Identification of Rice Origin Using Laser-Induced Breakdown Spectroscopy
SONG Shao-zhong1, FU Shao-yan2, LIU Yuan-yuan2, QI Chun-yan3, LI Jing-peng4, GAO Xun2*
1. School of Data Science and Artificial Intelligence, Jilin Normal University of Engineering and Technology, Changchun 130052, China
2. School of Physics, Changchun University of Science and Technology, Changchun 130022, China
3. Rice Research Institute, Jilin Academy of Agricultural Sciences, Changchun 130033, China
4. Northeast Institute of Geography and Agroecology, Chinese Academy of Sciences, Changchun 130102, China
Abstract：Rice is the primary grain crop in China, and the quality of rice is closely related to the external environment, such as soil characteristics, climate, sunshine time, and irrigation water. The high-quality rice-origin area has certain regional limitations. Therefore,the rice can be seen as an apparent geographical marker. There are often some counterfeits or branded famous high-quality rice in the market, which can damage the rice brand, reduce the rice quality guarantee of consumers, and disturb the market stability, so rapid identification technology of rice origin is needed. The rice origin identification models of five sources in Jilin Province (Daan, Gongzhuling, Qianguo, Songyuan and Taoerhe) are done by laser-induced breakdown spectroscopy and machine learning algorithms. The principal component analysis (PCA) algorithm, combined with four machine learning algorithms, Bagged Trees, Weighted KNN, Quadratic SVM, and Coaster Gaussian SVM, has been established. A total of 450 groups of LIBS data are selected. The spectral data of rice LIBS are pretreated with Savitzky-Golay smoothing (S-G smoothing) for noise reduction and normalisation. The principal component analysis uses the rice LIBS data, which shows that the rice origins had an excellent cluster distribution of clustering spaces. Still, there is spatial overlap in some rice origins. Utilising5x cross-validation, the identification accuracy of rice origins can reachmore than 91.8% by adopting PCA-Bagged Trees, PCA-Weighted KNN, PCA-Quadratic SVM and PCA-Coarse Gaussian SVM, and the recognition accuracy of PCA-Quadratic SVM model is as high as 97.3%. The results show that the combination of LIBS technology and machine learning algorithms can identify rice origin with high precision and high efficiency.
Key words：Laser-induced breakdown spectroscopy; Machine learning algorithms; Identification of rice production areas; Identification accuracy
宋少忠，符少燕，刘园园，齐春艳，李景鹏，高 勋. 激光诱导击穿光谱技术对水稻产地识别研究[J]. 光谱学与光谱分析, 2024, 44(06): 1553-1558.
SONG Shao-zhong, FU Shao-yan, LIU Yuan-yuan, QI Chun-yan, LI Jing-peng, GAO Xun. Identification of Rice Origin Using Laser-Induced Breakdown Spectroscopy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(06): 1553-1558.
[1] Sepaskhah A R, Barzegar M. Agricultural Water Management，2010, 98(1): 38.
[2] Jallad K N. Environmental Science and Pollution Research，2015, 22(20): 15449.
[3] Przybylski R, Klensporf-Pawlik D, Anwar F, et al. Journal of the American Oil Chemists Society，2009, 86(6): 553.
[4] GAO Tong, WU Jing-zhu, LIN Long, et al(高 彤，吴静珠，林 珑，等). Journal of Chinese Gereals and Oils Association(中国粮油学报)，2019, 34(7): 114.
[5] WANG Jing-hui, WU Yue, ZANG Yan-yu, et al(王靖会，吴 玥，臧妍宇，等). Journal of Jilin Agricultural University（吉林农业大学学报），2019, 41(3): 373378.
[6] XU Yu-ting, SUN Hao-ran, GAO Xun, et al(许毓婷，孙浩然，高 勋，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析)，2021, 41(11): 3572.
[7] Markiewicz-Keszycka M，Cama-Moncunill X，Casado-Gavalda Maria P, et al. Trends in Food Science and Technology，2017, 65: 80.
[8] Liu Yuanchao, Zhou Binbin, Wang Weiliang, et al. ACS Sensors, 2022, 7(5): 1381.
[9] Lin Xiaomei, Sun Haoran, Gao Xun, et al. Spectrochimica Acta Part B: Atomic Spectroscopy, 2021, 180(20): 106200.
[10] DONG Peng-kai, ZHAO Shang-yong, ZHENG Ke-xin, et al(董鹏凯，赵上勇，郑柯鑫，等). Acta Physica Sinica（物理学报），2021, 70(4): 67.
[11] Liu Yuanyuan, Zhao Shangyong, Gao Xun, et al. RSC Advances, 2022, 12: 34350.
[12] Zhang Tianlong, Liang Long, Wang Kang, et al. Journal of Analytical Atomic Spectrometry, 2014, 29(12): 2323.
[13] Zuo Yuying, Jiao Cuina, Wang Maoli, et al. Interdisciplinary Sciences Computational Life Sciences, 2021, 14(1): 22.
[14] Yeung K Y, Ruzzo W L. Bioinformatics，2001, 17(9): 763.
[15] Alpaydin E. Neural Computation，1999, 11(8): 1975.
[16] Jiang He, Dong Yao. Energy, 2017, 133: 270.
