Adaptive techniques to predict the N2O emission in a corn field under different fertilizer management practices and external factors.
Global warming is one of the largest environmental issues these days and the increasing greenhouse gases(GHGs) emission such as CO2, CH4 and N2O is the leading reason for global warming. The main sources of CH4 emission are rice cultivating systems and cattle rearing, meanwhile, N2O mainly come from the application of fertilizers. Many factors in the fertilizer management practices, as well as environmental factors, could affect the N2O emission therefore the carbon foot print. In this research, external factors such as temperature, irrigation, soil texture, etc. will be modeled simultaneously in a mathematical model to illustrate the N2O emission during the agriculture process. Machine learning will be implemented to tune the parameters of the mathematical model as well as optimize the fertilizer management practices and external conditions to minimize the N2O emission during the fertilizer application process.