Hyperspectral Inversion of Soil Organic Matter Content Based on a Combined Spectral Index Model

• Main Authors: Lifei Wei, Ziran Yuan, Zhengxiang Wang, Liya Zhao, Yangxi Zhang, Xianyou Lu, Liqin Cao
• Format: Article
• Language: English
• Published: MDPI AG 2020-05-01
• Series: Sensors
• Subjects: hyperspectral remote sensing; soil organic matter; AdaBoost algorithm; pearson correlation analysis
• Online Access: https://www.mdpi.com/1424-8220/20/10/2777

Soil organic matter (SOM) refers to all carbon-containing organic matter in soil and is one<br />of the most important indicators of soil fertility. The hyperspectral inversion analysis of SOM<br />traditionally relies on laboratory chemical testing methods, which have the disadvantages of being<br />inefficient and time-consuming. In this study, 69 soil samples were collected from the Honghu<br />farmland area and a mining area in northwest China. After pretreatment, 10 spectral indicators were<br />obtained. Ridge regression, kernel ridge regression, Bayesian ridge regression, and AdaBoost<br />algorithms were then used to construct the SOM hyperspectral inversion model based on the<br />characteristic bands, and the accuracy of the models was compared. The results showed that the<br />AdaBoost algorithm based on a grid search had the best accuracy in the different regions. For the<br />mining area in northwest China [...]