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
AU - Zscheischler, Jakob
AU - Mahecha, Miguel
AU - Reichstein, Markus
N1 - Publisher Copyright:
© 2015 IEEE.
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 - GPP
KW - Gaussian process
KW - carbon
KW - energy
KW - feature ranking
KW - global monitoring
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
T3 - International Geoscience and Remote Sensing Symposium (IGARSS)
SP - 4416
EP - 4419
BT - 2015 IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015 - Proceedings
PB - Institute of Electrical and Electronics Engineers Inc.
T2 - IEEE International Geoscience and Remote Sensing Symposium, IGARSS 2015
Y2 - 26 July 2015 through 31 July 2015
ER -