干旱区生态环境知识资源中心

We estimate future wildfire activity over the western United States during the mid-21st century (2046-2065), based on results from 15 climate models following the A1B scenario. We develop fire prediction models by regressing meteorological variables from the current and previous years together with fire indexes onto observed regional area burned. The regressions explain 0.25-0.60 of the variance in observed annual area burned during 1980-2004, depending on the ecoregion. We also parameterize daily area burned with temperature, precipitation, and relative humidity. This approach explains similar to 0.5 of the variance in observed area burned over forest ecoregions but shows no predictive capability in the semi-arid regions of Nevada and California. By applying the meteorological fields from 15 climate models to our fire prediction models, we quantify the robustness of our wildfire projections at midcentury. We calculate increases of 24-124% in area burned using regressions and 63-169% with the parameterization. Our projections are most robust in the southwestern desert, where all GCMs predict significant (p < 0.05) meteorological changes. For forested ecoregions, more GCMs predict significant increases in future area burned with the parameterization than with the regressions, because the latter approach is sensitive to hydrological variables that show large inter-model variability in the climate projections. The parameterization predicts that the fire season lengthens by 23 days in the warmer and drier climate at midcentury. Using a chemical transport model, we find that wildfire emissions will increase summertime surface organic carbon aerosol over the western United States by 46-70% and black carbon by 20-27% at midcentury, relative to the present day. The pollution is most enhanced during extreme episodes: above the 84th percentile of concentrations, OC increases by similar to 90% and BC by similar to 50%, while visibility decreases from 130 km to 100 km in 32 Federal Class 1 areas in Rocky Mountains Forest. (C) 2013 Elsevier Ltd. All rights reserved.