Multiscale Geoeffectiveness Forecasting: Upgrading the DAGGER Pipeline

Sahiti Yerramilli, Banafsheh Ferdousi, Panagiotis Tigas

Abstract:

To safeguard critical infrastructure against space weather hazards such as geomagnetically induced currents, we need to develop operational forecasting tools. Specifically, these tools need to (i) be computationally fast and inexpensive, (ii) resolve signatures over a range of length and time scales, and (iii) be actionable, i.e., to include their uncertainty and an appropriate lead-time so that informed decisions can be made. To address this need for a lightweight, multiscale, ground magnetic perturbation forecasting tool, the Deep leArninG Geomagnetic pErtuRbation (DAGGER) pipeline was created in 2020 during the Frontier Development Lab (FDL) research sprint. The core of the pipeline leverages spherical harmonic basis functions to predict magnetic perturbations at both global and local scales.

This year, The FDL-X program has focused on elevating DAGGER's technical readiness and integrating it across other FDL forecasting and data product modules. We present an updated DAGGER workflow that incorporates additional physical processes along with improvements to the deep learning scheme. Specifically, DAGGER now ingests magnetosphere-ionosphere contextual data, extends its forecast horizon by consuming solar remote sensing measurements, and quantifies uncertainty in forecasts. These upgrades enable DAGGER to facilitate real-time deployment and integration with Sun-side and Earth-side modules.
This work has been enabled by FDL-X (fdlxhelio.org); a derivative of Frontier Development Lab (FDL.ai); as a public/private partnership between NASA, Trillium Technologies and commercial AI partners Google Cloud and Nvidia.