An Evaluation Method of Quantitative Analysis Software for Near-Infrared Spectroscopy
LI Rong1, 2, HAO Lu4, YUAN Hong-fu4, HE Gui-mei1, 2, DENG Tian-long1, DU Biao4, 5, GONG Li4, YUE Xin2, 3*
1. College of Marine and Environmental Sciences, Tianjin University of Science & Technology, Tianjin 300457, China
2. Research Institute for Environmental Innovation (Binhai, Tianjin), Tianjin 300457, China
3. Chinese Research Academy of Environmental Sciences, Beijing 100012, China
4. Beijing Yixingyuan Petrochemical Technology Co., Ltd., Beijing 101300, China
5. China University of Petroleum(Beijing), Beijing 102249, China
Abstract:The commonly used evaluation indexes of multivariate models lack the ability to evaluate many important predictive performance indicators of near-infrared quantitative analysis software. This has become a pain point in evaluating the predictive performance of near-infrared instrument selection and the applicability of models in practical near-infrared analysis applications. Therefore, this study aims to develop an evaluation method for the predictive performance of near-infrared quantitative analysis software. 192 national VI gasoline samples, including 92#, 95#, and 98#, were collected for determination of olefin concentration of gasoline using near-infrared spectroscopy; their near-infrared spectra collected and olefin concentrations were measured as a reference value according to GB/T 30519—2014, and two different multivariate software(one is partial least squares (PLS) modeling software, and the other is non-PLS software) were used to study. It has been found that compared to the reference value, the PLS model has a positive bias in predicting low-concentration samples and a negative bias in predicting high-concentration samples, which is known as the phenomenon of “averaging”. The commonly used performance evaluation indicators for model prediction cannot yet evaluate the degree of the averaging, nor can evaluate (1) the proportion of samples with deviation from the reference value greater than the limit value for the reproducibility of the reference method and (2) the model's generalization ability. In this paper, four new evaluation indicators are proposed to address the above issues, including Averaging Index (AE), Ratio of samples with prediction bias exceeding the limit value (Ratio), Deviation of Abnormal Sample (DAS), and Deviation of Isolated Sample (DIS). The comprehensive use of commonly used evaluation indicators and new ones (12 items) has practical significance in evaluating the predictive performance of near-infrared quantitative analysis software for instrument selection and the applicability of models in practical near-infrared analysis applications. It also has reference significance for academic research in near-infrared analysis.
Key words:Near-infrared spectroscopy; Multivariate analysis model evaluation; NIR analysis software evaluation; Olefin concentration of gasoline
李 蓉,郝 璐,袁洪福,何桂梅,邓天龙,杜 彪,龚 丽,岳 欣. 一种近红外光谱定量分析软件预测性能评价方法[J]. 光谱学与光谱分析, 2025, 45(01): 213-221.
LI Rong, HAO Lu, YUAN Hong-fu, HE Gui-mei, DENG Tian-long, DU Biao, GONG Li, YUE Xin. An Evaluation Method of Quantitative Analysis Software for Near-Infrared Spectroscopy. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2025, 45(01): 213-221.
[1] Costa G B, Fernandes D D S, Véras G, et al. Journal of the American Oil Chemists' Society, 2024, 101(2): 187.
[2] LIU Yu-juan, LIU Yan-da, SONG Ying, et al(刘玉娟, 刘颜达, 宋 莹, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2023, 43(5): 1489.
[3] FANG Xu, LIU Xin, LI Qi, et al(方 旭, 刘 欣, 李 琪, 等). Acta Metrologica Sinica(计量学报), 2024, 45(1): 103.
[4] Li K, Zhang C, Du B, et al. ACS Omega, 2022, 7(23): 20291.
[5] ZHENG Quan, ZHU Shi-ping, QI Bao-hua, et al(郑 权, 祝诗平, 齐宝华, 等). Journal of Southwest University(Natural Science Edition)[西南大学学报(自然科学版)], 2023, 45(3): 232.
[6] Chu Xiaoli, Huang Yue, Yun Yonghuan, et al. Chemometric Methods in Analytical Spectroscopy Technology. Springer Nature, Singapore, 2022.
[7] LIU Jing-jing, HE Kai-xun(刘晶晶, 贺凯迅). Control Engineering of China(控制工程), 2022, 29(10): 1887.
[8] XU Mei-xian, ZHENG Yan, ZHOU Ruo-lan(许美贤,郑 琰,周若兰). Journal of Nanjing University of Information Science & Technology(南京信息工程大学学报), 2023, 15(4): 379.
[9] DONG Xiao-wei, YANG Ji-ping, YANG Zhi-meng, et al(董晓炜,杨继平,杨志猛,等). Petroleum Processing and Petrochemicals(石油炼制与化工),2022,53(12):106.
[10] DONG Xue-feng, DAI Lian-kui, HUANG Cheng-wei(董学锋,戴连奎,黄承伟). Journal of Zhejiang University (Engineering Science)[浙江大学学报(工学版)],2012,46(5):824.
[11] Huang T Y, Wang J Z, Liu Q Z, et al. Talanta Open, 2022, 5: 100106.
[12] Lalramnghaka J, Thanga H H, Biaktluanga L. Petroleum Science and Technology, 2023, 41(6): 677.
[13] CHEN Su-bin, HU Zhen, ZHANG Xiao-qi, et al(陈素彬, 胡 振, 张晓琪, 等). Chinese Journal of Chemical Education(化学教育), 2018, 39(16): 62.
[14] LI Mao-gang, YAN Chun-hua, XUE Jia, et al(李茂刚,闫春华,薛 佳,等). Chinese Journal of Analytical Chemistry(分析化学),2019,47(12):1995.
[15] JU Xing-rong, HOU Qi-jun, YUAN Jian, et al(鞠兴荣,后其军,袁 建,等). Journal of the Chinese Cereals and Oil Association(中国粮油学报),2015,30(11):120.
[16] LU Hao-xiang, WU Peng-fei, YANG Hui-hua, et al(路皓翔, 吴鹏飞, 杨辉华, 等). Journal of Instrumental Analysis(分析测试学报), 2019, 38(1): 39.
[17] QIN Qiang,CHEN Hua-zhou, LI Ling-hui, et al(秦 强, 陈华舟, 李玲慧, 等). Science Technology and Engineering(科学技术与工程), 2014, 14(36): 137.
[18] CHANG Li, ZHAI Chen, QIAN Cheng-jing, et al(常 莉,翟 晨,钱承敬,等). Chinese Journal of Animal Science(中国畜牧杂志),2024,60(1):101.
[19] SHAO Ping, WANG Jun, WANG Xing-li, et al(邵 平, 王 钧, 王星丽, 等). Journal of Nuclear Agricultural Sciences(核农学报), 2016, 30(1): 103.
[20] WANG Yan-bin, GUO Qing-zhou, LU Wan-zhen, et al(王艳斌,郭庆洲,陆婉珍,等). Petrochemical Technology(石油化工), 2001,30(3): 224.
[21] CHU Xiao-li, CHEN Pu, LI Jing-yan, et al(褚小立,陈 瀑,李敬岩,等). Journal of Instrumental Analysis(分析测试学报),2020,39(10): 1181.
[22] CHU Xiao-li, YUAN Hong-fu, JI Chang-qing, et al(褚小立, 袁洪福, 纪长青, 等). Petrochemical Technology(石油化工), 2001, 30(11): 866.
[23] LIU Qiu-fang, CHU Xiao-li, CHEN Pu, et al(刘秋芳, 褚小立, 陈 瀑, 等). Petroleum Processing and Petrochemicals(石油炼制与化工), 2022, 53(1): 86.