Search arXiv⌕ Search
Home/Archive/arXiv

arXiv · 2308.13280

AtmoRep: A stochastic model of atmosphere dynamics using large scale representation learning

Christian Lessig·Ilaria Luise·Bing Gong·Michael Langguth·Scarlet Stadtler·Martin Schultz
View original source ↗Read source document ↗Export metadata ↓

Abstract

The atmosphere affects humans in a multitude of ways, from loss of life due to adverse weather effects to long-term social and economic impacts on societies. Computer simulations of atmospheric dynamics are, therefore, of great importance for the well-being of our and future generations. Here, we propose AtmoRep, a novel, task-independent stochastic computer model of atmospheric dynamics that can provide skillful results for a wide range of applications. AtmoRep uses large-scale representation learning from artificial intelligence to determine a general description of the highly complex, stochastic dynamics of the atmosphere from the best available estimate of the system's historical trajectory as constrained by observations. This is enabled by a novel self-supervised learning objective and a unique ensemble that samples from the stochastic model with a variability informed by the one in the historical record. The task-independent nature of AtmoRep enables skillful results for a diverse set of applications without specifically training for them and we demonstrate this for nowcasting, temporal interpolation, model correction, and counterfactuals. We also show that AtmoRep can be improved with additional data, for example radar observations, and that it can be extended to tasks such as downscaling. Our work establishes that large-scale neural networks can provide skillful, task-independent models of atmospheric dynamics. With this, they provide a novel means to make the large record of atmospheric observations accessible for applications and for scientific inquiry, complementing existing simulations based on first principles.

Explore related subjects

physics.ao-phcs.AIcs.LGphysics.comp-ph

Keep this discovery

Explore connections, maps & timelines

BibTeXRIS

Christian Lessig, Ilaria Luise, Bing Gong, Michael Langguth, Scarlet Stadtler, Martin Schultz. 2023-09-07. AtmoRep: A stochastic model of atmosphere dynamics using large scale representation learning. https://arxiv.org/abs/2308.13280

Cite the original work for its findings. Save a collection to share your selection of sources.

KEEP EXPLORING

Related papers

arXiv2026

FAST-ML: A Hybrid Physics-Machine Learning Framework for Tropical Cyclone Intensity Forecasting

Rapid intensification (RI) remains one of the most consequential and difficult aspects of tropical cyclone (TC) forecasting. Although full-physics numerical weather prediction models can represent the processes governing RI, resolving storm-environment interactions remains computationally expensive, while purely data-driven approaches often lack physical interpretability. We present FAST-ML, a hybrid framework that bridges data-driven efficiency with physical constraints. A physically informed dual-stream neural parameterization ingests 3D ERA5 fields to diagnose ventilation controls---environmental wind shear and mid-level entropy deficit. By optimizing these parameters end-to-end through a differentiable FAST intensity model, this architecture establishes a robust new paradigm for observation-driven parameter optimization, ensuring storm evolution remains strictly governed by thermodynamic principles. By better capturing the storm's continuous intensity evolution, FAST-ML improves upon its physical baseline, reducing ensemble CRPS across forecast lead times, with a reduction of approximately 31% at 60 h and nearly halving the RI false alarm ratio without sacrificing detection skill. In a 100-member ensemble configuration, FAST-ML produces intensity forecasts comparable to FNV3 for selected storms under the evaluated input configurations. Furthermore, zero-shot tests on selected Eastern Pacific storms provide encouraging evidence of cross-basin transferability. FAST-ML provides a modular intensity forecasting framework that can be coupled with externally supplied storm tracks and environmental fields. It demonstrates that observation-driven parameter learning within physically constrained dynamics simultaneously enhances accuracy, interpretability, and computational efficiency.

physics.ao-ph↗
arXiv2026

West-WRF AI 2-km: High-Resolution Prediction of Integrated Vapor Transport and Precipitation

We introduce a stretched-grid artificial intelligence (AI) weather forecasting model with 2-km resolution over the western United States and part of the Northeast Pacific and approximately 31-km resolution elsewhere globally. Forecasting over the western U.S. is challenging because complex topography and atmospheric rivers (ARs) strongly influence orographic precipitation. West-WRF AI 2-km builds on a global model pretrained with a 40-year European Centre for Medium-Range Weather Forecasts Reanalysis v5 (ERA5) dataset and is fine-tuned with the Center for Western Weather and Water Extremes (CW3E) 2-km regional reanalysis to produce autoregressive 6-hourly forecasts of precipitation and integrated vapor transport (IVT). Forecasts are evaluated over winters 2020-2023 using gridded precipitation observations, rain gauges, and AR Reconnaissance dropsondes and are benchmarked against coarser-resolution AI forecasts and regional and global numerical weather prediction (NWP) systems. West-WRF AI 2-km reproduces observed precipitation-intensity distributions, retains fine-scale spectral variability, and produces sharper narrow coastal precipitation bands and localized, terrain-sensitive extremes. Its broader-scale performance remains comparable to coarser-resolution configurations while preserving large-scale skill despite higher resolution. Dropsonde verification shows lower errors and improved categorical skill at the most extreme IVT threshold. Overall, West-WRF AI 2-km provides its greatest value for localized precipitation extremes and intense AR-related moisture transport.

physics.ao-ph↗
arXiv2026

Hydrological Constraints on Temperature Sensitivities of Precipitation Frequency and Intensity

To improve understanding of how precipitation frequency and intensity change with warming, we combine the coupled land--atmosphere water balance with a stochastic hydrological model that retains explicit dependence on precipitation frequency and event depth. We find a linear relationship between co-variations of rainfall frequency and intensity, where the slope is a hydrological sensitivity determined by the dryness and storage indices and the intercept is a forcing term associated with changes in moisture convergence, potential evapotranspiration, and effective water-storage capacity. While a given relative change in either rainfall frequency or intensity produces an identical relative change in the mean rate, rainfall intensity additionally influences the runoff coefficient by altering terrestrial water storage relative to rainfall depth. This means frequency and intensity have different impacts on the water cycle, allowing the frequency--intensity slope to depart from -1. Analysis of long-term MOPEX records shows that the forcing term is dominated by moisture convergence and that the frequency--intensity relation becomes steeper from wet to dry regimes, consistent with the slope predicted by the theory. The framework provides a physical interpretation of the observed negative covariation between precipitation frequency and intensity and clarifies the roles of hydrological partitioning and atmospheric moisture supply in their responses to warming.

physics.ao-ph↗