A Neural Net Data Science Approach for Inferring Annual CO2 Flux from Long Term Measurements. ...
Inferring CO2 flux by assimilating CO2 observations into ecosystem models have been shown to be largely inconsistent with station observations. An investigation of how the biosphere has reacted to changes in atmospheric CO2 is essential to our understanding of potential climate-vegetation feedbacks....
| Main Author: | |
|---|---|
| Format: | Article in Journal/Newspaper |
| Language: | unknown |
| Published: |
Maryland Shared Open Access Repository
2017
|
| Subjects: | |
| Online Access: | https://dx.doi.org/10.13016/m2cgcl-zeja https://mdsoar.org/handle/11603/20810 |
| Summary: | Inferring CO2 flux by assimilating CO2 observations into ecosystem models have been shown to be largely inconsistent with station observations. An investigation of how the biosphere has reacted to changes in atmospheric CO2 is essential to our understanding of potential climate-vegetation feedbacks. Thus, a global, seasonal to annual investigation into new approaches for calculating CO2-flux is necessary to improve the prediction of annual Net Ecosystem Exchange (NEE). In this study, a Feed Forward Neural Network model is employed to train the prediction of CO2 flux based on station data from the Department of Energy (DOE) Atmospheric Radiation Measurement (ARM) for three different ecosystem sites; an arid plain near Oklahoma City, an arctic tundra at Barrows Alaska, and a tropical rainforest in the Amazon. The ARM program of DOE has been making long term CO2 flux measurements (in addition to an array of other meteorological quantities) at several towers and mobile sites located around the globe at half-hour ... |
|---|