An official website of the United States government
Abstract 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 networks (CGANs), a type of deep generative model, with a convolutional neural network (CNN) to postprocess convection-allowing model (CAM) forecasts. The CGANs are designed to create synthetic ensemble members from deterministic CAM forecasts, and their outputs are processed by the CNN to estimate the probability of severe weather. The method is tested using High-Resolution Rapid Refresh (HRRR) 1–24-h forecasts as inputs and Storm Prediction Center (SPC) severe weather reports as targets. The method produced skillful predictions with up to 20% Brier skill score (BSS) increases compared to other neural-network-based reference methods using a testing dataset of HRRR forecasts in 2021. For the evaluation of uncertainty quantification, the method is overconfident but produces meaningful ensemble spreads that can distinguish good and bad forecasts. The quality of CGAN outputs is also evaluated. Results show that the CGAN outputs behave similarly to a numerical ensemble; they preserved the intervariable correlations and the contribution of influential predictors as in the original HRRR forecasts. This work provides a novel approach to postprocess CAM output using neural networks that can be applied to severe weather prediction. Significance StatementWe use a new machine learning (ML) technique to generate probabilistic forecasts of convective weather hazards, such as tornadoes and hailstorms, with the output from high-resolution numerical weather model forecasts. The new ML system generates an ensemble of synthetic forecast fields from a single forecast, which are then used to train ML models for convective hazard prediction. Using this ML-generated ensemble for training leads to improvements of 10%–20% in severe weather forecast skills compared to using other ML algorithms that use only output from the single forecast. This work is unique in that it explores the use of ML methods for producing synthetic forecasts of convective storm events and using these to train ML systems for high-impact convective weather prediction.
more »
« less
Diagnosing Storm Mode with Deep Learning in Convection-Allowing Models
Abstract While convective storm mode is explicitly depicted in convection-allowing model (CAM) output, subjectively diagnosing mode in large volumes of CAM forecasts can be burdensome. In this work, four machine learning (ML) models were trained to probabilistically classify CAM storms into one of three modes: supercells, quasi-linear convective systems, and disorganized convection. The four ML models included a dense neural network (DNN), logistic regression (LR), a convolutional neural network (CNN) and semi-supervised CNN-Gaussian mixture model (GMM). The DNN, CNN, and LR were trained with a set of hand-labeled CAM storms, while the semi-supervised GMM used updraft helicity and storm size to generate clusters which were then hand labeled. When evaluated using storms withheld from training, the four classifiers had similar ability to discriminate between modes, but the GMM had worse calibration. The DNN and LR had similar objective performance to the CNN, suggesting that CNN-based methods may not be needed for mode classification tasks. The mode classifications from all four classifiers successfully approximated the known climatology of modes in the U.S., including a maximum in supercell occurrence in the U.S. Central Plains. Further, the modes also occurred in environments recognized to support the three different storm morphologies. Finally, storm mode provided useful information about hazard type, e.g., storm reports were most likely with supercells, further supporting the efficacy of the classifiers. Future applications, including the use of objective CAM mode classifications as a novel predictor in ML systems, could potentially lead to improved forecasts of convective hazards.
more »
« less
- Award ID(s):
- 2019758
- PAR ID:
- 10422713
- Date Published:
- Journal Name:
- Monthly Weather Review
- ISSN:
- 0027-0644
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Observational data collection is extremely hazardous in supercell storm environments, which makes for a scarcity of data used for evaluating the storm-scale guidance from convection allowing models (CAMs) like the National Oceanic and Atmospheric Administration (NOAA) Warn-on-Forecast System (WoFS). The Targeted Observations with UAS and Radar of Supercells (TORUS) 2019 field mission provided a rare opportunity to not only collect these observations, but to do so with advanced technology: vertically pointing Doppler lidar. One standing question for WoFS is how the system forecasts the feedback between supercells and their near-storm environment. The lidar can observe vertical profiles of wind over time, creating unique datasets to compare to WoFS kinematic predictions in rapidly evolving severe weather environments. Mobile radiosonde data are also presented to provide a thermodynamic comparison. The five lidar deployments (three of which observed tornadic supercells) analyzed show WoFS accurately predicted general kinematic trends in the inflow environment; however, the predicted feedback between the supercell and its environment, which resulted in enhanced inflow and larger storm-relative helicity (SRH), were muted relative to observations. The radiosonde observations reveal an overprediction of CAPE in WoFS forecasts, both in the near and far field, with an inverse relationship between the CAPE errors and distance from the storm. Significance Statement It is difficult to evaluate the accuracy of weather prediction model forecasts of severe thunderstorms because observations are rarely available near the storms. However, the TORUS 2019 field experiment collected multiple specialized observations in the near-storm environment of supercells, which are compared to the same near-storm environments predicted by the National Oceanic and Atmospheric Administration (NOAA) Warn-on-Forecast System (WoFS) to gauge its performance. Unique to this study is the use of mobile Doppler lidar observations in the evaluation; lidar can retrieve the horizontal winds in the few kilometers above ground on time scales of a few minutes. Using lidar and radiosonde observations in the near-storm environment of three tornadic supercells, we find that WoFS generally predicts the expected trends in the evolution of the near-storm wind profile, but the response is muted compared to observations. We also find an inverse relationship of errors in instability to distance from the storm. These results can aid model developers in refining model physics to better predict severe storms.more » « less
