Artem Smirnov

ST Solar-Terrestrial Sciences

The 2023 Outstanding Student and PhD candidate Presentation (OSPP) Award is awarded to Artem Smirnov for the poster/PICO entitled:

Neural network model of Electron density in the Topside ionosphere (NET) (Smirnov, A.; Shprits, Y.; Lühr, H.; Prol, F.; Berrendorf, M.; Xiong, C.)

Click here to download the poster/PICO file.

Artem Smirnov is a doctoral candidate in Section 2.7, “Space Physics and Space Weather”, at GFZ German Research Centre for Geosciences. He received a joint master’s degree in Geophysics from LMU Munich and TUM before starting his PhD in October 2019. His research interests are primarily focused on satellite data analysis and empirical modeling of plasma populations in the ionosphere and inner magnetosphere of the Earth using machine learning.

At EGU 2023, Artem presented a new data-driven model of the Earth’s topside ionosphere based on neural networks, called NET. The topside ionosphere is critically important for a wide variety of applications, including satellite positioning, as it delays radio signals due to the large number of free electrons. However, this region represents a particular challenge for modeling, due to the non-uniform data coverage and general scarcity of available observations. The developed NET model utilizes 3D radio occultation data sets covering nearly two solar cycles, and is additionally validated against several fully independent in-situ data sets. The results demonstrate that the model captures the effects of various physical processes in the topside ionosphere, and the model predictions are within a factor of 2 from the observations >90% of the time.