Quantifying biosphere-atmosphere exchange of CO2 using eddy covariance, wavelet denoising, neural networks, and multiple regression models

Net ecosystem exchange of CO2 (NEE) over a temperate peatland in northwestern Turkey was directly measured using the eddy covariance (EC) method for 590 days. Both the response variables of diurnal and nocturnal NEE (NEEd and Reco-n) and the explanatory variables of latent heat (LE), relative humidity (RH), and atmospheric CO2 and H2O concentrations (AtmCO(2) and AtmH(2)O) were denoised with discrete wavelet transform (DWT) using coiflet (coif10-6). Denoised NEE fluxes and their temporal components were modeled using multiple linear regression (MLR), polynomial regression (PR) and artificial neural network (ANN) models as a function of LE, RH, AtmCO(2), AtmH(2)O, air temperature (T-air), day of year (DOY), and local time. Peak NEEd flux, and peak Reco-n efflux were 0.37 mg CO2 m(-2) s(-1) in late July and 0.27 mg CO2 m(-2) s(-1) in mid-August. Mean annual NEE was estimated at -1157 g CO2 m(-2) which is in agreement with previous results of peatland studies. The use of DWT-augmented ANN, MLR and PR models significantly increased predictive power and reduced uncertainties in predicting the temporal dynamics of the biosphere-atmosphere CO2 exchange, relative to the models without DWT denoising. Out of 28 DWT-augmented ANNs, multilayer perceptron (MLP) and recurrent network (RN) models were the best diurnal and nocturnal ones, respectively, based on accuracy metrics derived from training, cross-validation and independent validation. Among the DWT-based ANN, MLR and PR models, diurnal MLP and nocturnal MLR outperformed the others. Wavelet-augmented ANN and MLR models appear to be a promising tool to quantify diurnal and nocturnal NEE dynamics, respectively. (C) 2012 Elsevier B.V. All rights reserved.