Speaker
Description
A series of PCA-based models were previously developed to forecast the total electron content (TEC) variations caused by space weather. The earlier versions used linear regression models to build a forecast, which later was replaced by neural networks (NN). Such models were tested on the TEC data obtained for a European mid-latitudinal region (Iberian Peninsula).
In this work we present a next generation of such models that now have several branches. First of all, we tested different NN algorithms (e.g., LSTM and CNN) to find a better one that suits our approach to model specific ionospheric parameters. We investigated the applicability of such approach to forecast other ionospheric parameters, like NmF2. Also, we compared the performance of the model using data obtained at locations that are almost opposite in longitude (European vs American).
| Do you plan to attend in-person or online? | In-person |
|---|
