Visible/Near Infrared Spectroscopic Modeling for Cadmium
Contaminated Lettuce
ZHOU Lei-jinyu1, ZHOU Li-na1*, CHEN Li-mei1, KONG Li-juan1, QIAO Jian-lei2, LI Ming-tang3
1. College of Engineering and Technology, Jilin Agricultural University, Changchun 130118, China
2. College of Horticulture, Jilin Agricultural University, Changchun 130118, China
3. College of Resources and Environment, Jilin Agricultural University, Changchun 130118, China
Abstract：To quickly and non-destructively monitor the degree of cadmium contamination in lettuce, visible-near infrared spectroscopy is used to classify cadmium contamination in lettuce. Lettuce leaves' visible-near infrared reflectance spectra were collected to analyze the variation in reflectance spectra under different cadmium pollution levels (0, 5, 10, 20 mg·kg-1) in soil, with lettuce as the research subject. The spectral analysis reveals that within the wavelength range of 510 to 730 nm, the reflectance of lettuce leaves in the visible-near infrared spectrum decreases and then increases with the increase in cadmium content in the soil. Within the wavelength range of 730 to 799.53 nm, the reflectance of lettuce leaves under 5 and 20 mg·kg-1 cadmium stress is higher than the CK, while under 10 mg·kg-1 cadmium stress, the reflectance is lower than the control group. Additionally, an absorption valley was observed at 762.199 nm. In establishing a cadmium pollution monitoring model for lettuce, various preprocessing methods were applied to the raw spectra to improve the signal-to-noise ratio. These methods include smoothing (SG), multiplicative scatter correction (MSC), standard normal variate (SNV), mean normalization (MN), SG+MSC, SG+SNV, SG+MN, SG+first derivative (FD), and SG+second derivative (SD). Based on the principal component analysis (PCA), dimensionality reduction was performed on the original spectra and spectra subjected to various preprocessing methods. Subsequently, the reduced data was divided into training and testing sets in a 4∶1 ratio. These sets were then used to establish classification monitoring models for cadmium pollution in lettuce by combining particle swarm optimization-random forest (PSO-RF), genetic algorithm-optimized support vector machine (GA-SVM), backpropagation neural network (BP-NN), extreme learning machine (ELM), and Naive Bayes, followed by analysis and comparison. The results demonstrate that among the different models, the PSO-RF (SG) model achieves the best recognition performance, followed by the GA-SVM (SG+FD) model and the ELM (MSC) model. The training accuracy of the PSO-RF (SG), GA-SVM (SG+FD), and ELM (MSC) models is 100%, while their testing accuracies are 100%, 83.33%, and 79.17% respectively. On the other hand, the BP-NN model and the Naive Bayes model perform relatively poorly. The training accuracy of the BP-NN (SNV) model is 42.72% with a testing accuracy of 50%. The Naive Bayes (SG+FD) model achieves a training accuracy of 71.84% and a testing accuracy of 83.33%. It indicates that applying visible-near infrared spectroscopy combined with particle swarm optimization random forest modeling can provide a novel approach for studying the monitoring of heavy metal contamination in lettuce.
Key words：Cd; Heavy metal pollution; Reflectance spectra; Random forest; Monitoring model
[1] Zhao F J, Ma Y B, Zhu Y G, et al. Environmental Science & Technology, 2015, 49(2): 750.
[2] Shi T R, Zhang Y Y, Gong Y W, et al. Chemosphere, 2019, 230: 136.
[3] WANG Xiao-juan, WANG Wen-bin, YANG Long, et al(王晓娟, 王文斌, 杨 龙, 等). Acta Ecologica Sinica(生态学报), 2015, 35(23): 7921.
[4] ZHANG Yan-chao, REN Yan-fang, LIN Xiao, et al(张艳超, 任艳芳, 林 肖, 等). Jiangsu Agricultural Sciences(江苏农业科学), 2017, 45(2): 51.
[5] Baudrot V, Fritsch C, Perasso A, et al. Ecological Modelling, 2018, 382, doi: 10.1016/j.ecolmodel.2018.05.002.