-
Abstract Ten bow echo events were simulated using the Weather Research and Forecasting (WRF) Model with 3- and 1-km horizontal grid spacing with both the Morrison and Thompson microphysics schemes to determine the impact of refined grid spacing on this often poorly simulated mode of convection. Simulated and observed composite reflectivities were used to classify convective mode. Skill scores were computed to quantify model performance at predicting all modes, and a new bow echo score was created to evaluate specifically the accuracy of bow echo forecasts. The full morphology score for runs using the Thompson scheme was noticeably improved by refined grid spacing, while the skill of Morrison runs did not change appreciably. However, bow echo scores for runs using both schemes improved when grid spacing was refined, with Thompson runs improving most significantly. Additionally, near storm environments were analyzed to understand why the simulated bow echoes changed as grid spacing was changed. A relationship existed between bow echo production and cold pool strength, as well as with the magnitude of microphysical cooling rates. More numerous updrafts were present in 1-km runs, leading to longer intense lines of convection which were more likely to evolve into longer-lived bow echoes in more cases. Large-scale features, such as a low-level jet orientation more perpendicular to the convective line and surface boundaries, often had to be present for bow echoes to occur in the 3-km runs.more » « less
-
null (Ed.)Abstract During the Remote Sensing of Electrification, Lightning, and Mesoscale/Microscale Processes with Adaptive Ground Observations-Cloud, Aerosol, and Complex Terrain Interactions (RELAMPAGO-CACTI) field experiments in 2018–19, an unprecedented number of balloon-borne soundings were collected in Argentina. Radiosondes were launched from both fixed and mobile platforms, yielding 2712 soundings during the period 15 October 2018–30 April 2019. Approximately 20% of these soundings were collected by highly mobile platforms, strategically positioned for each intensive observing period, and launching approximately once per hour. The combination of fixed and mobile soundings capture both the overall conditions characterizing the RELAMPAGO-CACTI campaign, as well as the detailed evolution of environments supporting the initiation and upscale growth of deep convective storms, including some that produced hazardous hail and heavy rainfall. Episodes of frequent convection were characterized by sufficient quantities of moisture and instability for deep convection, along with deep-layer vertical wind shear supportive of organized or rotating storms. A total of 11 soundings showed most unstable convective available potential energy (MUCAPE) exceeding 6000 J kg −1 , comparable to the extreme instability observed in other parts of the world with intense deep convection. Parameters used to diagnose severe-storm potential showed that conditions were often favorable for supercells and severe hail, but not for tornadoes, primarily because of insufficient low-level wind shear. High-frequency soundings also revealed the structure and evolution of the boundary layer leading up to convection initiation, convectively generated cold pools, the South American low-level jet (SALLJ), and elevated nocturnal convection. This sounding dataset will enable improved understanding and prediction of convective storms and their surroundings in subtropical South America, as well as comparisons with other heavily studied regions such as the central United States that have not previously been possible.more » « less
-
null (Ed.)ABSTRACT: During the Remote Sensing of Electrification, Lightning, and Mesoscale/Microscale Processes with Adaptive Ground Observations-Cloud, Aerosol, and Complex Terrain Interactions (RELAMPAGO-CACTI) field ex- periments in 2018–19, an unprecedented number of balloon-borne soundings were collected in Argentina. Radiosondes were launched from both fixed and mobile platforms, yielding 2712 soundings during the period 15 October 2018–30 April 2019. Approximately 20% of these soundings were collected by highly mobile platforms, strategically positioned for each intensive observing period, and launching approximately once per hour. The combination of fixed and mobile soundings capture both the overall conditions characterizing the RELAMPAGO-CACTI campaign, as well as the detailed evo- lution of environments supporting the initiation and upscale growth of deep convective storms, including some that produced hazardous hail and heavy rainfall. Episodes of frequent convection were characterized by sufficient quantities of moisture and instability for deep convection, along with deep-layer vertical wind shear supportive of organized or rotating storms. A total of 11 soundings showed most unstable convective available potential energy (MUCAPE) ex- ceeding 6000 J kg21, comparable to the extreme instability observed in other parts of the world with intense deep con- vection. Parameters used to diagnose severe-storm potential showed that conditions were often favorable for supercells and severe hail, but not for tornadoes, primarily because of insufficient low-level wind shear. High-frequency soundings also revealed the structure and evolution of the boundary layer leading up to convection initiation, convectively gen- erated cold pools, the South American low-level jet (SALLJ), and elevated nocturnal convection. This sounding dataset will enable improved understanding and prediction of convective storms and their surroundings in subtropical South America, as well as comparisons with other heavily studied regions such as the central United States that have not previously been possible.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1175/MWR-D-22-0342.1
