A comparison was made of the main transfer functions in the hidden layer of a nonlinear autoregressive neural network with an external input (NARX) to predict changes in the methane content in the surface layer of atmospheric air. Four transfer functions were used: S-type transfer function (LS), S-type hyperbolic tangent transfer function (TS), radial basis transfer function (RB), rectified linear units (LReLU). In general, all models were good at predicting changes in surface methane concentration. The most accurate results were obtained by the model, which using the RB type transfer function.