Ranking drivers of global carbon and energy fluxes over land

Gustau Camps-Valls, Martin Jung, Kazuhito Ichii, Dario Papale, Gianluca Tramontana, Paul Bodesheim, Christopher R Schwalm, Jakob Zscheischler, Miguel Mahecha, Markus Reichstein

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

4 Citations (Scopus)

Abstract

The accurate estimation of carbon and heat fluxes at global scale is paramount for future policy decisions in the context of global climate change. This paper analyzes the relative relevance of potential remote sensing and meteorological drivers of global carbon and energy fluxes over land. The study is done in an indirect way via upscaling both Gross Primary Production (GPP) and latent energy (LE) using Gaussian Process regression (GPR). In summary, GPR is successfully compared to multivariate linear regression (RMSE gain of +4.17% in GPP and +7.63% in LE) and kernel ridge regression (+2.91% in GPP and +3.07% in LE). The best GP models are then studied in terms of explanatory power based on the analysis of the lengthscales of the anisotropic covariance function, sensitivity maps of the predictive mean, and the robustness to distortions in the input variables. It is concluded that GPP is predominantly mediated by several vegetation indices and land surface temperature (LST), while LE is mostly driven by LST, global radiation and vegetation indices.

Original languageEnglish (US)
Title of host publicationInternational Geoscience and Remote Sensing Symposium (IGARSS)
PublisherInstitute of Electrical and Electronics Engineers Inc.
Pages4416-4419
Number of pages4
Volume2015-November
ISBN (Print)9781479979295
DOIs
StatePublished - Nov 10 2015
Externally publishedYes
EventIEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Milan, Italy
Duration: Jul 26 2015Jul 31 2015

Other

OtherIEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015
CountryItaly
CityMilan
Period7/26/157/31/15

Fingerprint

carbon flux
energy flux
ranking
primary production
Fluxes
Carbon
vegetation index
energy
land surface
surface temperature
upscaling
Linear regression
Climate change
heat flux
Heat flux
global climate
Remote sensing
remote sensing
Radiation
Temperature

Keywords

  • carbon
  • energy
  • feature ranking
  • Gaussian process
  • global monitoring
  • GPP
  • regression

ASJC Scopus subject areas

  • Earth and Planetary Sciences(all)
  • Computer Science Applications

Cite this

Camps-Valls, G., Jung, M., Ichii, K., Papale, D., Tramontana, G., Bodesheim, P., ... Reichstein, M. (2015). Ranking drivers of global carbon and energy fluxes over land. In International Geoscience and Remote Sensing Symposium (IGARSS) (Vol. 2015-November, pp. 4416-4419). [7326806] Institute of Electrical and Electronics Engineers Inc.. https://doi.org/10.1109/IGARSS.2015.7326806

Ranking drivers of global carbon and energy fluxes over land. / Camps-Valls, Gustau; Jung, Martin; Ichii, Kazuhito; Papale, Dario; Tramontana, Gianluca; Bodesheim, Paul; Schwalm, Christopher R; Zscheischler, Jakob; Mahecha, Miguel; Reichstein, Markus.

International Geoscience and Remote Sensing Symposium (IGARSS). Vol. 2015-November Institute of Electrical and Electronics Engineers Inc., 2015. p. 4416-4419 7326806.

