Team Title: Team Modelling and Forecasting Ionospheric TEC/Scintillations based on Artificial Intelligence Methods
Navigation and/or Communications
Keywords (Activity Type):
Modeling, Forecasting, Assessment
With the advent of multi-instrument GNSS observations the characterization of ionospheric variability accurately is evident. The tools and algorithms those can provide reliable ionospheric parameters to nowcast and forecast is greatly understood. The chaotic nature of ionosphere is greatly modeled by understanding the influences of external drivers namely solar and geomagnetic is observed. It is also found that short-term and long-term total electron content forecasting in proper spatial and temporal scales is to be addressed. The idea is to utilize the data assimilation, machine learning and artificial intelligence techniques in total electron content forecasting. To develop a hybrid total electron content short term forecasting model by combining data assimilation and machine learning is the discern task.
1. Low-latitude ionospheric short-term spatial TEC forecasting by driving assimilated outputs to machine learning approach.
2. Ionospheric spatial gradients forecasting using deep learning methods and understanding their impacts on horizontal and vertical protection limits.
3. Forecasting of Ionospheric scintillations in regional scale through group of GNSS receiver network datasets.
4. Assessment of forecast metrics to understand reliable ionospheric forecasts.
Understand and forecast the global state of the ionosphere, Assessment of modeling capability of global and regional vertical TEC on different spatial and temporal scales, Assessment of predictive capabilities of ionosphere scintillations
Cluster with overlapping topics:
G1: Geomagnetic environment, G2B: Ionosphere variability
Link to external website: