An official website of the United States government
Abstract Extreme weather events have significant consequences, dominating the impact of climate on society. While high‐resolution weather models can forecast many types of extreme events on synoptic timescales, long‐term climatological risk assessment is an altogether different problem. A once‐in‐a‐century event takes, on average, 100 years of simulation time to appear just once, far beyond the typical integration length of a weather forecast model. Therefore, this task is left to cheaper, but less accurate, low‐resolution or statistical models. But there is untapped potential in weather model output: despite being short in duration, weather forecast ensembles are produced multiple times a week. Integrations are launched with independent perturbations, causing them to spread apart over time and broadly sample phase space. Collectively, these integrations add up to thousands of years of data. We establish methods to extract climatological information from these short weather simulations. Using ensemble hindcasts by the European Center for Medium‐range Weather Forecasting archived in the subseasonal‐to‐seasonal (S2S) database, we characterize sudden stratospheric warming (SSW) events with multi‐centennial return times. Consistent results are found between alternative methods, including basic counting strategies and Markov state modeling. By carefully combining trajectories together, we obtain estimates of SSW frequencies and their seasonal distributions that are consistent with reanalysis‐derived estimates for moderately rare events, but with much tighter uncertainty bounds, and which can be extended to events of unprecedented severity that have not yet been observed historically. These methods hold potential for assessing extreme events throughout the climate system, beyond this example of stratospheric extremes.
more »
« less
LUCIE: A Lightweight Uncoupled Climate Emulator With Long‐Term Stability and Physical Consistency
Abstract We present a lightweight, easy‐to‐train, low‐resolution, fully data‐driven climate emulator, LUCIE, that can be trained on as low as 2 years of 6‐hourly ERA5 data. Unlike most state‐of‐the‐art AI weather models, LUCIE remains stable and physically consistent for 100 years of autoregressive simulation with 100 ensemble members. Long‐term mean climatology from LUCIE's simulation of temperature, wind, precipitation, and humidity matches that of ERA5 data, along with the variability. We further demonstrate how well extreme weather events and their return periods can be estimated from a large ensemble of long‐term simulations. We further discuss an improved training strategy with a hard‐constrained first‐order integrator to suppress autoregressive error growth, a novel spectral regularization strategy to better capture fine‐scale dynamics, and finally an optimization algorithm that enables data‐limited (as low as 2 years of 6‐hourly data) training of the emulator without losing stability and physical consistency. Finally, we provide a scaling experiment to compare the long‐term bias of LUCIE with respect to the number of training samples. Importantly, LUCIE is an easy to use model that can be trained in just 2.4 hr on a single A‐100 GPU, allowing for multiple experiments that can explore important scientific questions that could be answered with large ensembles of long‐term simulations, for example, the impact of different variables on the simulation, dynamic response to external forcing, and estimation of extreme weather events, amongst others.
more »
« less
- Award ID(s):
- 2425667
- PAR ID:
- 10650072
- Publisher / Repository:
- DOI PREFIX: 10.1029
- Date Published:
- Journal Name:
- Journal of Advances in Modeling Earth Systems
- Volume:
- 17
- Issue:
- 11
- ISSN:
- 1942-2466
- Format(s):
- Medium: X
- Sponsoring Org:
- National Science Foundation
More Like this
-
-
Abstract Recent years have seen a surge in interest in building deep learning-based fully data-driven models for weather prediction. Such deep learning models, if trained on observations can mitigate certain biases in current state-of-the-art weather models, some of which stem from inaccurate representation of subgrid-scale processes. However, these data-driven models, being over-parameterized, require a lot of training data which may not be available from reanalysis (observational data) products. Moreover, an accurate, noise-free, initial condition to start forecasting with a data-driven weather model is not available in realistic scenarios. Finally, deterministic data-driven forecasting models suffer from issues with long-term stability and unphysical climate drift, which makes these data-driven models unsuitable for computing climate statistics. Given these challenges, previous studies have tried to pre-train deep learning-based weather forecasting models on a large amount of imperfect long-term climate model simulations and then re-train them on available observational data. In this article, we propose a convolutional variational autoencoder (VAE)-based stochastic data-driven model that is pre-trained on an imperfect climate model simulation from a two-layer quasi-geostrophic flow and re-trained, using transfer learning, on a small number of noisy observations from a perfect simulation. This re-trained model then performs stochastic forecasting with a noisy initial condition sampled from the perfect simulation. We show that our ensemble-based stochastic data-driven model outperforms a baseline deterministic encoder–decoder-based convolutional model in terms of short-term skills, while remaining stable for long-term climate simulations yielding accurate climatology.more » « less
