Development of a Machine Learning Model for Martian Electron Density using MGS Data
- Paper number
IAC-21,A3,3A,2,x63979
- Author
Ms. Noora Alameri, United Arab Emirates, Sharjah Academy for Astronomy, Space Sciences and Technology (SAASST)
- Coauthor
Mr. Abdollah Darya, United Arab Emirates, Sharjah Academy for Astronomy, Space Sciences and Technology (SAASST)
- Coauthor
Mr. Ibrahim Alsabt, United Arab Emirates, Sharjah Academy for Astronomy, Space Sciences and Technology (SAASST)
- Coauthor
Dr. Mubasshir Shaikh, United Arab Emirates, Sharjah Academy for Astronomy, Space Sciences and Technology (SAASST)
- Coauthor
Prof. Ilias Fernini, United Arab Emirates, Sharjah Academy for Astronomy, Space Sciences and Technology (SAASST)
- Coauthor
Prof. Hamid Al Naimiy, United Arab Emirates, Sharjah Academy for Astronomy, Space Sciences and Technology (SAASST)
- Year
2021
- Abstract
The availability of Martian atmospheric data provided by several Martian missions broadened the opportunity to investigate and study the uncharacterized states/patterns of the Martian ionosphere. As such, ionospheric models play a crucial part in improving our understanding of ionospheric behaviour in response to different spatial, temporal, and space weather conditions. This study utilizes data from the Mars Global Surveyor (MGS) mission to construct an electron density prediction model of the Martian ionosphere between 60 and 85 degrees latitude, using machine learning. The performance of different machine learning models was compared in terms of root mean square error, coefficient of determination, and mean absolute error. Out of all the evaluated models, the bagged regression trees method performed best. The final prediction model serves as a flexible Martian electron density prediction model that requires a minimal number of inputs while achieving good prediction performance.
- Abstract document
- Manuscript document
IAC-21,A3,3A,2,x63979.pdf (🔒 authorized access only).
To get the manuscript, please contact IAF Secretariat.