基于连续小波变换下的土壤有害元素砷含量估测

doi:10.3964/j.issn.1000-0593(2023)01-0206-07

Abstract
References
Related Citation (6)

Download: PDF (4135 KB)
Export: BibTeX | EndNote (RIS)

Abstract Compared with the traditional detection methods, hyperspectral technology has the characteristics of rapid, accurate and low cost in estimating soil heavy metal arsenic content and can dynamically monitor heavy metal arsenic pollution of oasis soils in arid regions. Based on the collection of soil samples from the cultivated layer of the delta oasis of Weigan-Kuqa river in Xinjiang, soil spectral data and heavy metal arsenic content were obtained. Through the four wavelet basis functions bior1.3, db4, gaus4 and mexh, the original spectral reflectance of the soil was subjected to continuous wavelet transformation. The transformed spectral data was correlated with the heavy metal arsenic so that the selected sensitive wavelet coefficients were taken as independent variables, using partial least square regression, support vector machine regression, BP neural network and random forest regression methods to perform hyperspectral inversion of heavy metal arsenic content. The results showed that: (1) The spectral decomposition effect of the four wavelet basis functions at scales 3 to 8 was obviously better than that of other scales, especially the continuous wavelet transform at scales 4 to 6, effectively improved the correlation between the spectral reflectance with soil heavy metal arsenic, and the number of wavelet coefficients passing the significance test increased significantly (p<0.01), and there had a strong correlation in the vicinity of 400~700 nm in visible light and 1 100~1 700 and 2 200~2 400 nm in near-infrared. (2) By comparing the ability of the four wavelet basis functions to identify effective information in the spectral data, it was believed that the wavelet basis functions bior1.3 and mesh were better than db4 and gaus4. Among them, bior1.3 had the best spectral decomposition effect, and gaus4 was relatively weak. Through the spectral transformation of the 5th scale of bior1.3, the number of bands significantly related to soil heavy metal arsenic was the largest, which was 507 (p<0.01). (3) Comparing the inversion results of the four modeling methods, it was found that the SVMR, BPNN and RFR models had stronger estimation capabilities than the PLSR model, and the estimation accuracy of the model was high. After comprehensively analyzing each model’s stability and estimation accuracy, it was concluded that the bior1.3-2⁵-RFR model could be used as the best estimation model for the heavy metal arsenic in the study area. The R² of the training set and the validation set of the model were 0.893 and 0.639 respectively, the RMSE were 1.075 and 1.651 mg·kg^-1, and the RPD were 2.89 and 1.64 respectively, indicating that the model had a better estimation effect and powerful stability. Using appropriate wavelet basis functions to carry out continuous wavelet transform can reduce the white noise in hyperspectral soil data, excavate the effective information in soil spectral data, and provide a strong technical guarantee for accurate estimation of soil heavy metal arsenic content.

Key words：Wavelet basis function; Decomposition scale; Wavelet coefficient; Machine learning algorithm model; Arsenic

Received: 2022-01-03 Accepted: 2022-04-20

ZTFLH:

P237

Cite this article:

WANG Xue-mei,YUMITI Maiming,HUANG Xiao-yu, et al. Estimation of Arsenic Content in Soil Based on Continuous Wavelet Transform[J]. SPECTROSCOPY AND SPECTRAL ANALYSIS, 2023, 43(01): 206-212.

URL:

https://www.gpxygpfx.com/EN/10.3964/j.issn.1000-0593(2023)01-0206-07 OR https://www.gpxygpfx.com/EN/Y2023/V43/I01/206

[1] ZHOU Wei, LI Li-li, ZHOU Xu, et al(周伟, 李丽丽, 周旭, 等). Ecology and Environmental Sciences(生态环境学报), 2021, 30(1): 173.
[2] Rimondi V, Costagliola P, Lattanzi P, et al. Environmental Geochemistry and Health, 2022, 44(2): 465.
[3] SONG Bo, FU Feng-yan, ZHANG Xue-hong, et al(宋波, 伏凤艳, 张学洪, 等). Acta Scientiae Circumstantiae(环境科学学报), 2014, 34(3): 728.
[4] ZHOU Wei-hong, ZHANG Jing-jing, ZOU Meng-meng, et al(周卫红, 张静静, 邹萌萌, 等). Chinese Journal of Eco-Agriculture(中国生态农业学报), 2017, 25(4): 605.
[5] Gu X, Wang Y, Sun Q, et al. Computers and Electronics in Agriculture, 2019, 167: 105053.
[6] Fu C, Gan S, Yuan X, et al. Mathematics, 2019, 7(6): 488.
[7] LI Zhi-yuan, DENG Fan, HE Jun-liang, et al(李志远, 邓帆, 贺军亮, 等). Spectroscopy and Spectral Analysis(光谱学与光谱分析), 2021, 41(9): 2872.
[8] YE Hong-yun, XIONG Hei-gang, ZHANG Fang, et al(叶红云, 熊黑钢, 张芳, 等). Advances in Laser and Optoelectronics(激光与光电子学进展), 2019, 56(5): 115.
[9] GUO Yun-kai, XIE Xiao-feng, XIE Qiong, et al(郭云开, 谢晓峰, 谢琼, 等). Engineering of Surveying and Mapping(测绘工程), 2021, 30(3): 66.
[10] Zhang S, Shen Q, Nie C, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2019, 211: 393.
[11] XIAO Yan, XIN Hong-bo, WANG Bin, et al(肖艳, 辛洪波, 王斌, 等). Remote Sensing for Land and Resources(国土资源遥感), 2021, 33(2): 33.
[12] ZHAO Jing-yuan, XIONG Zhi-xin, NING Jing-ming, et al(赵静远, 熊智新, 宁井铭, 等). Journal of Analytical Science(分析科学学报), 2021, 37(5): 611.
[13] Zhang S, Shen Q, Nie C, et al. Spectrochimica Acta Part A: Molecular and Biomolecular Spectroscopy, 2019, 211: 393.
[14] Li R, Gao M, Zexin X U, et al. IOP Conference Series: Earth and Environmental Science, 2021, 734(1): 012030.
[15] Hong Y, Chen S, Chen Y, et al. Soil and Tillage Research, 2020, 199: 104589.