Regional Models¶
-
Varda-single-1.0: deterministic data-driven weather forecasting at 1 km resolution over Switzerland's complex topography¶
We present Varda-single-1.0, a medium-range data-driven weather prediction system built for the Alpine domain. It provides hourly deterministic regional forecasts on a mesh of 1 km resolution and...We present Varda-single-1.0, a medium-range data-driven weather prediction system built for the Alpine domain. It provides hourly deterministic regional forecasts on a mesh of 1 km resolution and global forecasts on a 31 km mesh. The system comprises two independently trained stretched-grid Graph Transformer models with encoder-processor-decoder architecture, developed in the Anemoi framework: a 6-hourly autoregressive forecaster and a temporal downscaler reconstructing hourly forecasts between the forecaster's steps. Its training curriculum includes pre-training on ERA5 reanalysis data, followed by training on a 20-year kilometre-scale regional reanalysis, and finally fine-tuning on operational kilometre-scale analyses. Verified over one year against operational analyses and surface station observations, Varda-single is competitive with or improves on MeteoSwiss' operational numerical weather prediction baselines for most headline scores and variables. It broadly matches the skill of the high-resolution 1 km ICON-CH1-EPS control at lead times up to +33 h and generally outperforms the 2 km ICON-CH2-EPS control at lead times up to +120 h. Despite competitive aggregate scores, Varda-single underestimates some local wind maxima and produces overly smooth convective precipitation fields, consistent with the smoothing associated with squared-error training. To gain insight into the model's behaviour, we investigate three case studies beyond the aggregated headline scores, and find particular weaknesses in Varda-single's representation of local winds over complex terrain. Varda-single represents an important step in the development of high-resolution ML forecasting over complex terrain, in complementing the operational regional numerical weather prediction models of MeteoSwiss with data-driven models and in providing a pretrained model for researchers and user-specific applications. more
-
Less is more: error-distance scaling relation for data-efficient kilometer-scale downscaling of extreme heat¶
Extreme heat is where urban adaptation needs kilometer-scale data the most, but the simulations training a downscaler can cost more than they save, and how much is needed has not been identified. We...Extreme heat is where urban adaptation needs kilometer-scale data the most, but the simulations training a downscaler can cost more than they save, and how much is needed has not been identified. We measured it with CASPER, a U-Net with a structure-preserving loss downscaling 32 km reanalysis to 1 km temperature, humidity and wind, across 24 configurations of one to eight months. Held-out error grows linearly with climatological distance to the training data, RMSE = 0.83 + 2.95 d, explaining 90% of its variance against 7% for volume and predicting unseen months in advance. On held-out extreme summer weeks CASPER preserves the fine-scale structure and cross-variable physics that matched-budget baselines degrade, and matches station observations during documented heat waves to within 1.8 K. Transfer to a new region degrades geographically; 11 days of local simulation cuts Vancouver's held-out error from 3.8 to 1.3 K. Training periods should span the target climate: the same accuracy for four times less simulation, putting kilometer-scale downscaling of extreme heat within reach of groups without large computing facilities. more
-
RainAtlas: A Multi-Continental Dataset for Precipitation Downscaling¶
Extreme rainfall events are increasing in intensity and frequency as climate change accelerates. While kilometer-scale precipitation forecasts are critical for supporting local decision-making, the...Extreme rainfall events are increasing in intensity and frequency as climate change accelerates. While kilometer-scale precipitation forecasts are critical for supporting local decision-making, the limited availability of high-resolution precipitation observations hinders their accuracy, especially in under-resourced regions. Machine learning models are widely used to downscale precipitation data to km-scale, but their application to unseen geographies presents challenges. First, processing raw high-resolution precipitation datasets across regions requires significant engineering and domain expertise. Second, generalization across regions remains difficult. To help overcome these barriers, we release RainAtlas, a large-scale, ML-ready and multi-continental dataset for precipitation downscaling. Covering three continents, RainAtlas harmonizes heterogeneous hourly km-scale observations to a common 2-km grid. Each regional partition contains around 210,000 aligned low- and high-resolution precipitation pairs, respectively from ERA5 reanalysis and direct observations. We benchmark state-of-the-art ML-based downscaling models across RainAtlas using a wide range of metrics. Our evaluation reveals substantial variance in out-of-domain generalization depending on the training regions. This underscores the need for cross-regional, multi-source km-scale evaluation, establishing RainAtlas as a well-positioned benchmark for precipitation downscaling research. more
-
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...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. more
-
Kilometer-Scale AI Downscaling of Atlantic Hurricanes with Generative Ensembles¶
