Bibliographic Details
| Title: |
An Explainable Deep-learning Model of Proton Auroras on Mars |
| Authors: |
Dattaraj B. Dhuri, Dimitra Atri, Ahmed AlHantoobi |
| Source: |
The Planetary Science Journal, Vol 5, Iss 6, p 136 (2024) |
| Publisher Information: |
IOP Publishing, 2024. |
| Publication Year: |
2024 |
| Collection: |
LCC:Astronomy |
| Subject Terms: |
Mars, Solar wind, Planetary magnetospheres, Aurorae, Neural networks, Astronomy, QB1-991 |
| More Details: |
Proton auroras are widely observed on the dayside of Mars, identified as a significant intensity enhancement in the hydrogen Ly α (121.6 nm) emission at altitudes of ∼110 and 150 km. Solar wind protons penetrating as energetic neutral atoms into Mars’ thermosphere are thought to be primarily responsible for these auroras. Recent observations of spatially localized “patchy” proton auroras suggest a possible direct deposition of protons into Mars’ atmosphere during unstable solar wind conditions. Improving our understanding of proton auroras is therefore important for characterizing the interaction of the solar wind with Mars’ atmosphere. Here, we develop a first purely data-driven model of proton auroras using Mars Atmosphere and Volatile Evolution (MAVEN) in situ observations and limb scans of Ly α emissions between 2014 and 2022. We train an artificial neural network that reproduces individual Ly α intensities and relative Ly α peak intensity enhancements with Pearson correlations of ∼94% and ∼60% respectively for the test data, along with a faithful reconstruction of the shape of the observed altitude profiles of Ly α emission. By performing a Shapley Additive Explanations (SHAP) analysis, we find that solar zenith angle, solar longitude, CO _2 atmosphere variability, solar wind speed, and temperature are the most important features for the modeled Ly α peak intensity enhancements. Additionally, we find that the modeled peak intensity enhancements are high for early local-time hours, particularly near polar latitudes, and the induced magnetic fields are weaker. Through SHAP analysis, we also identify the influence of biases in the training data and interdependences between the measurements used for the modeling, and an improvement of those aspects can significantly improve the performance and applicability of the ANN model. |
| Document Type: |
article |
| File Description: |
electronic resource |
| Language: |
English |
| ISSN: |
2632-3338 |
| Relation: |
https://doaj.org/toc/2632-3338 |
| DOI: |
10.3847/PSJ/ad45ff |
| Access URL: |
https://doaj.org/article/1fd5cb05ab9a4d28a659fb3f01100038 |
| Accession Number: |
edsdoj.1fd5cb05ab9a4d28a659fb3f01100038 |
| Database: |
Directory of Open Access Journals |