[6] LIU Kai-ge, SONG Yun-peng, ZHANG Li-li, et al(刘凯歌, 宋云鹏, 张丽丽, 等). Journal of Changjiang Vegetables(长江蔬菜), 2021，6: 51.
[7] Tang X W, Pang Y, Ji P H, et al. Ecotoxicology and Environmental Safety, 2016, 125: 102.
[8] ZHONG Liang, QIAN Jia-wei, CHU Xue-yuan, et al(钟 亮, 钱家炜, 储学远，等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2023, 39(5): 265.
[9] LIU Yan-ping, LUO Qing, CHENG He-fa(刘彦平, 罗 晴, 程和发). Journal of Agro-Environment Science(农业环境科学学报), 2020, 39(12): 2699.
[10] Kooistra L, Salas E A L, Clevers J G P W, et al. Environmental Pollution, 2004, 127(2): 281.
[11] SHI Rong-jie, PAN Xian-zhang, WANG Chang-kun, et al(石荣杰, 潘贤章, 王昌昆，等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2015, 35(11): 3140.
[12] LI Lan-tao, SHEN Feng-min, MA Wen-lian, et al(李岚涛, 申凤敏, 马文连，等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2020, 51(3): 146.
[13] Rathod P H, Brackhage C, Van der Meer F D, et al. European Journal of Remote Sensing, 2015, 48(1): 283.
[14] LI Jun-yan, ZHANG Yue-chun(李君妍, 张跃春). Agricultural Engineering(农业工程), 2018, 8(3): 65.
[15] TAO Liang, ZHANG Nai-ming(陶 亮, 张乃明). Chinese Agricultural Science Bulletin(中国农学通报), 2018, 34(18): 99.
[16] Berens M L, Wolinska K W, Spaepen S, et al. Proceedings of the National Academy of Sciences of the United States of America, 2019, 116(6): 2364.
[17] CHE Yong-fei, YAN Dong, WANG Zheng-qing, et al（车永飞, 严 冬, 王正庆，等）. Science Technology and Engineering（科学技术与工程）, 2023, 23(8): 3544.
[18] Newete S W, Erasmus B F N, Weiersbye I M, et al. International Journal of Remote Sensing, 2014, 35(3): 799.
[19] MA Dong-hui, KE Chang-qing(马东辉, 柯长青). Remote Sensing Technology and Application(遥感技术与应用), 2016, 31(4): 702.
[20] LI Jin-min, CHEN Xiu-qing, YANG Qi, et al(李金敏, 陈秀青, 杨 琦，等). Acta Agronomica Sinica(作物学报), 2021, 47(7): 1342.
[21] FENG Wei, GUO Tian-cai, XIE Ying-xin, et al(冯 伟, 郭天财, 谢迎新，等). Chinese Agricultural Science Bulletin(中国农学通报), 2009, 25(23): 182.
[22] ZHAO Jing-long, ZHANG Fan, WAN Xue-qin, et al(赵景龙, 张 帆, 万雪琴，等). Pratacultural Science(草业科学), 2016, 33(1): 54.
[23] YANG Yang, LI Yan-ling, CHEN Wei-ping, et al(杨 阳, 李艳玲, 陈卫平，等). Environmental Science(环境科学), 2017, 38(1): 399.
[24] Chen X J, Tao H F, Wu Y Z, et al. Scientia Horticulturae, 2022, 305: 111371.
[25] CHEN Nan, FENG Hui-lin, YANG Yan-dong, et al(陈 楠, 冯慧琳, 杨艳东，等). Journal of Agricultural Resources and Environment(农业资源与环境学报), 2021, 38(4): 570.
[26] JIA Yue-hui, HAN Ying-yan, LIU Jie, et al(贾月慧, 韩莹琰, 刘 杰，等). Journal of Agro-Environment Science(农业环境科学学报), 2018, 37(8): 1610.
[27] Zhou X, Sun J, Tian Y, et al. Chemometrics and Intelligent Laboratory Systems, 2020, 200: 103996.
[28] YANG Cheng-en, WU Hai-wei, YUAN Yue-ming, et al（杨承恩, 武海巍, 袁月明，等）. Journal of Jilin Agricultural University（吉林农业大学学报）, 2021, https://doi.org/10.13327/j.jjlau.2021.1425.
