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 main greenhouse gases - methane. The study is based on surface methane data obtained by monitoring dynamics major Arctic Island Belyy, Russia. We used a nonlinear autoregressive neural network with an external input (NARX), and vector regression model. An artificial type NARX was more accurate changes.