Abstract
The nonlinearity of the relationship between CO2 flux and other micrometeorological variables flux parameters limits the applicability of carbon flux models to accurately estimate the flux dynamics. However, the need for carbon dioxide (CO2) estimations covering larger areas and the limitations of the point eddy covariance technique to address this requirement necessitates the modeling of CO2 flux from other micrometeorological variables. Artificial neural networks (ANN) are used because of their power to fit highly nonlinear relations between input and output variables without explaining the nature of the phenomena. This paper applied a multilayer perception ANN technique with error back propagation algorithm to simulate CO2 flux on three different ecosystems (forest, grassland and cropland) in ChinaFLUX. Energy flux (net radiation, latent heat, sensible heat and soil heat flux) and temperature (air and soil) and soil moisture were used to train the ANN and predict the CO2 flux. Diurnal half-hourly fluxes data of observations from June to August in 2003 were divided into training, validating and testing. Results of the CO2 flux simulation show that the technique can successfully predict the observed values with R 2 value between 0.75 and 0.866. It is also found that the soil moisture could not improve the simulative accuracy without water stress. The analysis of the contribution of input variables in ANN shows that the ANN is not a black box model, it can tell us about the controlling parameters of NEE in different ecosystems and micrometeorological environment. The results indicate the ANN is not only a reliable, efficient technique to estimate regional or global CO2 flux from point measurements and understand the spatiotemporal budget of the CO2 fluxes, but also can identify the relations between the CO2 flux and micrometeorological variables.
Article PDF
Similar content being viewed by others
Explore related subjects
Discover the latest articles, news and stories from top researchers in related subjects.Avoid common mistakes on your manuscript.
References
Yu G R, Zhang L M, Sun X M. Advance in carbon flux observation and research in Asia. Sci China Ser D-Earth Sci, 2005, 48(Supp I): 1–16
Lek S, Guegan J F. Artificial neural networks as a tool in ecological modeling and introduction. Ecol Odel, 1999, 120: 65–73
Lek S, Delacoste M, Baran P, et al. Application of neural networks to modeling nonlinear relationships in ecology. Ecological Modeling, 1996, 90: 39–52
Francl L J, Panigrahi S. Artificial neural network models of wheat leaf wetness. Agricultural and Forest Meteorology, 1997, 88: 57–65
Elizondo D, Hoogenboom G, MeClendon R W. Development of a neural network model to predict daily solar radiation. Agri For Meteorol, 1994, 71: 115–132
Van Wijk M T, Bouten W. Water and carbon fluxes above European coniferous forest modeled with artificial neural networks. Ecological Modeling, 1999, 120: 181–197
Papale D, Valentini R. A new assessment of European forests carbon exchanges by eddy fluxes and artificial neural network spatialization. Global Change Biology, 2003, 9(4): 525–535
Assefa M M, Rondney S H. Artificial neural network application for multi-ecosystem carbon flux simulation. Ecological Modeling, 2005, 189: 305–314
Van Wijk M T, Bouten, Verstraten J M. Comparison of different modeling strategies for simulating gas exchange of a Douglas-fir forest. Ecological Modeling, 2002, 158: 63–81
Wang K C, Zhou X J. Using satellite remotely sensed data to retrieve sensible and latent heat fluxes: a review. Advance in Earth Sciences, 2005, 20(1): 42–48
Aubinet M, Grelle A, Ibrom A, et al. Estimates of the annual net carbon and water exchange of forests: the EUROFLUX methodology. Advance in Ecological Research, 2000, (30): 113–175
Olson R J, Hollady S K, Cook R B, et al. Fluxnet: Database of Fluxes. Site Characteristics, and Flux-Community Information. Oak Ridge National Laboratory. ORNL/TM-2003/204.
Guan D X, Wu J B, Yu G R, et al. Meteorological control on CO2 flux above broad-leaved Korean pine mixed forest in Changbai Mountains. Sci China Ser D-Earth Sci, 2005, 48(Supp I): 123–132
Qing Z, Yu Q, Xu S H. Water, heat fluxes and water use efficiency measurement and modeling above a farmland in the North China Plain. Sci China Ser D-Earth Sci, 2005, 48(Supp.I): 207–217
Xu S X, Zhao X Q, Fu Y L. Characterizing CO2 fluxes for growing and non-growing seasons in a shrub ecosystem on the Qinghai-Tibet Plateau. Sci China Ser D-Earth Sci, 2005, 48(Supp I): 133–140
Gevrey M, Diomopoulos I, Lek S. Review and comparison of methods to study the contribution of variables in artificial neural network models. Ecological Modeling, 2003, (160): 249–264
Julian D O, Michael K J, Russell G D. An accurate comparison of methods for quantifying variable importance in artificial neural networks using simulated data. Ecological Modeling, 2004, (178): 389–397
Valentini R, ed. Fluxes of Carbon, Water, Energy of European Forests: Ecological Studies. Vol. 163. Berlin: Springer, 2003
Author information
Authors and Affiliations
Corresponding author
Rights and permissions
About this article
Cite this article
He, H., Yu, G., Zhang, L. et al. Simulating CO2 flux of three different ecosystems in ChinaFLUX based on artificial neural networks. SCI CHINA SER D 49 (Suppl 2), 252–261 (2006). https://doi.org/10.1007/s11430-006-8252-z
Received:
Accepted:
Issue Date:
DOI: https://doi.org/10.1007/s11430-006-8252-z