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
Α Hybrid Approach to Atmospheric Modeling that Combines Machine Learning with a Physics-Based Numerical Model
This paper describes an implementation of the Combined Hybrid-Parallel Prediction (CHyPP) approach of Wikner et al. (2020) on a low-resolution atmospheric global circulation model (AGCM). This approach combines a physics-based numerical model of a dynamical system (e.g., the atmosphere) with a computationally efficient type of machine learning (ML) called reservoir computing (RC) to construct a hybrid model. This hybrid atmospheric model produces more accurate forecasts of most atmospheric state variables than the host AGCM for the first 7-8 forecast days, and for even longer times for the temperature and humidity near the earth's surface. It also produces more accurate forecasts than a purely ML-based model, or a model that combines linear regression, rather than ML, with the AGCM. The potential of the approach for climate research is demonstrated by a 10-year long hybrid model simulation of the atmospheric general circulation, which shows that the hybrid model can simulate the general circulation with substantially smaller systematic errors and more realistic variability than the host AGCM.
more »
« less
- Award ID(s):
- 1632976
- PAR ID:
- 10287977
- Date Published:
- Journal Name:
- James
- ISSN:
- 2213-9435
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
The southeast Indian Ocean (SEIO) exhibits decadal variability in sea surface temperature (SST) with amplitudes of ~0.2–0.3 K and covaries with the central Pacific ( r = −0.63 with Niño-4 index for 1975–2010). In this study, the generation mechanisms of decadal SST variability are explored using an ocean general circulation model (OGCM), and its impact on atmosphere is evaluated using an atmospheric general circulation model (AGCM). OGCM experiments reveal that Pacific forcing through the Indonesian Throughflow explains <20% of the total SST variability, and the contribution of local wind stress is also small. These wind-forced anomalies mainly occur near the Western Australian coast. The majority of SST variability is attributed to surface heat fluxes. The reduced upward turbulent heat flux ( Q T ; latent plus sensible heat flux), owing to decreased wind speed and anomalous warm, moist air advection, is essential for the growth of warm SST anomalies (SSTAs). The warming causes reduction of low cloud cover that increases surface shortwave radiation (SWR) and further promotes the warming. However, the resultant high SST, along with the increased wind speed in the offshore area, enhances the upward Q T and begins to cool the ocean. Warm SSTAs co-occur with cyclonic low-level wind anomalies in the SEIO and enhanced rainfall over Indonesia and northwest Australia. AGCM experiments suggest that although the tropical Pacific SST has strong effects on the SEIO region through atmospheric teleconnection, the cyclonic winds and increased rainfall are mainly caused by the SEIO warming through local air–sea interactions.more » « less
-
Irrigation can affect climate and weather patterns from regional to global scales through the alteration of surface water and energy balances. Here, we couple a land-surface model (LSM) that includes various human land-water management activities including irrigation with an atmospheric general circulation model (AGCM) to examine the impacts of irrigation-induced land disturbance on the subseasonal predictability of near-surface variables. Results indicate that the simulated global irrigation and groundwater withdrawals (circa 2000) are ~3600 and ~370 km3/year, respectively, which are in good agreement with previous estimates from country statistics and offline–LSMs. Subseasonal predictions for boreal summers during the 1986–1995 period suggest that the spread among ensemble simulations of air temperature can be substantially reduced by using realistic land initializations considering irrigation-induced changes in soil moisture. Additionally, it is found that the subseasonal forecast skill for near-surface temperature and sea level pressure significantly improves when human-induced land disturbance is accounted for in the AGCM. These results underscore the need to incorporate irrigation into weather forecast models, such as the global forecast system.more » « less
-
Abstract Machine learning (ML) models are successful with weather forecasting and have shown progress in climate simulations, yet leveraging them for useful climate predictions needs exploration. Here we show this feasibility using Neural General Circulation Model (NeuralGCM), a hybrid ML-physics atmospheric model developed by Google, for seasonal predictions of large-scale atmospheric variability and Northern Hemisphere tropical cyclone (TC) activity. Inspired by physical model studies, we simplify boundary conditions, assuming sea surface temperature (SST) and sea ice follow their climatological cycle but persist anomalies present at the initialization time. With such forcings, NeuralGCM can generate 100 simulation days in ~8 minutes with a single Graphics Processing Unit (GPU), while simulating realistic atmospheric circulation and TC climatology patterns. This configuration yields useful seasonal predictions (July–November) for the tropical atmosphere and various TC activity metrics. Notably, the predicted and observed TC frequency in the North Atlantic and East Pacific basins are significantly correlated during 1990–2023 (r=~0.7), suggesting prediction skill comparable to existing physical GCMs. Despite challenges associated with model resolution and simplified boundary forcings, the model-predicted interannual variations demonstrate significant correlations with the observation, including the sub-basin TC tracks (p<0.1) and basin-wide accumulated cyclone energy (p<0.01) of the North Atlantic and North Pacific basins. These findings highlight the promise of leveraging ML models with physical insights to model TC risks and deliver seamless weather-climate predictions.more » « less
-
We introduce a hybrid model that synergistically combines machine learning (ML) with semiconductor device physics to simulate nanoscale transistors. This approach integrates a physics-based ballistic transistor model with an ML model that predicts ballisticity, enabling flexibility to interface the model with device data. The inclusion of device physics not only enhances the interpretability of the ML model but also streamlines its training process, reducing the necessity for extensive training data. The model's effectiveness is validated on both silicon nanotransistors and carbon nanotube FETs, demonstrating high model accuracy with a simplified ML component. We assess the impacts of various ML models—Multilayer Perceptron (MLP), Recurrent Neural Network (RNN), and RandomForestRegressor (RFR)—on predictive accuracy and training data requirements. Notably, hybrid models incorporating these components can maintain high accuracy with a small training dataset, with the RNN-based model exhibiting better accuracy compared to the MLP and RFR models. The trained hybrid model provides significant speedup compared to device simulations, and can be applied to predict circuit characteristics based on the modeled nanotransistors.more » « less
- Free Publicly Accessible Full Text
-
Accepted Manuscript1.0
- Journal Article:
- https://doi.org/10.1002/essoar.10507548.1
