Ryan A. Sobash
YOU?
Author Swipe
View article: Improving Medium Range Severe Weather Prediction through Transformer Post-processing of AI Weather Forecasts
Improving Medium Range Severe Weather Prediction through Transformer Post-processing of AI Weather Forecasts Open
Improving the skill of medium-range (3–8 day) severe weather prediction is crucial for mitigating societal impacts. This study introduces a novel approach leveraging decoder-only transformer networks to post-process AI-based weather foreca…
View article: Improving Medium Range Severe Weather Prediction through Transformer Post-processing of AI Weather Forecasts
Improving Medium Range Severe Weather Prediction through Transformer Post-processing of AI Weather Forecasts Open
Improving the skill of medium-range (3-8 day) severe weather prediction is crucial for mitigating societal impacts. This study introduces a novel approach leveraging decoder-only transformer networks to post-process AI-based weather foreca…
View article: Evaluating Machine Learning–Based Probabilistic Lightning Forecasts Using the HRRR: A Comparison to Three Forecast Baselines
Evaluating Machine Learning–Based Probabilistic Lightning Forecasts Using the HRRR: A Comparison to Three Forecast Baselines Open
Probabilistic forecasts of lightning for the CONUS were generated by postprocessing the HRRR with neural networks (NNs). These NN probability forecasts (NNPFs) were produced for HRRR forecasts in 2021–22 using NNs trained with 0000 UTC HRR…
View article: Improving Ensemble Extreme Precipitation Forecasts Using Generative Artificial Intelligence
Improving Ensemble Extreme Precipitation Forecasts Using Generative Artificial Intelligence Open
An ensemble postprocessing method is developed to improve the probabilistic forecasts of extreme precipitation events across the conterminous United States (CONUS). The method combines a 3D vision transformer (ViT) for bias correction with…
View article: Improving ensemble extreme precipitation forecasts using generative artificial intelligence
Improving ensemble extreme precipitation forecasts using generative artificial intelligence Open
An ensemble post-processing method is developed to improve the probabilistic forecasts of extreme precipitation events across the conterminous United States (CONUS). The method combines a 3-D Vision Transformer (ViT) for bias correction wi…
View article: Generative Ensemble Deep Learning Severe Weather Prediction from a Deterministic Convection-Allowing Model
Generative Ensemble Deep Learning Severe Weather Prediction from a Deterministic Convection-Allowing Model Open
An ensemble postprocessing method is developed for the probabilistic prediction of severe weather (tornadoes, hail, and wind gusts) over the conterminous United States (CONUS). The method combines conditional generative adversarial network…
View article: Generative ensemble deep learning severe weather prediction from a deterministic convection-allowing model
Generative ensemble deep learning severe weather prediction from a deterministic convection-allowing model Open
An ensemble post-processing method is developed for the probabilistic prediction of severe weather (tornadoes, hail, and wind gusts) over the conterminous United States (CONUS). The method combines conditional generative adversarial networ…
View article: Simulations of Severe Convective Systems Using 1- versus 3-km Grid Spacing
Simulations of Severe Convective Systems Using 1- versus 3-km Grid Spacing Open
Herein, 14 severe quasi-linear convective systems (QLCS) covering a wide range of geographical locations and environmental conditions are simulated for both 1- and 3-km horizontal grid resolutions, to further clarify their comparative capa…
View article: Assimilation of a Coordinated Fleet of Uncrewed Aircraft System Observations in Complex Terrain: Observing System Experiments
Assimilation of a Coordinated Fleet of Uncrewed Aircraft System Observations in Complex Terrain: Observing System Experiments Open
Uncrewed aircraft system (UAS) observations from the Lower Atmospheric Profiling Studies at Elevation–A Remotely-Piloted Aircraft Team Experiment (LAPSE-RATE) field campaign were assimilated into a high-resolution configuration of the Weat…
View article: An Iterative Storm Segmentation and Classification Algorithm for Convection-Allowing Models and Gridded Radar Analyses
An Iterative Storm Segmentation and Classification Algorithm for Convection-Allowing Models and Gridded Radar Analyses Open
Thunderstorm mode strongly impacts the likelihood and predictability of tornadoes and other hazards, and thus is of great interest to severe weather forecasters and researchers. It is often impossible for a forecaster to manually classify …
