3A.1 Creating High-Resolution Convection Forecasts over Northeast Colorado Using Random Forests

Friday, 28 July 2017: 1:30 PM
Constellation E (Hyatt Regency Baltimore)
Gregory R. Herman, Colorado State Univ., Fort Collins, CO; and R. S. Schumacher

Hourly probabilistic forecasts of categorical composite reflectivity (CREF) are produced for 1500-0900 UTC for each warm season (April-September) day over northeast Colorado, far southeast Wyoming, and far southwest Nebraska in association with the recent C3LOUD-Ex field program. Forecasts from 0000 UTC initializations of the convection-allowing National Severe Storms Laboratory Weather Research and Forecasting model (NSSL-WRF) from all warm season days in 2013-2016 are used. Predictors come from thirteen atmospheric fields portrayed by the NSSL-WRF: composite reflectivity, convective available potential energy, convective inhibition, precipitable water, surface air temperature and dew point, ten meter zonal and meridional winds, six kilometer zonal and meridional winds, 500 hPa geopotential heights, planetary boundary layer height, and updraft helicity. Predictors include those displaced in both space and time relative to the forecast location to enable capability to correct for spatial displacement biases and convective initiation biases in the NSSL-WRF model. This procedure yields a very large number of candidate NSSL-WRF predictors of CREF; to obtain more tractable analysis and alleviate overfitting concerns, this rearranged record of historical model data is pre-processed with principal component analysis (PCA) and the primary modes of warm-season atmospheric variability in NE CO are identified. The dimension-reduced NSSL-WRF model data is then supplied to a random forest (RF) algorithm to produce probabilistic hourly CREF forecasts over the forecast domain. These results of applying this methodology will be presented. Overall, the preliminary results are quite encouraging: the probabilistic forecasts generated through RFs were both more skillful and more reliable than forecasts generated through applying straightforward neighborhood techniques on the raw NSSL-WRF composite reflectivity output to generate forecast probabilities.
- Indicates paper has been withdrawn from meeting
- Indicates an Award Winner