Short-term forecast the dynamics of changes in the surface concentration of methane using a non-linear autoregressive neural network with external input and vector autoregression model

In our work, we compared two approaches for predicting changes in the concentration of one of the main greenhouse gases - methane. The study is based on surface methane concentration data obtained by monitoring the dynamics of changes in major greenhouse gases on the Arctic Island Belyy, Russia. We used a nonlinear autoregressive neural network with an external input (NARX), and a vector regression model. An artificial neural network type NARX was more accurate for predicting methane concentration changes.