Predicting carbon dioxide and energy fluxes across global FLUXNET sites with regression algorithms
Top Cited Papers
Open Access
- 29 July 2016
- journal article
- research article
- Published by Copernicus GmbH in Biogeosciences (online)
- Vol. 13 (14), 4291-4313
- https://doi.org/10.5194/bg-13-4291-2016
Abstract
Spatio-temporal fields of land–atmosphere fluxes derived from data-driven models can complement simulations by process-based land surface models. While a number of strategies for empirical models with eddy-covariance flux data have been applied, a systematic intercomparison of these methods has been missing so far. In this study, we performed a cross-validation experiment for predicting carbon dioxide, latent heat, sensible heat and net radiation fluxes across different ecosystem types with 11 machine learning (ML) methods from four different classes (kernel methods, neural networks, tree methods, and regression splines). We applied two complementary setups: (1) 8-day average fluxes based on remotely sensed data and (2) daily mean fluxes based on meteorological data and a mean seasonal cycle of remotely sensed variables. The patterns of predictions from different ML and experimental setups were highly consistent. There were systematic differences in performance among the fluxes, with the following ascending order: net ecosystem exchange (R2 < 0.5), ecosystem respiration (R2 > 0.6), gross primary production (R2> 0.7), latent heat (R2 > 0.7), sensible heat (R2 > 0.7), and net radiation (R2 > 0.8). The ML methods predicted the across-site variability and the mean seasonal cycle of the observed fluxes very well (R2 > 0.7), while the 8-day deviations from the mean seasonal cycle were not well predicted (R2 < 0.5). Fluxes were better predicted at forested and temperate climate sites than at sites in extreme climates or less represented by training data (e.g., the tropics). The evaluated large ensemble of ML-based models will be the basis of new global flux products.Keywords
This publication has 60 references indexed in Scilit:
- Evaluating the Land and Ocean Components of the Global Carbon Cycle in the CMIP5 Earth System ModelsJournal of Climate, 2013
- Decomposition of the mean squared error and NSE performance criteria: Implications for improving hydrological modellingJournal of Hydrology, 2009
- Estimation of net ecosystem carbon exchange for the conterminous United States by combining MODIS and AmeriFlux dataAgricultural and Forest Meteorology, 2008
- 'Breathing' of the terrestrial biosphere: lessons learned from a global network of carbon dioxide flux measurement systemsAustralian Journal of Botany, 2008
- Developing a continental-scale measure of gross primary production by combining MODIS and AmeriFlux data through Support Vector Machine approachRemote Sensing of Environment, 2007
- Development of pedotransfer functions using a group method of data handling for the soil of the Pianura Padano–Veneta region of North Italy: water retention propertiesGeoderma, 2005
- Overview of the radiometric and biophysical performance of the MODIS vegetation indicesRemote Sensing of Environment, 2002
- The random subspace method for constructing decision forestsIeee Transactions On Pattern Analysis and Machine Intelligence, 1998
- Multivariate Adaptive Regression SplinesThe Annals of Statistics, 1991
- River flow forecasting through conceptual models part I — A discussion of principlesJournal of Hydrology, 1970