Predicting carbon dioxide and energy fluxes across global FLUXNET sites with
regression algorithms
-
Published:2016-07-29
Issue:14
Volume:13
Page:4291-4313
-
ISSN:1726-4189
-
Container-title:Biogeosciences
-
language:en
-
Short-container-title:Biogeosciences
Author:
Tramontana Gianluca, Jung Martin, Schwalm Christopher R., Ichii Kazuhito, Camps-Valls GustauORCID, Ráduly Botond, Reichstein Markus, Arain M. Altaf, Cescatti AlessandroORCID, Kiely Gerard, Merbold LutzORCID, Serrano-Ortiz Penelope, Sickert Sven, Wolf SebastianORCID, Papale DarioORCID
Abstract
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.
Publisher
Copernicus GmbH
Subject
Earth-Surface Processes,Ecology, Evolution, Behavior and Systematics
Reference64 articles.
1. Amiro, B. D., Barr, A. G., Barr, J. G., Black, T. A., Gracho, R., Brown, M., Chen, J., Clark, K. L., Davis, K. J., Desai, A. R., Dore, S., Engel, V., Fuentes, J. D., Goldstein, A. H., Goulden, M. L., Kolb, T. E., Lavigne, M. B., Law, B. E., Margolis, H. A., Martin, T., McCaughey, J. H., Misson, L., Montes, Helu, M., Noormets, A., Randerson, J. T., Starr, G., and Xiao, J.: Ecosystem carbon dioxide fluxes after disturbance in forests of North America, J. Geophys. Res-Biogeo., 115, G00K02, https://doi.org/10.1029/2010JG001390, 2010. 2. Alonso Fernández, J. R., Díaz-Muñiza, C., Garcia Nieto, P. J., de Cos, Juez, F. J., Sánchez, Lasheras, F., and Roqueñíc, M. N.: Forecasting the cyanotoxins presence in fresh waters: A new model based on genetic algorithms combined with the MARS technique, Ecol. Eng., 53, 68–78, https://doi.org/10.1016/j.ecoleng.2012.12.015, 2013. 3. Anav, A., Friedlingstein, P., Kidston, M., Bopp, L., Ciais, P., Cox, P., Jones, C., Jung, M., Myneni, R., and Zhu, Z.: Evaluating the land and ocean components of the global carbon cycle in the cmip5 earth system models, J. Climate, 26, 6801–6843, https://doi.org/10.1175/JCLI-D-12-00417.1, 2013. 4. Aubinet, M., Vesala, T., and Papale, D.: Eddy Covariance: A Practical Guide to Measurement and Data Analysis, Springer, Dordrecht Heidelberg London New York, 460 pp., 2012. 5. Baldocchi, D.: Breathing of the terrestrial biosphere: lessons learned from a global network of carbon dioxide flux measurement systems, Aust. J. Bot., 56, 1–26, https://doi.org/10.1071/BT07151, 2008.
Cited by
441 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
|
|