Microsoft Research uses machine learning to predict power grid space weather risk, covering 66,935 substations in the US
Microsoft Research developed an end-to-end machine learning pipeline that combines solar wind observations, AE and Dst index forecasts, geological conductivity, and power grid data to generate local space weather risk estimates 30-60 minutes in advance for 66,935 substations in the continental United States.
Return to original text
A short introduction is retained here; the full text from the source website is not reposted. For specific wording and subsequent updates, please refer to the original article.
Open AIHOT original