Deadline for abstracts submission: June 15, 2025.
More details: https://bss2025.ingv.it/
The chairs are:
- Jade Morton (Univ. of Colorado, US)
- Claudio Cesaroni (INGV)
- Maria Graciela Molina (FACET-UNT, Argentina)
The ionosphere’s impact on radio propagation is well-established, but accurately modeling these phenomena remains a challenge due to their complexity, many unknown aspects, and the incomplete understanding of ionospheric processes. Over the past few decades, advanced statistical and machine learning techniques have found widespread application across scientific fields, offering powerful tools to address complex physical scenarios that require more flexible and sophisticated modeling. Key advancements include uncovering correlations between diverse data sets and enabling computationally efficient predictions.
The application of these techniques to geosciences has evolved from a “proof of concept” phase to one where real-world research and operational applications are now possible. This session aims to showcase the current and next phase of applying advanced statistical and machine learning methods to ionospheric studies. Presentations will focus on using these techniques for ionospheric characterization, nowcasting and forecasting, and understanding their effects on radio propagation.
We invite contributions that explore the full spectrum of data science applied to the ionosphere, from data collection and management to analysis and communication. Topics of interest include, but are not limited to, efficient data management, correlation analysis between various ionospheric phenomena, prediction and forecasting of critical ionospheric variables using data-driven models, establishing causal relationships between ionospheric data and other phenomena, and comparing observed versus model-generated ionospheric data. We particularly encourage innovative ideas on how data science and machine learning can reshape the future of ionospheric research.
