Characterizing Antecedent Conditions Prior to Annual Maximum Flood Events in a High-Elevation Watershed Using Self-Organizing Maps

Abstract

Abstract Flood frequency estimates are required for many water management and design engineering projects, including dam safety risk management activities. Most studies assume that annual or peak-over-threshold flood events are sampled from a single homogeneous population, an assumption that is sometimes invalid. In this study, we characterize conditions prior to annual maximum flood events in the Taylor Park watershed between water years 1981 and 2016 using historical observations and the self-organizing maps (SOM) algorithm. Inputs to the SOM algorithm include annual maximum daily reservoir inflow, annual maximum snow water equivalent (SWE), SWE melt length, and 4-day antecedent precipitation. Four-day antecedent precipitation is defined as the precipitation accumulated over the 3 days prior to and on the day of the annual maximum event. Results based on a 2 × 2 SOM output map, which represents four flood categories, suggest that 58% of events are the result of snowmelt with a near-negligible contribution from antecedent precipitation, 17% of events are the result of snowmelt combined with large antecedent precipitation, and the remaining 25% of events are the result of snowmelt with no contribution from antecedent precipitation. These results, which highlight the existence of more than one flood mechanism, may have implications for future flood frequency analyses in this watershed and other watersheds within the region.