Contrasting Trends in Colorado Fire Weather Index from Reanalysis and Observations

Abstract Recent wildfires in Colorado raise the question of whether rising global temperatures have increased fire weather occurrences in Colorado. The U.S. National Weather Service defines fire weather as when “forecast weather conditions will result in a significant threat for the ignition and/or spread of wildfires.” We use two datasets to address the question: “How has the occurrence of fire weather changed in Colorado?” Using 22 years of observed weather conditions from a meteorological tower at the National Renewable Energy Laboratory and 67 years of ERA5 reanalysis data, we assess changing trends in Colorado fire weather as defined by hot, dry, and windy conditions. Additionally, we explore if the difference in recorded wind speeds between observational data and reanalysis data can be explained by differences in spatial and temporal resolution and what are the implications in the context of quantifying fire weather occurrences. The observational data are limited in temporal extent and spatial representativeness, but they capture exact real-world conditions at a location in complex terrain. The reanalysis data are available for an extended period of time and for the entire state, but the data are of relatively coarse spatial and temporal resolution and may fail to capture extremes. To quantify fire risk, we calculate the hot–dry–windy index (HDWI), which relies on wind speed and vapor pressure deficit. No statistically significant trend in the HDWI appears in the observational dataset. However, according to the reanalysis data, strong increasing trends in HDWI values emerge across all of Colorado. This apparent conflict between observational and reanalysis data suggests that reanalysis data may not be representative. Further, more long-term observational datasets are required to assess fire risk. Significance Statement The purpose of this study is to understand if the occurrences of fire weather are changing in Colorado. Using a 22-yr observational dataset representative of one location, we fail to find a significant trend in fire weather occurrences over this period. However, when we examine a reanalysis dataset for the same time period and for a longer 67-yr time period, fire weather occurrences seem to be increasing. We find that reanalysis often underestimates wind speed when compared to observations. The coarser spatial and temporal resolution of reanalysis data do not fully explain the bias. This conflict between observations and reanalysis data suggests that more long-term observational datasets are required to accurately assess fire risk.