View article: Relationship of Convection Initiation and Subsequent Storm Strength to Ensemble Simulated Environmental Conditions during IOP3b of VORTEX Southeast 2017
Relationship of Convection Initiation and Subsequent Storm Strength to Ensemble Simulated Environmental Conditions during IOP3b of VORTEX Southeast 2017 Open
A 50-member convection-allowing ensemble was used to examine environmental factors influencing afternoon convection initiation (CI) and subsequent severe weather on 5 April 2017 during intensive observing period (IOP) 3b of the Verificatio…
View article: Assimilation of a Coordinated Fleet of Uncrewed Aircraft System Observations in Complex Terrain: EnKF System Design and Preliminary Assessment
Assimilation of a Coordinated Fleet of Uncrewed Aircraft System Observations in Complex Terrain: EnKF System Design and Preliminary Assessment Open
Uncrewed aircraft system (UAS) observations collected during the 2018 Lower Atmospheric Process Studies at Elevation—a Remotely Piloted Aircraft Team Experiment (LAPSE-RATE) field campaign were assimilated into a high-resolution configurat…
View article: A Comparison of Neural-Network and Surrogate-Severe Probabilistic Convective Hazard Guidance Derived from a Convection-Allowing Model
A Comparison of Neural-Network and Surrogate-Severe Probabilistic Convective Hazard Guidance Derived from a Convection-Allowing Model Open
A feed-forward neural network (NN) was trained to produce gridded probabilistic convective hazard predictions over the contiguous United States. Input fields to the NN included 174 predictors, derived from 38 variables output by 497 convec…
View article: Initial Conditions for Convection-Allowing Ensembles over the Conterminous United States
Initial Conditions for Convection-Allowing Ensembles over the Conterminous United States Open
Five sets of 48-h, 10-member, convection-allowing ensemble (CAE) forecasts with 3-km horizontal grid spacing were systematically evaluated over the conterminous United States with a focus on precipitation across 31 cases. The various CAEs …
View article: Lower-Tropospheric Influences on the Timing and Intensity of Afternoon Severe Convection over Modest Terrain in a Convection-Allowing Ensemble
Lower-Tropospheric Influences on the Timing and Intensity of Afternoon Severe Convection over Modest Terrain in a Convection-Allowing Ensemble Open
A 50-member convection-allowing ensemble is used to examine effects of daytime PBL evolution and ambient flow interacting with modest terrain features on convection initiation (CI) in the lee of the Rocky Mountains. The examined case (4 Ju…
View article: Revisiting Sensitivity to Horizontal Grid Spacing in Convection-Allowing Models over the Central and Eastern United States
Revisiting Sensitivity to Horizontal Grid Spacing in Convection-Allowing Models over the Central and Eastern United States Open
Hourly accumulated precipitation forecasts from deterministic convection-allowing numerical weather prediction models with 3- and 1-km horizontal grid spacing were evaluated over 497 forecasts between 2010 and 2017 over the central and eas…
View article: Next-Day Prediction of Tornadoes Using Convection-Allowing Models with 1-km Horizontal Grid Spacing
Next-Day Prediction of Tornadoes Using Convection-Allowing Models with 1-km Horizontal Grid Spacing Open
Explicit attributes of convective storms within convection-allowing model (CAM) forecasts are routinely used as surrogates for convective weather hazards. The ability of 3- and 1-km horizontal grid spacing CAM forecasts to anticipate torna…
View article: NCAR’s Real-Time Convection-Allowing Ensemble Project
NCAR’s Real-Time Convection-Allowing Ensemble Project Open
Beginning 7 April 2015, scientists at the U.S. National Center for Atmospheric Research (NCAR) began producing daily, real-time, experimental, 10-member ensemble forecasts with 3-km horizontal grid spacing across the entire conterminous Un…
View article: Toward 1-km Ensemble Forecasts over Large Domains
Toward 1-km Ensemble Forecasts over Large Domains Open
Precipitation forecasts from convection-allowing ensembles with 3- and 1-km horizontal grid spacing were evaluated between 15 May and 15 June 2013 over central and eastern portions of the United States. Probabilistic forecasts produced fro…
View article: Severe Weather Prediction Using Storm Surrogates from an Ensemble Forecasting System
Severe Weather Prediction Using Storm Surrogates from an Ensemble Forecasting System Open
Probabilistic severe weather forecasts for days 1 and 2 were produced using 30-member convection-allowing ensemble forecasts initialized by an ensemble Kalman filter data assimilation system during a 32-day period coinciding with the Mesos…