CLARE: Classification-based Regression for Electron Temperature Prediction
This provides a high-accuracy model for space weather prediction using publicly available data, addressing an underexplored area in the literature.
The authors tackled the problem of predicting electron temperature in the Earth's plasmasphere, achieving a 6.46% improvement in accuracy over traditional regression and 69.67% accuracy within 10% of ground truth on a test set.
Electron temperature (Te) is an important parameter governing space weather in the upper atmosphere, but has historically been underexplored in the space weather machine learning literature. We present CLARE, a machine learning model for predicting electron temperature in the Earth's plasmasphere trained on AKEBONO (EXOS-D) satellite measurements as well as solar and geomagnetic indices. CLARE uses a classification-based regression architecture that transforms the continuous Te output space into 150 discrete classification intervals. Training the model on a classification task improves prediction accuracy by 6.46% relative compared to a traditional regression model while also outputting uncertainty estimation information on its predictions. On a held out test set from the AKEBONO data, the model's Te predictions achieve 69.67% accuracy within 10% of the ground truth and 46.17% on a known geomagnetic storm period from January 30th to February 7th, 1991. We show that machine learning can be used to produce high-accuracy Te models on publicly available data.