Methane (CH4) emissions from wetland ecosystems exert large positive feedbacks to the global climate system. However, the estimation of wetland CH4 emissions at the global scale still has large uncertainties. Here we develop a predictive model of CH4 emissions using an artificial neural network (ANN) approach and available field observations of CH4 fluxes. This study first uses an ANN approach to find the optimal nonlinear regression between CH4 fluxes and key environmental controls. Driven with the spatially explicit data of climate, hydrology and soil properties, the developed ANN is then extrapolated to the global scale to estimate wetland CH4 emissions during a historical period 1979-2018 and a future period of 2006-2099. The entire simulation was conducted in a Linux environment. The supercomputing was provided by the Rosen Center for Advanced Computing at Purdue University. The ANN model was achieved using Matlab. The input data, output data and visualizations were processed using (Interactive Data Language (IDL). In this data archive, we provide all data related to the manuscript "Inventorying Global Wetland Methane Emissions Based on In Situ Data and an Artificial Neural Network Approach".
Cite this work
Researchers should cite this work as follows:
- Liu, L., Zhuang, Q. (2020). Data of global wetland methane emissions from artificial neural network modeling v1.0. Purdue University Research Repository. doi:10.4231/3YX4-EY30
The data are from one manuscript under review in Global Biogeochemical Cycles (GBC). If you want to use the data prior to publication of the manuscript, please contact the author for details.