Abstract：Nitrogen is an important component to measure soil fertility. The traditional chemical method for detecting soil nitrogen content is complex and time-consuming. Fourier transform near infrared (FT-NIR) technology is utilized for direct and rapid quantitative determinationof soil nitrogen. Nevertheless, the calibration models always perform too ideally well to believe when established by the linear analytical methods, like partial least squares (PLS). That is not convinced for the practical application in on-line detection. In this paper, we proposed a fault-tolerant mechanism to be plug-into the quantitative analytical model, transforming the FT-NIR quantitative mode into a quasi-qualitative discriminant mode. In this way, the application ability of the calibration model can be enhanced. A new discriminant method was proposed for quasi-qualitative determination by combining the interval search principal component analysis algorithm with logistic regression (iPCA-LR). The nitrogen contents of soil samples were firstly predicted based on the common PLS regression. The fault-tolerant threshold was set as three different values of 0.05, 0.10 and 0.15, respectively. The samples were marked as accurately or non-accurately discriminated according to the priori predictive values and the thresholds, so that the original quantitative calibration method was transformed into a new quasi-qualitative discriminant method. The iPCA-LR method was applied for the FT-NIR quasi-qualitative discrimination of soil nitrogen. In the same process, we also discussed the latent variable extraction based on different wavebands that were generated by tuning the waveband division number as 5, 10, 15 and 20. Some informative FT-NIR wavebands were selected with optimal discriminant accuracy. And some combination of informative wavebands were also tested. Results showed that the FT-NIR quasi-qualitative discriminant predictive accuracy varied significantly for different thresholds, but fortunately the worst optimal accuracy climbed tothe level slightly above 75%. And the test of different informative wavebands or the combination of informative wavebands output optimal calibration models with the accuracy above 90%. These results were able to meet some practical cases of online detection. In the application of FT-NIR prediction of nitrogen content in soil samples, the proposed method of iPCA-LR manage to transform the common quantitative prediction problem into the quasi-qualitative discriminant problem when combined with the priori PLS prediction. The newly proposed method deals with the disadvantages of overfitting and overidealistic modeling that always appears in common PLS quantitative analysis. In comparison, the quasi-qualitative discriminant mode is more suitable for actual cases in field detection, more beneficial for real-time application of spectroscopy technology.
[1] LI Min-zan, ZHENG Li-hua, AN Xiao-fei, et al(李民赞, 郑立华, 安晓飞, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2013, 44(3): 73.
[2] LU Shan, MAO Cai-yun, XIAO He-xia, et al(鲁 珊, 毛彩云, 肖荷霞, 等). Journal of Anhui Agricultural Sciences(安徽农业科学), 2014, 42(18): 5789.
[3] Chen H Z, Feng Q X, Jia Z, et al. Asian Journal of Chemistry, 2014, 26(15): 4839.
[4] ZHANG Juan-juan, XIONG Shu-ping, SHI Lei, et al(张娟娟, 熊淑萍, 时 雷, 等). Soils(土壤), 2015, 47(4): 653.
[5] LU Wan-zhen(陆婉珍). Modern Near-Infrared Spectroscopy Analytical Technology(现代近红外光谱分析技术). 2nd ed(第2版). Beijing: China Petrochemical Press(北京: 中国石化出版社), 2007.
[6] Chen H Z, Liu Z Y, Gu J, et al. Analytical Methods, 2018, 10: 5004.
[7] WANG Fan, LI Yong-yu, PENG Yan-kun, et al(王 凡, 李永玉, 彭彦昆, 等). Chinese Journal of Analytical Chemistry(分析化学), 2018, 49(9): 1424.
[8] Sampaio P S, Soares A, Castanho A, et al. Food Chemistry, 2018, 242: 196.
[9] WANG Chang, HUANG Chi-chao, YU Guang-hui, et al(王 昶, 黄驰超, 余光辉, 等). Acta Pedologica Sinica(土壤学报), 2013, 50(5): 881.
[10] Dong X L, Sun X D. Journal of Food Measurement and Characterization, 2013, 7: 141.
[11] MAO Yi, CHEN Wen-lin, GUO Bao-long, et al(毛 毅, 陈稳霖, 郭宝龙, 等). Acta Automatic Sinica(自动化学报), 2014, 40(1): 62.
[12] Zhou L, Chen J, Yao L, et al. Chemometrics and Intelligent Laboratory Systems, 2017, 161: 88.
[13] Sharifzadeh S, Ghodsi A, Clemmensen L H, et al. Engineering Applications of Artificial Intelligence, 2017, 65: 168.
[14] JIANG Xiao-qing, SONG Jiang-feng, LI Da-jing, et al(姜晓青, 宋江峰, 李大婧, 等). Modern Food Science and Technology(现代食品科技), 2013, 29(8): 2020.
[15] Goodarzi M, Saeys W. Talanta, 2016, 146: 155.
[16] Borille B T, Marcelo M C A, Ortiz R S, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2017, 173: 318.
[17] PENG Hai-gen, PENG Yun-fa, ZHAN Ying, et al(彭海根, 彭云发, 詹 映, 等). Food Science and Technology(食品科技), 2014, 39(6): 276.
[18] Bi Y M, Yuan K L, Xiao W Q, et al. Analytica Chimica Acta, 2016, 909: 30.
[19] HJ/T 717—2014. National Environmental Protection Standards of the People’s Republic of China(中华人民共和国国家环境保护标准).
