基于XGBoost算法的鱼粉中微塑料的红外光谱识别研究

doi:10.3964/j.issn.1000-0593(2024)07-1835-08

摘要
参考文献
相关文章 (15)

全文: PDF (10490 KB)
输出: BibTeX | EndNote (RIS)

摘要：作为四大新兴污染物之一的“微塑料”带来的危害日益凸显，微塑料的检测识别是其污染评估和风险管理防控的关键。以鱼粉饲料中的微塑料（包括PA、PE、PET、PP、PS、PVC）作为研究对象，运用XGBoost算法分别研究构建了近红外光谱和红外光谱定性识别模型。采用GridSearchCV工具包研究优化XGBoost模型的主要超参数，近红外光谱模型的超参数优化结果为n_estimators：300，learning_rate：0.08，gamma：0，max_depth：4，min_child_weight：1；红外光谱的超参数优化结果为n_estimators：100，learning_rate：0.02，gamma：0.20，max_depth：4，min_child_weight：1。基于优化后的超参数构建的近红外定性识别模型平均精确率（Precision）为0.985，平均召回率（Recall）为0.977，平均F1值（F1 score）为0.978，相比于优化前模型效果分别提升了40.17%，51.00%，50.00%；红外定性识别模型平均精确率（Precision）、平均召回率（Recall）和平均F1值（F1 score）均为1.000，优化后的模型效果分别提升了20.67%，27.50%，26.33%。进一步与PLS-DA模型对比分析发现，红外光谱的XGBoost模型与PLS-DA模型效果基本一致，近红外光谱的XGBoost模型各参数（Accuracy，Precision，Recall，F1 score）效果均不同程度地优于PLS-DA模型。综上所述，运用XGBoost算法可以有效识别鱼粉中不同种类的微塑料，该研究为鱼粉饲料中微塑料的快速检测识别方法提供理论支持和技术支撑。

关键词：微塑料；红外光谱；XGBoost；PLS-DA

Abstract：As one of the four emerging pollutants, the harm caused by “microplastics” has become increasingly prominent. The detection and identification of microplastics are the keys to pollution assessment and risk management prevention and control. This paper uses microplastics (including PA, PE, PET, PP, PS, and PVC) in fishmeal as the research objects. The XGBoost algorithm studies and constructs the qualitative recognition models of near-infrared and infrared spectroscopy. The XGBoost algorithm studies and constructs the qualitative recognition models of near-infrared and infrared spectroscopy. Optimising the main hyperparameters of the XGBoost model using the GridSearchCV toolkit. The hyperparameter optimization results of the near-infrared spectroscopy model were n_estimators: 300, learning_rate: 0.08, gamma: 0, max_depth: 4, min_child_weight: 1. The hyperparameter optimization results of infrared spectroscopy are n_estimators: 100, learning_rate: 0.02, gamma: 0.20, max_depth: 4, and min_child_weight: 1. The average Precision of the NIR qualitative recognition model constructed based on the optimized hyperparameters was 0.985, the average Recall was 0.977, and the average F1 score was 0.978, which improved by 40.17%, 51.00%, and 50.00% compared with the model before optimization. The average precision, average recall, and average F1 scores of the infrared qualitative recognition model were all 1.000, and the optimized model effect improved by 20.67%, 27.50%, and 26.33%, respectively. Further comparative analysis with the PLS-DA model shows that the XGBoost model of the infrared spectrum is the same as that of the PLS-DA model, and the effect of each parameter (Accuracy, Precision, Recall, F1 score) of the XGBoost model of the near-infrared spectrum is better than that of PLS-DA model to varying degrees. In summary, the XGBoost algorithm can effectively identify different types of microplastics in fishmeal. This study provides theoretical and technical support for rapidly detecting and identifying microplastics in fishmeal.

Key words：Microplastics; Infrared spectroscopy; XGBoost; PLS-DA

收稿日期: 2023-03-17 修订日期: 2023-11-05

中图分类号:

O433.4

基金资助: 国家重点研发计划项目（2019YFE0103800）资助

通讯作者: 刘贤 E-mail: lx@cau.edu.cn

作者简介: 许晓栋，1996年生，中国农业大学工学院农业工程系博士研究生 e-mail: xuxd@cau.edu.cn

引用本文:

许晓栋，张慧敏，刘佳乐，韩鲁佳，杨增玲，刘贤. 基于XGBoost算法的鱼粉中微塑料的红外光谱识别研究[J]. 光谱学与光谱分析, 2024, 44(07): 1835-1842.
XU Xiao-dong, ZHANG Hui-min, LIU Jia-le, HAN Lu-jia, YANG Zeng-ling, LIU Xian. Study on Infrared Spectral Recognition of Microplastics in Fishmeal Based on XGBoost Algorithm. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2024, 44(07): 1835-1842.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2024)07-1835-08 或 https://www.gpxygpfx.com/CN/Y2024/V44/I07/1835

[1] Veerasingam S, Saha M, Suneel V, et al. Chemosphere, 2016, 159: 496.
[2] Thompson R C. Science, 2004, 304(5672): 838.
[3] Hale S E, Arp H P H, Schliebner I, et al. Environmental Science & Technology, 2020, 54(23): 14790.
[4] Bhat M A, Gedik K, Gaga E O. Air Quality, Atmosphere & Health, 2023, 16(2): 233.
[5] Amato-Lourenço L F, Carvalho-Oliveira R, Júnior G R, et al. Journal of Hazardous Materials, 2021, 416: 126124.
[6] Ragusa A, Svelato A, Santacroce C, et al. Environment International, 2021, 146: 106274.
[7] Tang B L. Frontiers in Environmental Science, 2017, 7(1): 46687.
[8] Jenner L C, Rotchell J M, Bennett R T, et al. Science of The Total Environment, 2022, 831: 154907.
[9] Leslie H A, van Velzen M J M, Brandsma S H, et al. Environment International, 2022, 163: 107199.
[10] Ragusa A, Svelato A, Santacroce C, et al. Environment International, 2021, 146: 106274.
[11] WU Xue, FENG Wei-wei, CAI Zong-qi, et al(吴雪，冯巍巍，蔡宗岐, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2022, 42(11): 3501.
[12] LUO Yong-ming, SHI Hua-hong, TU Chen, et al(骆永明，施华宏，涂晨, 等). Chinese Science Bulletin(科学通报), 2021, 66(13): 1547.
[13] Peñalver R, Arroyo-Manzanares N, López-García I, et al. Chemosphere, 2020, 242: 125170.
[14] Castelvetro V, Corti A, Bianchi S, et al. Environmental Pollution, 2021, 273: 115792.
[15] Thiele C J, Hudson M D, Russell A E, et al. Scientific Reports, 2021, 11(1): 2045.
[16] Walkinshaw C, Tolhurst T J, Lindeque P K, et al. Marine Pollution Bulletin, 2022, 185: 114189.
[17] Chen T, Guestrin C. ACM SIGKDD International Conference on Knowledge Discovery and Data Mining, 2016, 785.
[18] ZHAO Xin, LIU Xin, WANG Yun-peng, et al(赵昕，刘鑫，王韵彭, 等). Science and Technology of Food Industry(食品工业科技), 2022, 43(21): 294.
[19] Zontov Y V, Rodionova O Y, Kucheryavskiy S V, et al. Chemometrics and Intelligent Laboratory Systems, 2020, 203: 104064.
[20] Santos Y J S, Malegori C, Colnago L A, et al. Critical Reviews in Food Science and Nutrition, 2022, 64(10): 11.