Automated classification of MESSENGER plasma observations via unsupervised transfer learning
Our methodology demonstrates a proof of concept of the applicability of transfer learning for heliophysics, a machine learning technique where knowledge learned from one task is reused to perform a similar unsupervised learning task with additional fine tuning. We applied an unsupervised clustering...
Saved in:
| Main Authors: | , , , , |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
Frontiers Media S.A.
2025-07-01
|
| Series: | Frontiers in Astronomy and Space Sciences |
| Subjects: | |
| Online Access: | https://www.frontiersin.org/articles/10.3389/fspas.2025.1608091/full |
| Tags: |
Add Tag
No Tags, Be the first to tag this record!
|
| Summary: | Our methodology demonstrates a proof of concept of the applicability of transfer learning for heliophysics, a machine learning technique where knowledge learned from one task is reused to perform a similar unsupervised learning task with additional fine tuning. We applied an unsupervised clustering algorithm, initially trained on data from the Magnetospheric Multiscale (MMS) mission at Earth, to MErcury Surface, Space ENvironment, GEochemistry, and Ranging (MESSENGER) observationsat Mercury to identify three distinct plasma regions: magnetosphere, magnetosheath, and solar wind. While our method requires modifications to the model from post-cleaning rules due to instrument effects, it allows for rapid classification using just a few examples to generate post-cleaning rules. Since there is no ground truth or standardized validation set to compare with, we compare our model’s result with published magnetopause and bow shock lists and find that the clustering algorithm is agreement with 67% of bow shock crossings and 74% of magnetopause crossings. These findings highlight the potential use of clustering algorithms across multiple planetary environments. |
|---|---|
| ISSN: | 2296-987X |