不同pH值土壤中铅含量的太赫兹光谱反演建模研究

doi:10.3964/j.issn.1000-0593(2020)08-2397-06

摘要
参考文献
相关文章 (15)

全文: PDF (2134 KB)
输出: BibTeX | EndNote (RIS)

摘要：针对土壤中铅含量的定量检测问题，本研究基于太赫兹光谱技术对不同pH下土壤中铅含量的最佳反演预测模型进行了探索性研究。分别制备了pH为8.5，7.0和5.5的含铅土壤样品，采集样品的太赫兹光谱数据，并对光谱数据做了多元散射矫正(MSC)、基线校正和Savitzky-Golay平滑等预处理。对预处理后的光谱数据，采用连续投影法(SPA)选取光谱数据的特征频率。基于选取的特征频率分别采用偏最小二乘法(PLS)、支持向量机(SVM)和误差反向传播神经网络(BPNN)建立土壤中铅含量的反演预测模型，采用校正集相关系数(R_c)、校正集均方根误差(RMSEC)、预测集相关系数(R_p)、预测集均方根误差(RMSEP)和剩余预测偏差(RPD)作为评价参数对模型性能进行评估，确定铅在不同pH土壤中的最佳预测模型。实验结果表明：在经过SPA选择特征频率后的建模效果普遍比全光谱的效果好。其中pH 8.5的样品最佳预测模型为SPA-PLS，R_c，R_p，RMSEC，RMSEP和RPD分别为0.997 7，0.994 6，14.52 mg·kg^-1，22.70 mg·kg^-1和9.63；pH 7.0的样品最佳预测模型为SPA-SVM，R_c，R_p，RMSEC，RMSEP和RPD分别为0.996 2，0.975 7，20.25 mg·kg^-1，33.04 mg·kg^-1和4.56；pH 5.5的样品最佳预测模型为SPA-BPNN，R_c，R_p，RMSEC，RMSEP和RPD分别为0.968 7，0.974 4，48.83 mg·kg^-1，55.03 mg·kg^-1和4.44。该研究结果为不同pH土壤中铅含量的光谱反演预测提供了一种新思路，亦可为其他重金属在不同pH土壤中的含量反演预测模型提供理论方法和技术支持。

关键词：土壤；铅；太赫兹光谱；偏最小二乘法；支持向量机；神经网络

Abstract：Aiming at the quantitative determination of heavy metal lead in soils, the optimal inversion prediction model of lead content in soils at different pH was studied based on terahertz spectroscopy. Lead-containing soil samples with pH of 8.5, 7.0 and 5.5 were prepared. Terahertz time-domain spectroscopy system TERA K15 was used to collect the Terahertz spectra of the samples, and multivariate scattering correction (MSC), baseline correction and Savoitzky-Golay smoothing were used to pre-process the spectra. For the spectral data of pre-treatment, successive projection algorithm (SPA) was used to select the sensitive frequencies of spectral data. Based on the selected sensitive frequencies, partial least squares (PLS), support vector machine (SVM) and back propagation neural network (BPNN) was used to establish inversion prediction models of lead content in the soil. The correlation coefficient of calibration (R_c), root mean square error of calibration (RMSEC), the correlation coefficient of prediction (R_p), root mean square error of prediction (RMSEP) and residual predictive deviation (RPD) were used as model evaluation parameters to evaluate the performance of the model, and to determine the best prediction model of leadship in different pH soils. The experimental results show that the modeling effect after SPA choosing sensitive frequencies is generally better than that of full spectrum. Among them, the best prediction models for the samples with pH 8. 5 were SPA-PLS, R_c, R_p, RMSEC, RMSEP and RPD were 0.997 7, 0.994 6, 14.52 mg·kg^-1, 22.70 mg·kg^-1 and 9.63, respectively; the best prediction models for the samples with pH 7.0 were SPA-SVM, R_c, R_p, RMSEC, RMSEP and RPD were 0.996 2, 0.975 7, 20.25 mg·kg^-1, 33.04 mg·kg^-1 and 4.56, respectively; and the samples with pH 5.5 were the best. The prediction models are SPA-BPNN, R_c, R_p, RMSEC, RMSEP and RPD are 0.968 7, 0.974 4, 48.83 mg·kg^-1, 55.03 mg·kg^-1 and 4.44, respectively. The results provide a new idea for inversion prediction of lead content in different pH soils, and also provide theoretical methods and technical support for other heavy metals inversion prediction models in different pH soils.

