EGU General Assembly 2020
© Author(s) 2020. This work is distributed under
the Creative Commons Attribution 4.0 License.

Development and investigation of a deep learning based method for TEC map completion

Mingwu Jin1, Yang Pan1, Shunrong Zhang2, and Yue Deng1
Mingwu Jin et al.
  • 1University of Texas at Arlington, Physics, United States of America (
  • 2Massachusetts Institute of Technology, Haystack Observatory, United States of America (

Because of the limited coverage of receiver stations, current measurements of Total Electron Content (TEC) by ground-based GNSS receivers are not complete with large portions of data gaps. The processing to obtain complete TEC maps for space science research is time consuming and needs the collaboration of five International GNSS Service (IGS) Ionosphere Associate Analysis Centers (IAACs) to use different data processing and filling algorithms and to consolidate their results into final IGS completed TEC maps. In this work, we developed a Deep Convolutional Generative Adversarial Network (DCGAN) and Poisson blending model (DCGAN-PB) to learn IGS completion process for automatic completion of TEC maps. Using 10-fold cross validation of 20-year IGS TEC data, DCGAN-PB achieves the average root mean squared error (RMSE) about 4 absolute TEC units (TECu) of the high solar activity years and around 2 TECu for low solar activity years, which is about 50% reduction of RMSE for recovered TEC values compared to two conventional single-image inpainting methods. The developed DCGAN-PB model can lead to an efficient automatic completion tool for TEC maps.

How to cite: Jin, M., Pan, Y., Zhang, S., and Deng, Y.: Development and investigation of a deep learning based method for TEC map completion, EGU General Assembly 2020, Online, 4–8 May 2020, EGU2020-11541,, 2020

This abstract will not be presented.