Academic Bibliography

 Search 200 years of publications by Ghent University researchers.
Advanced search
1 file | 5.66 MB
Add to list
  1. Search results
  2. Estimation of organic carbon in anthr...

Estimation of organic carbon in anthropogenic soil by VIS-NIR spectroscopy : effect of variable selection

Lu Xu, Yongsheng Hong, Yu Wei, Long Guo, Tiezhu Shi, Yi Liu, Qinghu Jiang, Teng Fei, Yaolin Liu, Abdul Mouazen (UGent) , et al.
(2020) REMOTE SENSING. 12(20).
Author
Organization
Abstract
Visible and near-infrared reflectance (VIS-NIR) spectroscopy is widely applied to estimate soil organic carbon (SOC). Intense and diverse human activities increase the heterogeneity in the relationships between SOC and VIS-NIR spectra in anthropogenic soil. This fact results in poor performance of SOC estimation models. To improve model accuracy and parsimony, we investigated the performance of two variable selection algorithms, namely competitive adaptive reweighted sampling (CARS) and random frog (RF), coupled with five spectral pretreatments. A total of 108 samples were collected from Jianghan Plain, China, with the SOC content and VIS-NIR spectra measured in the laboratory. Results showed that both CARS and RF coupled with partial least squares regression (PLSR) outperformed PLSR alone in terms of higher model accuracy and less spectral variables. It revealed that spectral variable selection could identify important spectral variables that account for the relationships between SOC and VIS-NIR spectra, thereby improving the accuracy and parsimony of PLSR models in anthropogenic soil. Our findings are of significant practical value to the SOC estimation in anthropogenic soil by VIS-NIR spectroscopy.
Keywords
General Earth and Planetary Sciences, anthropogenic soil, spectral variable selection, soil organic carbon, visible and near-infrared spectroscopy, NEAR-INFRARED SPECTROSCOPY, RANDOM FROG, SPECTRAL LIBRARIES, TOTAL NITROGEN, MATTER, PREDICTION, REGRESSION, MODEL, OPTIMIZATION, IMPROVE

Downloads

  • Download
    remotesensing-12-03394.pdf
    • full text (Published version)
    • |
    • open access
    • |
    • PDF
    • |
    • 5.66 MB

Citation

Please use this url to cite or link to this publication:

MLA
Xu, Lu, et al. “Estimation of Organic Carbon in Anthropogenic Soil by VIS-NIR Spectroscopy : Effect of Variable Selection.” REMOTE SENSING, vol. 12, no. 20, 2020, doi:10.3390/rs12203394.
APA
Xu, L., Hong, Y., Wei, Y., Guo, L., Shi, T., Liu, Y., … Chen, Y. (2020). Estimation of organic carbon in anthropogenic soil by VIS-NIR spectroscopy : effect of variable selection. REMOTE SENSING, 12(20). https://doi.org/10.3390/rs12203394
Chicago author-date
Xu, Lu, Yongsheng Hong, Yu Wei, Long Guo, Tiezhu Shi, Yi Liu, Qinghu Jiang, et al. 2020. “Estimation of Organic Carbon in Anthropogenic Soil by VIS-NIR Spectroscopy : Effect of Variable Selection.” REMOTE SENSING 12 (20). https://doi.org/10.3390/rs12203394.
Chicago author-date (all authors)
Xu, Lu, Yongsheng Hong, Yu Wei, Long Guo, Tiezhu Shi, Yi Liu, Qinghu Jiang, Teng Fei, Yaolin Liu, Abdul Mouazen, and Yiyun Chen. 2020. “Estimation of Organic Carbon in Anthropogenic Soil by VIS-NIR Spectroscopy : Effect of Variable Selection.” REMOTE SENSING 12 (20). doi:10.3390/rs12203394.
Vancouver
1.
Xu L, Hong Y, Wei Y, Guo L, Shi T, Liu Y, et al. Estimation of organic carbon in anthropogenic soil by VIS-NIR spectroscopy : effect of variable selection. REMOTE SENSING. 2020;12(20).
IEEE
[1]
L. Xu et al., “Estimation of organic carbon in anthropogenic soil by VIS-NIR spectroscopy : effect of variable selection,” REMOTE SENSING, vol. 12, no. 20, 2020.
@article{8691796,
  abstract     = {{Visible and near-infrared reflectance (VIS-NIR) spectroscopy is widely applied to estimate soil organic carbon (SOC). Intense and diverse human activities increase the heterogeneity in the relationships between SOC and VIS-NIR spectra in anthropogenic soil. This fact results in poor performance of SOC estimation models. To improve model accuracy and parsimony, we investigated the performance of two variable selection algorithms, namely competitive adaptive reweighted sampling (CARS) and random frog (RF), coupled with five spectral pretreatments. A total of 108 samples were collected from Jianghan Plain, China, with the SOC content and VIS-NIR spectra measured in the laboratory. Results showed that both CARS and RF coupled with partial least squares regression (PLSR) outperformed PLSR alone in terms of higher model accuracy and less spectral variables. It revealed that spectral variable selection could identify important spectral variables that account for the relationships between SOC and VIS-NIR spectra, thereby improving the accuracy and parsimony of PLSR models in anthropogenic soil. Our findings are of significant practical value to the SOC estimation in anthropogenic soil by VIS-NIR spectroscopy.}},
  articleno    = {{3394}},
  author       = {{Xu, Lu and Hong, Yongsheng and Wei, Yu and Guo, Long and Shi, Tiezhu and Liu, Yi and Jiang, Qinghu and Fei, Teng and Liu, Yaolin and Mouazen, Abdul and Chen, Yiyun}},
  issn         = {{2072-4292}},
  journal      = {{REMOTE SENSING}},
  keywords     = {{General Earth and Planetary Sciences,anthropogenic soil,spectral variable selection,soil organic carbon,visible and near-infrared spectroscopy,NEAR-INFRARED SPECTROSCOPY,RANDOM FROG,SPECTRAL LIBRARIES,TOTAL NITROGEN,MATTER,PREDICTION,REGRESSION,MODEL,OPTIMIZATION,IMPROVE}},
  language     = {{eng}},
  number       = {{20}},
  pages        = {{18}},
  title        = {{Estimation of organic carbon in anthropogenic soil by VIS-NIR spectroscopy : effect of variable selection}},
  url          = {{http://doi.org/10.3390/rs12203394}},
  volume       = {{12}},
  year         = {{2020}},
}
Altmetric
View in Altmetric
Web of Science
Times cited: