DOE PAGES title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Effect of spatial sampling from European flux towers for estimating carbon and water fluxes with artificial neural networks

Abstract

Abstract Empirical modeling approaches are frequently used to upscale local eddy covariance observations of carbon, water, and energy fluxes to regional and global scales. The predictive capacity of such models largely depends on the data used for parameterization and identification of input‐output relationships, while prediction for conditions outside the training domain is generally uncertain. In this work, artificial neural networks (ANNs) were used for the prediction of gross primary production (GPP) and latent heat flux (LE) on local and European scales with the aim to assess the portion of uncertainties in extrapolation due to sample selection. ANNs were found to be a useful tool for GPP and LE prediction, in particular for extrapolation in time (mean absolute error MAE for GPP between 0.53 and 1.56 gC m −2  d −1 ). Extrapolation in space in similar climatic and vegetation conditions also gave good results (GPP MAE 0.7–1.41 gC m −2  d −1 ), while extrapolation in areas with different seasonal cycles and controlling factors (e.g., the tropical regions) showed noticeably higher errors (GPP MAE 0.8–2.09 gC m −2  d −1 ). The distribution and the number of sites used for ANN training had a remarkable effect on prediction uncertainty in both, regional GPP and LE budgetsmore » and their interannual variability. Results obtained show that for ANN upscaling for continents with relatively small networks of sites, the error due to the sampling can be large and needs to be considered and quantified. The analysis of the spatial variability of the uncertainty helped to identify the meteorological drivers driving the uncertainty.« less

Authors:
 [1];  [2];  [3];  [4];  [5];  [6];  [7];  [8];  [6];  [9];  [10];  [11];  [12]; ORCiD logo [13];  [6];  [14];  [15]; ORCiD logo [16];  [17]
  1. Department for Innovation in Biological, Agro‐Food and Forest Systems University of Tuscia Viterbo Italy, CzechGlobe, Global Change Research Centre AS CR Brno Czech Republic
  2. Faculty of Land and Food Systems University of British Columbia Vancouver British Columbia Canada
  3. Department Biogeochemical Integration Max Planck Institute for Biogeochemistry Jena Germany, Departamento de Ciências e Engenharia do Ambiente, Faculdade de Ciências e Tecnologia Universidade Nova de Lisboa Lisbon Portugal
  4. Institute for Environment and Sustainability, Joint Research Centre European Commission Ispra Italy
  5. CGCEO/Department of Geography Michigan State University East Lansing Michigan USA
  6. Department Biogeochemical Integration Max Planck Institute for Biogeochemistry Jena Germany
  7. Civil and Environmental Engineering Department, and Environmental Research Institute University College Cork Cork Ireland
  8. Fire in the Earth System, Land in the Earth System Max Planck Institute for Meteorology Hamburg Germany
  9. Centre d'étude de la forêt Université Laval Quebec Quebec Canada
  10. Department of Environmental Systems Science, Institute of Agricultural Sciences ETH Zurich Zurich Switzerland
  11. Forest Services, Autonomous Province of Bolzano Bolzano Italy, Faculty of Sciences and Technology Free University of Bolzano Bolzano Italy
  12. Alterra Wageningen UR Wageningen Netherlands, VU University Amsterdam Amsterdam Netherlands
  13. Department of Agroecology Aarhus University Tjele Denmark
  14. Department for Innovation in Biological, Agro‐Food and Forest Systems University of Tuscia Viterbo Italy
  15. CSIRO Oceans and Atmosphere Flagship Yarralumla Australia
  16. Institute for Ecology University of Innsbruck Innsbruck Austria, European Academy Bolzano Bolzano Italy
  17. Department of Bioengineering Sapientia Hungarian University of Transylvania Miercurea Ciuc Romania
Publication Date:
Sponsoring Org.:
USDOE
OSTI Identifier:
1402304
Resource Type:
Publisher's Accepted Manuscript
Journal Name:
Journal of Geophysical Research. Biogeosciences
Additional Journal Information:
Journal Name: Journal of Geophysical Research. Biogeosciences Journal Volume: 120 Journal Issue: 10; Journal ID: ISSN 2169-8953
Publisher:
American Geophysical Union (AGU)
Country of Publication:
United States
Language:
English

