Forecasting Local Ionospheric Parameters Using Transformers

TL;DR

This paper introduces LIFT, a transformer-based neural network model that forecasts key ionospheric parameters with high accuracy and uncertainty quantification, incorporating exogenous variables for improved predictions across locations and times.

Contribution

The paper presents a novel transformer-based model, LIFT, for ionospheric forecasting that integrates exogenous variables and demonstrates generalization to new locations and times.

Findings

LIFT provides accurate 24-hour ionospheric forecasts.

The model effectively quantifies uncertainty in predictions.

LIFT outperforms the IRI model in performance metrics.

Abstract

We present a novel method for forecasting key ionospheric parameters using transformer-based neural networks. The model provides accurate forecasts and uncertainty quantification of the F2-layer peak plasma frequency (foF2), the F2-layer peak density height (hmF2), and total electron content (TEC) for a given geographic location. It includes a number of exogenous variables, including F10.7cm solar flux and disturbance storm time (Dst). We demonstrate how transformers can be trained in a data assimilation-like fashion that uses these exogenous variables along with naive predictions from climatology to generate 24-hour forecasts with nonparametric uncertainty bounds. We call this method the Local Ionospheric Forecast Transformer (LIFT). We demonstrate that the trained model can generalize to new geographic locations and time periods not seen during training, and we compare its performance to that of the International Reference Ionosphere (IRI) using CCIR coefficients.