; Machine learning; Chemometrics; Drying temperatures; Amomum tsao-ko
-
The potential of Amomum tsao-ko as a traditional Chinese medicine: Traditional clinical applications, phytochemistry and pharmacological properties
作者:He, Gang;Yang, Shao-bing;Wang, Yuan-zhong;He, Gang
关键词:Amomum tsao-ko; Chinese herbal medicine; Chemical compounds; Physiological characteristics; Review
-
An integrated chemical characterization based on FT-NIR, and GC-MS for the comparative metabolite profiling of 3 species of the genus Amomum
作者:He, Gang;Yang, Shao-bing;Wang, Yuan-zhong;He, Gang
关键词:Genus Amomum; Quality markers; Identification research; Network pharmacology; Deep learning