Citation Formats

Papale, Dario, Black, T. Andrew, Carvalhais, Nuno, Cescatti, Alessandro, Chen, Jiquan, Jung, Martin, Kiely, Gerard, Lasslop, Gitta, Mahecha, Miguel D., Margolis, Hank, Merbold, Lutz, Montagnani, Leonardo, Moors, Eddy, Olesen, Jørgen E., Reichstein, Markus, Tramontana, Gianluca, van Gorsel, Eva, Wohlfahrt, Georg, and Ráduly, Botond. Effect of spatial sampling from European flux towers for estimating carbon and water fluxes with artificial neural networks. United States: N. p., 2015. Web. doi:10.1002/2015JG002997.
Papale, Dario, Black, T. Andrew, Carvalhais, Nuno, Cescatti, Alessandro, Chen, Jiquan, Jung, Martin, Kiely, Gerard, Lasslop, Gitta, Mahecha, Miguel D., Margolis, Hank, Merbold, Lutz, Montagnani, Leonardo, Moors, Eddy, Olesen, Jørgen E., Reichstein, Markus, Tramontana, Gianluca, van Gorsel, Eva, Wohlfahrt, Georg, & Ráduly, Botond. Effect of spatial sampling from European flux towers for estimating carbon and water fluxes with artificial neural networks. United States. https://doi.org/10.1002/2015JG002997
Papale, Dario, Black, T. Andrew, Carvalhais, Nuno, Cescatti, Alessandro, Chen, Jiquan, Jung, Martin, Kiely, Gerard, Lasslop, Gitta, Mahecha, Miguel D., Margolis, Hank, Merbold, Lutz, Montagnani, Leonardo, Moors, Eddy, Olesen, Jørgen E., Reichstein, Markus, Tramontana, Gianluca, van Gorsel, Eva, Wohlfahrt, Georg, and Ráduly, Botond. Fri . "Effect of spatial sampling from European flux towers for estimating carbon and water fluxes with artificial neural networks". United States. https://doi.org/10.1002/2015JG002997.
@article{osti_1402304,
title = {Effect of spatial sampling from European flux towers for estimating carbon and water fluxes with artificial neural networks},
author = {Papale, Dario and Black, T. Andrew and Carvalhais, Nuno and Cescatti, Alessandro and Chen, Jiquan and Jung, Martin and Kiely, Gerard and Lasslop, Gitta and Mahecha, Miguel D. and Margolis, Hank and Merbold, Lutz and Montagnani, Leonardo and Moors, Eddy and Olesen, Jørgen E. and Reichstein, Markus and Tramontana, Gianluca and van Gorsel, Eva and Wohlfahrt, Georg and Ráduly, Botond},
abstractNote = {Abstract Empirical modeling approaches are frequently used to upscale local eddy covariance observations of carbon, water, and energy fluxes to regional and global scales. The predictive capacity of such models largely depends on the data used for parameterization and identification of input‐output relationships, while prediction for conditions outside the training domain is generally uncertain. In this work, artificial neural networks (ANNs) were used for the prediction of gross primary production (GPP) and latent heat flux (LE) on local and European scales with the aim to assess the portion of uncertainties in extrapolation due to sample selection. ANNs were found to be a useful tool for GPP and LE prediction, in particular for extrapolation in time (mean absolute error MAE for GPP between 0.53 and 1.56 gC m −2  d −1 ). Extrapolation in space in similar climatic and vegetation conditions also gave good results (GPP MAE 0.7–1.41 gC m −2  d −1 ), while extrapolation in areas with different seasonal cycles and controlling factors (e.g., the tropical regions) showed noticeably higher errors (GPP MAE 0.8–2.09 gC m −2  d −1 ). The distribution and the number of sites used for ANN training had a remarkable effect on prediction uncertainty in both, regional GPP and LE budgets and their interannual variability. Results obtained show that for ANN upscaling for continents with relatively small networks of sites, the error due to the sampling can be large and needs to be considered and quantified. The analysis of the spatial variability of the uncertainty helped to identify the meteorological drivers driving the uncertainty.},
doi = {10.1002/2015JG002997},
journal = {Journal of Geophysical Research. Biogeosciences},
number = 10,
volume = 120,
place = {United States},
year = {Fri Oct 09 00:00:00 EDT 2015},
month = {Fri Oct 09 00:00:00 EDT 2015}
}

Journal Article:
Free Publicly Available Full Text
Publisher's Version of Record
https://doi.org/10.1002/2015JG002997

Citation Metrics:
Cited by: 57 works
Citation information provided by
Web of Science

Save / Share:

Works referenced in this record:

Temporal and among-site variability of inherent water use efficiency at the ecosystem level: VARIABILITY OF INHERENT WUE
journal, June 2009

  • Beer, C.; Ciais, P.; Reichstein, M.
  • Global Biogeochemical Cycles, Vol. 23, Issue 2
  • DOI: 10.1029/2008GB003233

Remote sensing of annual terrestrial gross primary productivity from MODIS: an assessment using the FLUXNET La Thuile data set
journal, January 2014


Developing an empirical model of phytoplankton primary production: a neural network case study
journal, August 1999


Spatiotemporal patterns of terrestrial gross primary production: A review: GPP Spatiotemporal Patterns
journal, August 2015

  • Anav, Alessandro; Friedlingstein, Pierre; Beer, Christian
  • Reviews of Geophysics, Vol. 53, Issue 3
  • DOI: 10.1002/2015RG000483

Evaluation of ecosystem dynamics, plant geography and terrestrial carbon cycling in the LPJ dynamic global vegetation model
journal, February 2003


A new assessment of European forests carbon exchanges by eddy fluxes and artificial neural network spatialization
journal, April 2003


