The geomagnetic storm and Kp prediction using Wasserstein transformer
This work addresses geomagnetic storm prediction for space weather applications, representing an incremental improvement by combining machine learning with traditional models.
The paper tackles geomagnetic activity forecasting by developing a multimodal Transformer framework that integrates satellite measurements, solar images, and Kp time series to predict the 3-day and 5-day planetary Kp index, demonstrating performance comparable to the NOAA model in capturing both quiet and storm phases.
The accurate forecasting of geomagnetic activity is important. In this work, we present a novel multimodal Transformer based framework for predicting the 3 days and 5 days planetary Kp index by integrating heterogeneous data sources, including satellite measurements, solar images, and KP time series. A key innovation is the incorporation of the Wasserstein distance into the transformer and the loss function to align the probability distributions across modalities. Comparative experiments with the NOAA model demonstrate performance, accurately capturing both the quiet and storm phases of geomagnetic activity. This study underscores the potential of integrating machine learning techniques with traditional models for improved real time forecasting.