-
Abstract 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 a latent diffusion model (LDM), a generative artificial intelligence (AI) method, to postprocess 6-hourly precipitation ensemble forecasts and produce an enlarged generative ensemble that contains spatiotemporally consistent precipitation trajectories. These trajectories are expected to improve the characterization of extreme precipitation events and offer skillful multiday accumulated and 6-hourly precipitation guidance. The method is tested using the Global Ensemble Forecast System (GEFS) precipitation forecasts out to day 6 and is verified against the Climatology-Calibrated Precipitation Analysis (CCPA) data. Verification results indicate that the method generated skillful ensemble members with improved continuous ranked probabilistic skill scores (CRPSSs) and Brier skill scores (BSSs) over the raw operational GEFS and a multivariate statistical postprocessing baseline. It showed skillful and reliable probabilities for events at extreme precipitation thresholds. Explainability studies were further conducted, which revealed the decision-making process of the method and confirmed its effectiveness on ensemble member generation. This work introduces a novel, generative AI–based approach to address the limitation of small numerical ensembles and the need for larger ensembles to identify extreme precipitation events. Significance StatementWe use a new artificial intelligence (AI) technique to improve extreme precipitation forecasts from a numerical weather prediction ensemble, generating more scenarios that better characterize extreme precipitation events. This AI-generated ensemble improved the accuracy of precipitation forecasts and probabilistic warnings for extreme precipitation events. The study explores AI methods to generate precipitation forecasts and explains the decision-making mechanisms of such AI techniques to prove their effectiveness.more » « less
-
Abstract Extreme winds associated with tropical cyclones (TCs) can cause significant loss of life and economic damage globally, highlighting the need for accurate, high‐resolution modeling and forecasting for wind. However, due to their coarse horizontal resolution, most global climate and weather models suffer from chronic underprediction of TC wind speeds, limiting their use for impact analysis and energy modeling. In this study, we introduce a cascading deep learning framework designed to downscale high‐resolution TC wind fields given low‐resolution data. Our approach maps 85 TC events from ERA5 data (0.25° resolution) to high‐resolution (0.05° resolution) observations at 6‐hr intervals. The initial component is a debiasing neural network designed to model accurate wind speed observations using ERA5 data. The second component employs a generative super‐resolution strategy based on a conditional denoising diffusion probabilistic model (DDPM) to enhance the spatial resolution and to produce ensemble estimates. The model is able to accurately model intensity and produce realistic radial profiles and fine‐scale spatial structures of wind fields, with a percentage mean bias of −3.74% compared to the high‐resolution observations. Our downscaling framework enables the prediction of high‐resolution wind fields using widely available low‐resolution and intensity wind data, allowing for the modeling of past events and the assessment of future TC risks.more » « less
-
To predict rare extreme events using deep neural networks, one encounters the so-called small data problem because even long-term observations often contain few extreme events. Here, we investigate a model-assisted framework where the training data are obtained from numerical simulations, as opposed to observations, with adequate samples from extreme events. However, to ensure the trained networks are applicable in practice, the training is not performed on the full simulation data; instead, we only use a small subset of observable quantities, which can be measured in practice. We investigate the feasibility of this model-assisted framework on three different dynamical systems (Rössler attractor, FitzHugh–Nagumo model, and a turbulent fluid flow) and three different deep neural network architectures (feedforward, long short-term memory, and reservoir computing). In each case, we study the prediction accuracy, robustness to noise, reproducibility under repeated training, and sensitivity to the type of input data. In particular, we find long short-term memory networks to be most robust to noise and to yield relatively accurate predictions, while requiring minimal fine-tuning of the hyperparameters.more » « less
