Cross-regional digital soil carbon modeling in two contrasting soil-ecological regions in the US

B. Cao, S. Grunwald, X. Xiong

Research output: Chapter in Book/Report/Conference proceedingConference contribution

2 Scopus citations

Abstract

The implications of transposing regional digital soil models to continental and global scales are still poorly understood. This paper presents a 'controlled landscape experiment' where soil organic carbon (SOC) stocks were predicted using a standardized set of nationally available environmental predictor variables and sampling density of soil observations. Our specific objective was to compare the prediction performance of SOC in two contrasting regions in the United States. We used soil samples in the topsoil (0-20 cm) depth across Colorado and Florida from the U.S. National Soil Survey Database (Natural Resource and Conservation Service, NRCS). Environmental covariate sets were assembled representing a subset of STEP-AWBH factors (S: soils, T: topography, E: ecology, P: parent material, A: atmosphere, W: water, B: biota, and H: human). We used single Regression Trees (RT) and Support Vector Machines (SVMs) and various error metrics to assess the prediction performance of SOC stocks. Our results demonstrate that in ecologically contrasting states, both RT and SVM could produce moderate good predictions with R2 of 0.76 (SVMs) in Florida and R2 of 0.62 (RT) in Colorado. The differences in model results elucidate on the contrasting relationships between SOC and environmental predictors that were climate, soil and vegetation driven in Colorado and soil and vegetation driven in Florida. These findings have implications for upscaling of regional digital soil models to continental and global scales, specifically for SOC modeling across the U.S.

Original languageEnglish (US)
Title of host publicationDigital Soil Assessments and Beyond - Proceedings of the Fifth Global Workshop on Digital Soil Mapping
PublisherTaylor and Francis - Balkema
Pages103-107
Number of pages5
ISBN (Print)9780415621557
DOIs
StatePublished - Jan 1 2012
Event5th Global Workshop on Digital Soil Mapping - Sydney, NSW, Australia
Duration: Apr 10 2012Apr 13 2012

Publication series

NameDigital Soil Assessments and Beyond - Proceedings of the Fifth Global Workshop on Digital Soil Mapping

Other

Other5th Global Workshop on Digital Soil Mapping
CountryAustralia
CitySydney, NSW
Period4/10/124/13/12

Fingerprint Dive into the research topics of 'Cross-regional digital soil carbon modeling in two contrasting soil-ecological regions in the US'. Together they form a unique fingerprint.

  • Cite this

    Cao, B., Grunwald, S., & Xiong, X. (2012). Cross-regional digital soil carbon modeling in two contrasting soil-ecological regions in the US. In Digital Soil Assessments and Beyond - Proceedings of the Fifth Global Workshop on Digital Soil Mapping (pp. 103-107). (Digital Soil Assessments and Beyond - Proceedings of the Fifth Global Workshop on Digital Soil Mapping). Taylor and Francis - Balkema. https://doi.org/10.1201/b12728-22