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

Camps-Valls, G, Jung, M, Ichii, K, Papale, D, Tramontana, G, Bodesheim, P, Schwalm, CR, Zscheischler, J, Mahecha, M & Reichstein, M 2015, Ranking drivers of global carbon and energy fluxes over land. in International Geoscience and Remote Sensing Symposium (IGARSS). vol. 2015-November, 7326806, Institute of Electrical and Electronics Engineers Inc., pp. 4416-4419, IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015, Milan, Italy, 7/26/15. https://doi.org/10.1109/IGARSS.2015.7326806
Camps-Valls G, Jung M, Ichii K, Papale D, Tramontana G, Bodesheim P et al. Ranking drivers of global carbon and energy fluxes over land. In International Geoscience and Remote Sensing Symposium (IGARSS). Vol. 2015-November. Institute of Electrical and Electronics Engineers Inc. 2015. p. 4416-4419. 7326806 https://doi.org/10.1109/IGARSS.2015.7326806
Camps-Valls, Gustau ; Jung, Martin ; Ichii, Kazuhito ; Papale, Dario ; Tramontana, Gianluca ; Bodesheim, Paul ; Schwalm, Christopher R ; Zscheischler, Jakob ; Mahecha, Miguel ; Reichstein, Markus. / Ranking drivers of global carbon and energy fluxes over land. International Geoscience and Remote Sensing Symposium (IGARSS). Vol. 2015-November Institute of Electrical and Electronics Engineers Inc., 2015. pp. 4416-4419
@inproceedings{d1086f2098be4505ae75f73380073062,
title = "Ranking drivers of global carbon and energy fluxes over land",
abstract = "The accurate estimation of carbon and heat fluxes at global scale is paramount for future policy decisions in the context of global climate change. This paper analyzes the relative relevance of potential remote sensing and meteorological drivers of global carbon and energy fluxes over land. The study is done in an indirect way via upscaling both Gross Primary Production (GPP) and latent energy (LE) using Gaussian Process regression (GPR). In summary, GPR is successfully compared to multivariate linear regression (RMSE gain of +4.17{\%} in GPP and +7.63{\%} in LE) and kernel ridge regression (+2.91{\%} in GPP and +3.07{\%} in LE). The best GP models are then studied in terms of explanatory power based on the analysis of the lengthscales of the anisotropic covariance function, sensitivity maps of the predictive mean, and the robustness to distortions in the input variables. It is concluded that GPP is predominantly mediated by several vegetation indices and land surface temperature (LST), while LE is mostly driven by LST, global radiation and vegetation indices.",
keywords = "carbon, energy, feature ranking, Gaussian process, global monitoring, GPP, regression",
author = "Gustau Camps-Valls and Martin Jung and Kazuhito Ichii and Dario Papale and Gianluca Tramontana and Paul Bodesheim and Schwalm, {Christopher R} and Jakob Zscheischler and Miguel Mahecha and Markus Reichstein",
year = "2015",
month = "11",
day = "10",
doi = "10.1109/IGARSS.2015.7326806",
language = "English (US)",
isbn = "9781479979295",
volume = "2015-November",
pages = "4416--4419",
booktitle = "International Geoscience and Remote Sensing Symposium (IGARSS)",
publisher = "Institute of Electrical and Electronics Engineers Inc.",

}

TY - GEN

T1 - Ranking drivers of global carbon and energy fluxes over land

AU - Camps-Valls, Gustau

AU - Jung, Martin

AU - Ichii, Kazuhito

AU - Papale, Dario

AU - Tramontana, Gianluca

AU - Bodesheim, Paul

AU - Schwalm, Christopher R

AU - Zscheischler, Jakob

AU - Mahecha, Miguel

AU - Reichstein, Markus

PY - 2015/11/10

Y1 - 2015/11/10

N2 - The accurate estimation of carbon and heat fluxes at global scale is paramount for future policy decisions in the context of global climate change. This paper analyzes the relative relevance of potential remote sensing and meteorological drivers of global carbon and energy fluxes over land. The study is done in an indirect way via upscaling both Gross Primary Production (GPP) and latent energy (LE) using Gaussian Process regression (GPR). In summary, GPR is successfully compared to multivariate linear regression (RMSE gain of +4.17% in GPP and +7.63% in LE) and kernel ridge regression (+2.91% in GPP and +3.07% in LE). The best GP models are then studied in terms of explanatory power based on the analysis of the lengthscales of the anisotropic covariance function, sensitivity maps of the predictive mean, and the robustness to distortions in the input variables. It is concluded that GPP is predominantly mediated by several vegetation indices and land surface temperature (LST), while LE is mostly driven by LST, global radiation and vegetation indices.

AB - The accurate estimation of carbon and heat fluxes at global scale is paramount for future policy decisions in the context of global climate change. This paper analyzes the relative relevance of potential remote sensing and meteorological drivers of global carbon and energy fluxes over land. The study is done in an indirect way via upscaling both Gross Primary Production (GPP) and latent energy (LE) using Gaussian Process regression (GPR). In summary, GPR is successfully compared to multivariate linear regression (RMSE gain of +4.17% in GPP and +7.63% in LE) and kernel ridge regression (+2.91% in GPP and +3.07% in LE). The best GP models are then studied in terms of explanatory power based on the analysis of the lengthscales of the anisotropic covariance function, sensitivity maps of the predictive mean, and the robustness to distortions in the input variables. It is concluded that GPP is predominantly mediated by several vegetation indices and land surface temperature (LST), while LE is mostly driven by LST, global radiation and vegetation indices.

KW - carbon

KW - energy

KW - feature ranking

KW - Gaussian process

KW - global monitoring

KW - GPP

KW - regression

UR - http://www.scopus.com/inward/record.url?scp=84962486937&partnerID=8YFLogxK

UR - http://www.scopus.com/inward/citedby.url?scp=84962486937&partnerID=8YFLogxK

U2 - 10.1109/IGARSS.2015.7326806

DO - 10.1109/IGARSS.2015.7326806

M3 - Conference contribution

AN - SCOPUS:84962486937

SN - 9781479979295

VL - 2015-November

SP - 4416

EP - 4419

BT - International Geoscience and Remote Sensing Symposium (IGARSS)

PB - Institute of Electrical and Electronics Engineers Inc.

ER -