Southeastern Florida has seen unprecedented rainfall events in the past year, with models failing to accurately predict the amount of precipitation over the region. This work will investigate the dependence of El Niño/Southern Oscillation (ENSO) impacts on precipitation over the southeastern US, specifically during the cold season. We will examine the output from a suite of coupled model experiments with varying ENSO strength, frequency, asymmetry, and the location of the strongest sea surface temperature anomalies, in both the pre-industrial and future climate. At least 18 model runs of approximately 400 years each will be generated, with output saved from several daily variables and many monthly fields. To achieve the project's objectives, machine learning techniques will be used to quantify meaningful statements in the data. Expected outcomes from the proposed project include a nuanced understanding of ENSO’s effect on the southeastern US extreme climate.

Southeastern Florida has seen unprecedented rainfall events in the past year, with models failing to accurately predict the amount of precipitation over the region. This work will investigate the dependence of El Niño/Southern Oscillation (ENSO) impacts on precipitation over the southeastern US, specifically during the cold season. We will examine the output from a suite of coupled model experiments with varying ENSO strength, frequency, asymmetry, and the location of the strongest sea surface temperature anomalies, in both the pre-industrial and future climate. At least 18 model runs of approximately 400 years each will be generated, with output saved from several daily variables and many monthly fields. To achieve the project's objectives, machine learning techniques will be used to quantify meaningful statements in the data. Expected outcomes from the proposed project include a nuanced understanding of ENSO’s effect on the southeastern US extreme climate.