Logo
ScienceStack
Table of Contents
Fetching ...
Sign In

CLARE: Classification-based Regression for Electron Temperature Prediction

Michael Liang, Blake DeHaas, Naomi Maruyama, Xiangning Chu, Takumi Abe, Koh-Ichiro Oyama

Abstract

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.

CLARE: Classification-based Regression for Electron Temperature Prediction

Abstract

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.
Paper Structure (15 sections, 5 equations, 7 figures, 4 tables)

This paper contains 15 sections, 5 equations, 7 figures, 4 tables.

Table of Contents

  1. Introduction
  2. Dataset
  3. Model
  4. Results
  5. Model Performance
  6. Uncertainty Estimation Capabilities
  7. Impact of Discrete and Continuous Training Objective
  8. Impact of Spatial and Solar Features
  9. Event Analysis
  10. Discussion
  11. Conclusion
  12. Titheridge and Titheridge-IRI verification
  13. Titheridge Model
  14. Model performance on diurnal filtered dataset
  15. Titheridge-IRI methodology

Figures (7)

  • Figure 1: The distributions of in situ observations of the electron temperature (Te) with respect to (a) L shell (between 1 and 12), (b) MLAT (between -90° to 90°), and (c) GMLT. The colorbar shows the number of observations in each bin on a log10 scale.
  • Figure 2: Model architecture for CLARE. The model consists of multiple feedforward blocks, with a detailed view of a single feedforward block shown on the right. Gray components represent neural network layers, while yellow components indicate input data and output logits.
  • Figure 3: Correlation between observed and predicted electron temperature on the (a) test dataset of 50,000 randomly held out samples and (b) the held out known solar storm period (January 30th through February 7th, 1991).
  • Figure 4: Prediction accuracy of CLARE within 10% of observed electron temperature against Titheridge and Titheridge-IRI baselines on test-quiet and test-storm sets.
  • Figure 5: (a) Low confidence probability distribution during high solar storm activity time instant compared to (b) high confidence probability distribution during quiet solar storm activity time instant.
  • ...and 2 more figures