Item

Abstract

Forecasting the ambient solar wind several days in advance still proves extremely difficult. In fact, state-of-the-art models (either physics-based or based on machine learning) do not consistently outperform simple baseline predictions based on 1-day persistence or 27-day recurrence. In turn, our inability to precisely forecast the ambient solar wind impacts both the accuracy and the lead-time of every Geospace and Magnetosphere-Ionosphere-Thermosphere model used for space weather purposes.Here, we present a new physics-informed machine learning model that aims to predict the ambient solar wind up to 5 days ahead, by combining Global Oscillation Network Group (GONG) observations and physics-based hydrodynamic propagation models, essentially in a grey-box approach. The model learns a coronal model in a completely data-driven fashion, by using ACE observations as its target, and propagates the solar wind to L1 by using a physics-based model.