We analyze daily extremes of precipitation produced with a polar-optimized version of the Advanced Weather Research and Forecasting (ARW-WRF) model that simulated 19 years on the domain developed for the Regional Arctic System (RASM) model. Analysis focuses on Alaska, because of its proximity to the Pacific and Arctic oceans, both of which provide a large moisture fetch inland. Alaska’s topography also has an important impact on orographically-forced precipitation. In order to understand the circulation characteristics conducive for extreme precipitation events, we use Self-Organizing Maps (SOMs) to find general patterns of circulation behavior. The SOM algorithm employs an artificial neural network that uses an unsupervised training process. In our analysis, we use mean sea level pressure (MSLP) anomalies to train the SOM.

We examine daily widespread extreme precipitation events, defined as at least 25 grid points experiencing 99^th percentile precipitation. Using the SOM procedure, we map days with widespread extremes onto the SOM’s array of circulation patterns. This mapping aids in determining which nodes are being accessed at higher frequencies, and hence, which circulations are more conducive to extreme events. We show that there are multiple circulation patterns responsible for extreme precipitation differentiated by where they produce extreme events in our analysis region. Additionally, we plot composites of several meteorological fields for SOM nodes being accessed by both extreme and non-extreme events to determine what specific conditions are necessary for a widespread extreme event. Composites of individual nodes (or of adjacent nodes in SOM space) produce more physically reasonable circulations as opposed to composites of all extreme events, which can include multiple synoptic circulation regimes. We also trace the temporal evolution of extreme events through SOM space. Thus, our analysis lays the groundwork for diagnosing differences in atmospheric circulations and their associated widespread, extreme precipitation events.