Spectroscopy and Spectral Analysis, Volume. 42, Issue 5, 1595(2022)
Experimental Study on Quantitative Inversion Model of Heavy Metals in Soda Saline-Alkali Soil Based on RBF Neural Network
Figures & Tables(10)
Fig. 3. Correlation distribution of the manganese content and the difference index after three kinds of pretreatment
Fig. 5. Comparison of Mn content predicted by RBF neural network and measured Mn content
Fig. 6. Comparison of Co content predicted by RBF neural network and measured Co content
Fig. 7. Comparison of Fe content predicted by RBF neural network and measured Fe content
Table 1. Basic parameters of SVC HR-1024 portable ground-object spectrometer
View tableView in ArticleTable 1. Basic parameters of SVC HR-1024 portable ground-object spectrometer
功能 参数范围 波段范围 350~2 500 nm 通道数 1 024 光谱精度 ±0.5 nm 光谱分辨率 ≤8.5 nm 最小积分时间 1 s 视场角 4°
Table 2. Descriptive statistics for heavy metal concentrations in soil samples (mg·kg-1)
View tableView in ArticleTable 2. Descriptive statistics for heavy metal concentrations in soil samples (mg·kg-1)
项目 最大值 最小值 均值 标准差 Mn 673.03 312.94 512.99 85.03 Co 12.85 4.35 8.61 2.18 Fe 2.87 1.22 2.10 0.47
Table 3. Principle of the optimal selection of spectral indices of heavy metal elements
View tableView in ArticleTable 3. Principle of the optimal selection of spectral indices of heavy metal elements
重金属元素 光谱指数 预处理方法 组数 总组数 DI SG 23 Mn RI MSC 47 108 NDI MSC 38 DI MSC 95 Co RI MSC 434 690 NDI MSC 161 Fe RI MSC 29 31 NDI CR 2
Tools
Get Citation
Copy Citation Text
Yan-hua FU, Jing LIU, Ya-chun MAO, Wang CAO, Jia-qi HUANG, Zhan-guo ZHAO. Experimental Study on Quantitative Inversion Model of Heavy Metals in Soda Saline-Alkali Soil Based on RBF Neural Network[J]. Spectroscopy and Spectral Analysis, 2022, 42(5): 1595
Paper Information
Category: Research Articles
Received: Mar. 23, 2021
Accepted: --
Published Online: Nov. 10, 2022
The Author Email: FU Yan-hua (fuyanhua@mail.neu.edu.cn)
© Copyright 2018-2021 | Chinese Laser Press.
All Rights Reserved 沪ICP备15018463号-20