Analysis of Time Series of Greenhouse Gas Concentrations in the Russian Arctic Using the Artificial Neural Networks.

The work is devoted to the forecasting of the time series by artificial neural networks (ANNs). The data were obtained as a result of the monitoring of greenhouse gases on Belyi Island, Yamalo-Nenetsky AO, Russia. For prediction, a model based on a Nonlinear Autoregressive Neural Network with an External Input (NARX) and Multi-Layer Perceptron (MLP) was used. Based on the concentrations of greenhouse gas methane, a forecast for a certain time interval was done, and a time horizon was established for the forecasting. The model based on the ANN type NARX showed the best results. [ABSTRACT FROM AUTHOR]