Strategies for the efficient estimation of soil organic matter in salt-affected soils through Vis-NIR spectroscopy: Optimal band combination algorithm and spectral degradation

• Published in: Geoderma Vol. 382; p. 114729
• Main Authors: Zhang, Zipeng, Ding, Jianli, Zhu, Chuanmei, Wang, Jingzhe, Ma, Guolin, Ge, Xiangyu, Li, Zhenshan, Han, Lijing
• Format: Journal Article
• Language: English
• Published: Elsevier B.V 15.01.2021
• Subjects: algorithms; China; cost effectiveness; data collection; Laboratory Vis-NIR spectra; lakes; Optimal spectral variable; Partial least-squares-support vector machine; prediction; Principal component analysis; salinity; soil organic matter; soil salinity; spectral analysis; Spectral configuration; spectroradiometers; spectroscopy; China; Laboratory Vis-NIR spectra; Spectral configuration; Optimal spectral variable; Partial least-squares-support vector machine; Principal component analysis

•Vis-NIR spectra were used to estimate the SOM in salt-affected soils.•Seven spectral resolutions (SRs) were tested from 1 nm to 100 nm.•The optimal band combination algorithm is useful for extracting spectral variables.•The soil salinity had a strong negative influence on the SOM model performance....