Quantifying moisture and roughness with Support Vector Machines improves spectroscopic soil organic carbon prediction

• Published in: Journal of plant nutrition and soil science Vol. 177; no. 6; pp. 845 - 847
• Main Authors: Römer, Christoph, Rodionov, Andrei, Behmann, Jan, Pätzold, Stefan, Welp, Gerhard, Plümer, Lutz
• Format: Journal Article
• Language: English
• Published: Weinheim WILEY-VCH Verlag 01.12.2014; WILEY‐VCH Verlag; Wiley-VCH; Wiley Subscription Services, Inc
• Subjects: Agronomy. Soil science and plant productions; Biological and medical sciences; Chemical, physicochemical, biochemical and biological properties; Fundamental and applied biological sciences. Psychology; General agronomy. Plant production; moisture; ordinal classification; Organic matter; Physics, chemistry, biochemistry and biology of agricultural and forest soils; roughness; soil organic carbon (SOC); Soil science; Soil-plant relationships. Soil fertility; Soil-plant relationships. Soil fertility. Fertilization. Amendments; Spectrum analysis; Tillage; Vis-NIR spectroscopy; Organic carbon; Organic matter; Automatic classification; Prediction; Roughness; Visible spectrometry; Support vector machine; moisture; Soils; Near infrared spectrometry; Vis-NIR spectroscopy; ordinal classification; Humidity; Optical method; soil organic carbon (SOC); Soil science; Soil plant relation; Spectroscopical observation; Physical method; Quantitative analysis
• ISSN: 1436-8730; 1522-2624
• DOI: 10.1002/jpln.201400152

The challenges of Vis‐NIR spectroscopy are permanent soil surface variations of moisture and roughness. Both disturbance factors reduce the prediction accuracy of soil organic carbon (SOC) significantly. For improved SOC prediction, both disturbance effects have to be determined from Vis‐NIR spectra, which is especially challenging for roughness. Thus, an approach for roughness quantification under varying moisture and its impact on SOC assessment using Support Vector Machines is presented here.