A full greenhouse gases budget of Africa: synthesis, uncertainties, and vulnerabilities
journal, January 2014


'Breathing' of the terrestrial biosphere: lessons learned from a global network of carbon dioxide flux measurement systems
journal, January 2008

  • Baldocchi, Dennis
  • Australian Journal of Botany, Vol. 56, Issue 1
  • DOI: 10.1071/BT07151

Intercomparison of MODIS albedo retrievals and in situ measurements across the global FLUXNET network
journal, June 2012

  • Cescatti, Alessandro; Marcolla, Barbara; Santhana Vannan, Suresh K.
  • Remote Sensing of Environment, Vol. 121
  • DOI: 10.1016/j.rse.2012.02.019

A comparative analysis of the Global Land Cover 2000 and MODIS land cover data sets
journal, January 2005


Analyzing the causes and spatial pattern of the European 2003 carbon flux anomaly using seven models
journal, January 2008


Mean annual GPP of Europe derived from its water balance: MEAN EUROPEAN GPP
journal, March 2007

  • Beer, C.; Reichstein, M.; Ciais, P.
  • Geophysical Research Letters, Vol. 34, Issue 5
  • DOI: 10.1029/2006GL029006

Recent decline in the global land evapotranspiration trend due to limited moisture supply
journal, October 2010

  • Jung, Martin; Reichstein, Markus; Ciais, Philippe
  • Nature, Vol. 467, Issue 7318
  • DOI: 10.1038/nature09396

Deciphering the components of regional net ecosystem fluxes following a bottom-up approach for the Iberian Peninsula
journal, January 2010


Data-driven diagnostics of terrestrial carbon dynamics over North America
journal, October 2014


River flow forecasting through conceptual models part I — A discussion of principles
journal, April 1970


On the separation of net ecosystem exchange into assimilation and ecosystem respiration: review and improved algorithm
journal, September 2005


A dynamic global vegetation model for studies of the coupled atmosphere-biosphere system: DVGM FOR COUPLED CLIMATE STUDIES
journal, February 2005

  • Krinner, G.; Viovy, Nicolas; de Noblet-Ducoudré, Nathalie
  • Global Biogeochemical Cycles, Vol. 19, Issue 1
  • DOI: 10.1029/2003GB002199

Terrestrial Gross Carbon Dioxide Uptake: Global Distribution and Covariation with Climate
journal, July 2010


The Elements of Statistical Learning
book, January 2001


Solar Radiation and Productivity in Tropical Ecosystems
journal, December 1972

  • Monteith, J. L.
  • The Journal of Applied Ecology, Vol. 9, Issue 3
  • DOI: 10.2307/2401901

Assessing and improving the representativeness of monitoring networks: The European flux tower network example
journal, January 2011

  • Sulkava, Mika; Luyssaert, Sebastiaan; Zaehle, Sönke
  • Journal of Geophysical Research, Vol. 116
  • DOI: 10.1029/2010JG001562

Eddy Covariance
book, January 2012


Seasonal variation of photosynthetic model parameters and leaf area index from global Fluxnet eddy covariance data
journal, January 2011

  • Groenendijk, M.; Dolman, A. J.; Ammann, C.
  • Journal of Geophysical Research, Vol. 116, Issue G4
  • DOI: 10.1029/2011JG001742

Attributing uncertainties in simulated biospheric carbon fluxes to different error sources: ANALYZING ERRORS IN BIOSPHERIC C MODELS
journal, June 2011

  • Lin, J. C.; Pejam, M. R.; Chan, E.
  • Global Biogeochemical Cycles, Vol. 25, Issue 2
  • DOI: 10.1029/2010GB003884

Developing a continental-scale measure of gross primary production by combining MODIS and AmeriFlux data through Support Vector Machine approach
journal, September 2007

  • Yang, Feihua; Ichii, Kazuhito; White, Michael A.
  • Remote Sensing of Environment, Vol. 110, Issue 1
  • DOI: 10.1016/j.rse.2007.02.016

Observing terrestrial ecosystems and the carbon cycle from space
journal, February 2015

  • Schimel, David; Pavlick, Ryan; Fisher, Joshua B.
  • Global Change Biology, Vol. 21, Issue 5
  • DOI: 10.1111/gcb.12822

A continuous measure of gross primary production for the conterminous United States derived from MODIS and AmeriFlux data
journal, March 2010

  • Xiao, Jingfeng; Zhuang, Qianlai; Law, Beverly E.
  • Remote Sensing of Environment, Vol. 114, Issue 3
  • DOI: 10.1016/j.rse.2009.10.013

Global patterns of land-atmosphere fluxes of carbon dioxide, latent heat, and sensible heat derived from eddy covariance, satellite, and meteorological observations
journal, January 2011

  • Jung, Martin; Reichstein, Markus; Margolis, Hank A.
  • Journal of Geophysical Research, Vol. 116
  • DOI: 10.1029/2010JG001566

Vegetation-specific model parameters are not required for estimating gross primary production
journal, November 2014