Authors: Lois J. Landwer(CIRES/NOAA), Hazel Bain(CIRES/NOAA), Mark Miesch (CIRES/NOAA), George Millward (CIRES/NOAA), Enrico Camporeale (CIRES/NOAA), Eric Adamson (NOAA)

Space Weather Prediction Center(SWPC) in NOAA plans to operationalize machine learning(ML) model for use with the Space Weather Follow On Lagrange 1 (SWFO-L1) data to enhance forecaster situational awareness. SWFO-L1 mission is a deep-space mission operating in a Lissajous orbit at the Sun-Earth Lagrange 1 (L1) point, enabling upstream measurements of solar wind disturbances before they reach Earth. It will provide continuous measurements of the sun’s corona and of the solar wind at the L1 point and transmit continuous real-time data to Earth. It is scheduled for launch in 2025. As part of this plan, we validated a Gaussian process ML model developed by Camporeale et al. (2017) using DSCOVR and ACE data. SWFO-L1 will replace ACE’s and DSCOVR’s monitoring of solar wind, energetic particles, and the interplanetary magnetic field. This ML model is a four-category classification algorithm for the solar wind, previously adopted in Xu and Borovsky (2015): ejecta, coronal hole origin plasma, streamer belt origin plasma, and sector reversal origin plasma.  The algorithm is trained and tested on a labeled portion of the OMNI data set identifying the wind regime based on several parameters, including in-situ observations of wind speed, proton temperature standard deviation, temperature ratio, proton specific entropy, and Alfven speed, as well as non-in-situ data on sunspot number and solar radio flux.