Using soil library hyperspectral reflectance and machine learning to predict soil organic carbon: Assessing potential of airborne and spaceborne optical soil sensing

• Published in: Remote sensing of environment Vol. 271; no. C; p. 112914
• Main Authors: Wang, Sheng, Guan, Kaiyu, Zhang, Chenhui, Lee, DoKyoung, Margenot, Andrew J., Ge, Yufeng, Peng, Jian, Zhou, Wang, Zhou, Qu, Huang, Yizhi
• Format: Journal Article
• Language: English
• Published: New York Elsevier Inc 15.03.2022; Elsevier BV; Elsevier
• Subjects: Airborne sensing; Algorithms; Artificial neural networks; Atmospheric models; Carbon; Carbon cycle; cost effectiveness; Ecosystem services; ecosystems; environment; Environmental monitoring; ENVIRONMENTAL SCIENCES; Geology; Hyperspectral reflectance; Infrared signatures; Laboratories; Leaf area; Learning algorithms; Learning theory; Least squares method; Libraries; Long short-term memory; Machine learning; Neural networks; Noise levels; Organic carbon; Organic soils; Performance prediction; plant residues; Radiative transfer; Radiative transfer modeling; Reflectance; Remote sensing; Satellite data; Satellites; SBG; Short wave radiation; Soil moisture; Soil organic carbon; soil water; Spectra; spectral analysis; Spectral signatures; Spectroscopy; Spectrum analysis; Vegetation; Spectroscopy; Hyperspectral reflectance; Machine learning; Radiative transfer modeling; Long short-term memory; SBG; Soil organic carbon

Soil organic carbon (SOC) is a key variable to determine soil functioning, ecosystem services, and global carbon cycles. Spectroscopy, particularly optical hyperspectral reflectance coupled with machine learning, can provide rapid, efficient, and cost-effective quantification of SOC. However, how to...