Modeling soil organic carbon with Quantile Regression: Dissecting predictors' effects on carbon stocks

Handle URI:
http://hdl.handle.net/10754/626517
Title:
Modeling soil organic carbon with Quantile Regression: Dissecting predictors' effects on carbon stocks
Authors:
Lombardo, Luigi; Saia, Sergio; Schillaci, Calogero; Mai, Paul Martin ( 0000-0002-9744-4964 ) ; Huser, Raphaël ( 0000-0002-1228-2071 )
Abstract:
Soil Organic Carbon (SOC) estimation is crucial to manage both natural and anthropic ecosystems and has recently been put under the magnifying glass after the Paris agreement 2016 due to its relationship with greenhouse gas. Statistical applications have dominated the SOC stock mapping at regional scale so far. However, the community has hardly ever attempted to implement Quantile Regression (QR) to spatially predict the SOC distribution. In this contribution, we test QR to estimate SOC stock (0-30 $cm$ depth) in the agricultural areas of a highly variable semi-arid region (Sicily, Italy, around 25,000 $km2$) by using topographic and remotely sensed predictors. We also compare the results with those from available SOC stock measurement. The QR models produced robust performances and allowed to recognize dominant effects among the predictors with respect to the considered quantile. This information, currently lacking, suggests that QR can discern predictor influences on SOC stock at specific sub-domains of each predictors. In this work, the predictive map generated at the median shows lower errors than those of the Joint Research Centre and International Soil Reference, and Information Centre benchmarks. The results suggest the use of QR as a comprehensive and effective method to map SOC using legacy data in agro-ecosystems. The R code scripted in this study for QR is included.
KAUST Department:
Physical Sciences and Engineering (PSE) Division; Computer, Electrical and Mathematical Sciences and Engineering (CEMSE) Division
Publisher:
arXiv
Issue Date:
13-Aug-2017
DOI:
10.1016/j.geoderma.2017.12.011
ARXIV:
arXiv:1708.03859
Additional Links:
http://arxiv.org/abs/1708.03859v1; http://arxiv.org/pdf/1708.03859v1
Appears in Collections:
Other/General Submission

Full metadata record

DC FieldValue Language
dc.contributor.authorLombardo, Luigien
dc.contributor.authorSaia, Sergioen
dc.contributor.authorSchillaci, Calogeroen
dc.contributor.authorMai, Paul Martinen
dc.contributor.authorHuser, Raphaëlen
dc.date.accessioned2018-05-01T13:41:17Z-
dc.date.available2017-12-28T07:32:14Z-
dc.date.available2018-05-01T13:41:17Z-
dc.date.issued2017-08-13-
dc.identifier.doi10.1016/j.geoderma.2017.12.011-
dc.identifier.urihttp://hdl.handle.net/10754/626517-
dc.description.abstractSoil Organic Carbon (SOC) estimation is crucial to manage both natural and anthropic ecosystems and has recently been put under the magnifying glass after the Paris agreement 2016 due to its relationship with greenhouse gas. Statistical applications have dominated the SOC stock mapping at regional scale so far. However, the community has hardly ever attempted to implement Quantile Regression (QR) to spatially predict the SOC distribution. In this contribution, we test QR to estimate SOC stock (0-30 $cm$ depth) in the agricultural areas of a highly variable semi-arid region (Sicily, Italy, around 25,000 $km2$) by using topographic and remotely sensed predictors. We also compare the results with those from available SOC stock measurement. The QR models produced robust performances and allowed to recognize dominant effects among the predictors with respect to the considered quantile. This information, currently lacking, suggests that QR can discern predictor influences on SOC stock at specific sub-domains of each predictors. In this work, the predictive map generated at the median shows lower errors than those of the Joint Research Centre and International Soil Reference, and Information Centre benchmarks. The results suggest the use of QR as a comprehensive and effective method to map SOC using legacy data in agro-ecosystems. The R code scripted in this study for QR is included.en
dc.language.isoenen
dc.publisherarXiven
dc.relation.urlhttp://arxiv.org/abs/1708.03859v1en
dc.relation.urlhttp://arxiv.org/pdf/1708.03859v1en
dc.rightsArchived with thanks to arXiven
dc.titleModeling soil organic carbon with Quantile Regression: Dissecting predictors' effects on carbon stocksen
dc.contributor.departmentPhysical Sciences and Engineering (PSE) Divisionen
dc.contributor.departmentComputer, Electrical and Mathematical Sciences and Engineering (CEMSE) Divisionen
dc.eprint.versionPre-printen
dc.contributor.institutionCouncil for Agricultural Research and Economics (CREA), Cereal and Industrial Crops Research Centre (CREA-CI), Foggia, Italyen
dc.contributor.institutionDepartment of Agricultural and Environmental Science, University of Milan, Italyen
dc.identifier.arxividarXiv:1708.03859-
kaust.authorLombardo, Luigien
kaust.authorMai, Paul Martinen
kaust.authorHuser, Raphaëlen

Version History

VersionItem Editor Date Summary
2 10754/626517wangh0e2018-05-01 08:38:06.147Published with DOI
1 10754/626517.1grenzdm2017-12-28 07:32:14.0
All Items in KAUST are protected by copyright, with all rights reserved, unless otherwise indicated.