Key words：Soil; Lead; Terahertzspectrum; PLS; SVM; BPNN

收稿日期: 2019-07-16 修订日期: 2019-11-28

中图分类号:

O657.3

基金资助: 北京市自然科学基金面上项目（6182012），北京市农林科学院创新能力建设专项（KJCX20180421），国家“十三五”重点研发计划项目（2016YFD0702002）资助

通讯作者: 李斌，叶大鹏 E-mail: lib@nercita.org.cn

作者简介: 李超，1993年生，福建农林大学机电工程学院工程硕士研究生 e-mail: 819752082@qq.com

引用本文:

李超，李斌，张丽琼，叶大鹏，郑书河. 不同pH值土壤中铅含量的太赫兹光谱反演建模研究[J]. 光谱学与光谱分析, 2020, 40(08): 2397-2402.
LI Chao, LI Bin, ZHANG Li-qiong, YE Da-peng, ZHENG Shu-he. Terahertz Spectrum Inversion Modeling of Lead Content in Different pH Soils. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2020, 40(08): 2397-2402.

链接本文:

https://www.gpxygpfx.com/CN/10.3964/j.issn.1000-0593(2020)08-2397-06 或 https://www.gpxygpfx.com/CN/Y2020/V40/I08/2397

[1] XU Xi-bo, LÜ Jian-shu, XU Ru-ru(徐夕博，吕建树，徐汝汝). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2018, 34(9): 216.
[2] XIE Long-tao, PAN Jian-jun, BAI Hao-ran, et al(谢龙涛, 潘剑军, 白浩然, 等). Acta Pedologica Sinica (土壤学报), http://kns.cnki.net/kcms/detail/32.1119.P.20190103.0927.002.html.
[3] YANG Xiu-min, REN Guang-meng, LI Li-xin, et al(杨秀敏，任广萌，李立新，等). China Mining Magazine(中国矿业), 2017, 26(6): 79.
[4] Liu Y L, Chen Y Y. Soil and Sediment Contamination: An International Journal, 2012, 21(8): 951.
[5] CHEN Yuan-peng, ZHANG Shi-wen, LUO Ming, et al(陈元鹏，张世文，罗明, 等). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2019, 50(1): 170.
[6] Sun W C, Zhang X. International Journal of Applied Earth Observation and Geoinformation，2017, 58: 126.
[7] ZHANG Qiu-xia, ZHANG He-bing, LIU Wen-kai, et al(张秋霞, 张合兵, 刘文锴，等). Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2017, 33(12): 230.
[8] Sun W C, Zhang X, Sun X J, et al. Geoderma，2018, 327: 25.
[9] Shi T Z, Wang J J, Chen Y Y, et al. International Journal of Applied Earth Observation and Geoinformation，2016, 52: 95.
[10] LI Bin, ZHAO Chun-jiang(李斌，赵春江). Transactions of the Chinese Society for Agricultural Machinery(农业机械学报), 2016, 47(S1): 291.
[11] GB 15618—2018 National Standards of the People’s Republic of China(中华人民共和国国家标准). Soil Environmental Quality Risk Control Standard for Soil Contamination of Agricultural Land(土壤环境质量农用地土壤污染风险管控标准)，2018.
[12] FENG Hai-kuan, LI Zhen-hai, JIN Xiu-liang, et al（冯海宽, 李振海, 金秀良，等）. Transactions of the Chinese Society of Agricultural Engineering(农业工程学报), 2016, 32(12): 165.
[13] Liu W, Liu C H, Yu J J, et al. Food Chemistry，2018, 251：86.
[14] Li M L, Dai G B, Chang T Y, et al. Applied Sciences，2017, 7(2): 172.