Accurate and Precise Prediction of Soil Properties from a Large Mid-Infrared Spectral Library

• Published in: Soil systems Vol. 3; no. 1; p. 11
• Main Authors: Dangal, Shree R. S., Sanderman, Jonathan, Wills, Skye, Ramirez-Lopez, Leonardo
• Format: Journal Article
• Language: English
• Published: MDPI AG 29.01.2019
• Subjects: algorithms; artificial intelligence; carbon cycle; cost effectiveness; Cubist; least squares; local model; MIR spectral library; partial least squares regression; prediction; prediction uncertainty; random forest; reflectance spectroscopy; soil properties; soil surveys; uncertainty; United States; USDA; United States

Diffuse reflectance spectroscopy (DRS) is emerging as a rapid and cost-effective alternative to routine laboratory analysis for many soil properties. However, it has primarily been applied in project-specific contexts. Here, we provide an assessment of DRS spectroscopy at the scale of the continenta...