A primary goal of the National Oceanic and Atmospheric Administration Warn-on-Forecast (WoF) project is to provide rapidly updating probabilistic guidance to human forecasters for short-term (e.g., 0-3 h) severe weather forecasts. Post-processing is required to maximize the usefulness of probabilistic guidance from an ensemble of convection-allowing model forecasts. Machine learning (ML) models have become popular methods for post-processing severe weather guidance since they can leverage numerous variables to discover useful patterns in complex datasets. In this study, we develop and evaluate a series of ML models to produce calibrated, probabilistic severe weather guidance from WoF System (WoFS) output.Our dataset includes WoFS ensemble forecasts available every 5 minutes out to 150 min of lead time from the 2017-2019 NOAA Hazardous Weather Testbed Spring Forecasting Experiments (81 dates). Using a novel ensemble storm track identification method, we extracted three sets of predictors from the WoFS forecasts: intra-storm state variables, near-storm environment variables, and morphological attributes of the ensemble storm tracks. We then trained random forests, gradient-boosted trees, and logistic regression algorithms to predict which WoFS 30-min ensemble storm tracks will overlap a tornado, severe hail, and/or severe wind report. To provide rigorous baselines against which to evaluate the skill of the ML models, we extracted the ensemble probabilities of hazard-relevant WoFS variables exceeding tuned thresholds from each ensemble storm track. The three ML algorithms discriminated well for all three hazards and produced more reliable probabilities than the baseline predictions. Overall, the results suggest that ML-based post-processing of dynamical ensemble output can improve short term, storm-scale severe weather probabilistic guidance.

No abstract

In 2013, all NEXRAD WSR-88D units in the United States were upgraded to dual polarization. Dual polarization allows for the identification of precipitation particle shape, size, orientation, and concentration. In this study, dual-polarization NEXRAD observations from 34 recent events are used to identify the bulk microphysical characteristics of a specific subset of mesoscale convective systems (MCSs), the leading-line trailing-stratiform (LLTS) MCS. NEXRAD observations are used to examine hydrometeor distributions in relative altitude to the 0°C level and as a function of storm life cycle, precipitation source (convective or stratiform), and storm environment. The analysis reveals that graupel particles are the most frequently classified hydrometeor class in a layer extending from the 0°C-level altitude to approximately 5 km above within the convective region. Below the 0°C level, rain is the most frequently classified hydrometeor, with small hail and graupel concentrations present throughout the LLTS system’s life cycle. The stratiform precipitation region contains small graupel concentrations in a shallow layer above the 0°C level, with pristine ice crystals being classified as the most frequently observed hydrometeor at higher altitudes and snow aggregates being classified as the most frequently observed hydrometeor at lower altitudes above the environmental 0°C level. Variations in most unstable convective available potential energy (MUCAPE) have the largest impact on the vertical distribution of hydrometeors, because more-unstable environments are characterized by a greater production of rimed ice.

In this study, a machine learning algorithm for generating a gridded CONUS-wide probabilistic road-temperature forecast is presented. A random forest is used to tie a combination of HRRR model surface variables and information about the geographic location and time of day/year to observed road temperatures. This approach differs from its predecessors in that road temperature is not deterministic (i.e., provides a forecast of a specific road temperature), but rather it is probabilistic, providing a 0-100% probability that the road temperature is subfreezing. This approach can account for the varying controls on road temperature that are not easily known or able to be accounted for in physical models, such as amount of traffic, road composition, and differential shading by surrounding buildings and terrain. The algorithm is trained using road temperature observations from one winter season (Oct-Mar 2016-17) and calibrated/evaluated using observations from the following winter season (Oct-Mar 2017-18). Case-study analyses show the algorithm performs well for various scenarios and captures the temporal and spatial evolution of the probability of subfreezing roads reliably. Statistical evaluation for the predicted probabilities shows good skill as the mean area under the receiver operating characteristics curve is 0.96 and the Brier Skill Score is 0.66 for a 2-hr forecast and only degrades slightly as lead time is increased. Additionally, the algorithm produces well-calibrated probabilities, and consistent discrimination between clearly above-freezing and subfreezing environments.