Mackey, Hwang, Orenstein take prizes in Sub-Seasonal Climate Forecast Rodeo

Lester Mackey, Jessica Hwang, and Paulo Orenstein, in joint work with AER climatologist Judah Cohen and MIT professor Ernest Fraenkel, have completed a year-long real-time forecasting competition to predict temperature and precipitation in the western United States. Seeking  crowdsourced advancements to improve the ability of the US Bureau of Reclamation (USBR) to anticipate droughts, floods, and other wet weather extremes, the judging panel awarded their team first prize in 2-to-4 week temperature forecasting, second prize in 4-to-6 week precipitation forecasting, and first prize again for temperature hindcasts.  A description of the team's final forecasting system which resulted in this hard-won achievement can be found in “Improving Subseasonal Forecasting in the Western U.S. with Machine Learning”.