This study presents an AI-based dynamical downscaling system for Tropical Cyclones (TCs). The system incorporates an AI-based limited-area model that downscales 3-hourly low-resolution boundary...This study presents an AI-based dynamical downscaling system for Tropical Cyclones (TCs). The system incorporates an AI-based limited-area model that downscales 3-hourly low-resolution boundary forcings into hourly high-resolution fields autoregressively, and a diffusion model that converts the outputs into ensembles of hazard-relevant variables. The system is trained on the regridded CONUS404 data with ERA5 forcings, and is evaluated on 20 TCs in 2020--2024. Verification shows stable downscaling performance across Atlantic hurricane seasons, with energy spectra closely matching the CONUS404 reference. The system is also verified to produce skillful TC-relevant weather extremes, largely improved over a deterministic AI baseline. The system performs well with forcing data from other models (GDAS/FNL) and can produce detailed eyewall, rainband, and landfall structures in TC case studies. The study provides a good example of how AI-based dynamical downscaling systems can be designed to resolve small-scale extreme weather events. more
-
Generative data assimilation highlights fronts as key regulators of ocean energy cascade¶
Mesoscale eddies are fundamental to the ocean circulation, yet the extent to which submesoscale motions, a few kilometers across, influence mesoscale eddy energetics through a kinetic energy cascade...Mesoscale eddies are fundamental to the ocean circulation, yet the extent to which submesoscale motions, a few kilometers across, influence mesoscale eddy energetics through a kinetic energy cascade remains uncertain. High-resolution simulations predict that submesoscale fronts are key regulators of the cascade, transferring energy both downscale towards dissipation and upscale to sustain and shape the seasonality of mesoscale eddies. Testing these predictions has remained difficult because existing observations and state estimates cannot resolve submesoscale currents over sufficiently broad domains. Here we map the ocean's submesoscale energy cascade by combining multi-source satellite observations with a generative deep learning framework, reconstructing gap-free, kilometer-scale surface currents with physically plausible dynamics learned from simulations. Applying this to the eddy-rich Agulhas Current system, we find that submesoscales energize the mesoscale through an upscale energy cascade above 10 km, contributing to the seasonality of mesoscale eddies. Below 10 km, convergence at submesoscale fronts drives a downscale cascade towards dissipation. Both upscale and downscale pathways concentrate within fronts, where cross-scale transfer is up to an order of magnitude more efficient. Despite their limited extent, fronts account for a substantial fraction of the domain-integrated cascade, establishing them as key regulators of the cascade and targets for next-generation eddy parameterizations. more
-
High-resolution Calibrated Probabilistic Hourly Precipitation from a Deterministic Forecast¶
An “Attention Residual U-Net” method is described for probabilistic quantitative precipitation forecasting (PQPF) that predicts the hourly probability of no precipitation plus the distribution of...An “Attention Residual U-Net” method is described for probabilistic quantitative precipitation forecasting (PQPF) that predicts the hourly probability of no precipitation plus the distribution of positive precipitation from a weighted mixture of two Gamma distributions. The neural network is trained on patches of numerical weather prediction (NWP) hourly precipitation from The Weather Company's convection-permitting GRAF (Global high-Resolution Atmospheric Forecasting) model along with terrain information and column-average relative humidity from the National Oceanic and Atmospheric Administration's (NOAA's) Global Forecast System (GFS). The target data are NOAA's Multi-Radar, Multi-Sensor (MRMS) gauge-corrected, quality controlled radar data sampled to the same grid as the GRAF data. The network outputs distributional parameters for each model grid point. Training uses negative log-likelihood as a proper scoring rule, with climatological initialization for stable convergence. Inference is performed as a single forward pass over the contiguous United States (CONUS) domain, with edge-replication padding to satisfy the network's spatial-divisibility requirement. The subsequent forecasts are spatially detailed, highly reliable, and skillful with respect to climatology and a simpler reference forecast method. The method is particularly useful for estimating probabilities in regions with large terrain variation. more
-
MAPCast: A Convection Allowing MPAS Emulator for Ensemble-based Background Error Covariance Estimation Toward Multi-Scale Data Assimilation¶
Machine learning (ML) emulators offer a cost-efficient alternative to numerical weather prediction models for generating convection-allowing background ensembles in ensemble-based data assimilation...Machine learning (ML) emulators offer a cost-efficient alternative to numerical weather prediction models for generating convection-allowing background ensembles in ensemble-based data assimilation (DA). However, few studies have explored ML-based surrogate background ensembles for estimating background-error covariances (BECs). This study develops a convection-allowing emulator, MAPCast, trained on historical convection-allowing simulations from the Model for Prediction Across Scales (MPAS), and evaluates its ability to estimate BECs, paving the way toward multiscale DA. The evaluation uses 10 retrospective convective cases at 15- and 60-min forecast lead times corresponding to subhourly and hourly DA. MAPCast reproduces MPAS forecasts with good fidelity, including realistic storm coverage, temporal evolution, and similar spatial and spectral characteristics of state variables. Discrepancies are primarily confined to small spatial scales near sharp gradients and convective-scale features and variables. For BEC statistics, MAPCast captures ensemble spread magnitude and spatial distribution for most variables, although larger errors occur for storm-related fields that are vertical velocity and reflectivity. Correlation structures are reproduced most faithfully at mesoscale and above, followed by at convective scales, whereas cross-variable correlations are less accurately represented than univariate correlations, indicating that multivariate coupling remains the principal limitation. MAPCast shows weaker replication of full-scale versus decomposed large and small-scale correlations. BEC estimates derived from 15-min forecasts consistently outperform those from 60-min forecasts, suggesting that shorter lead times better preserve flow-dependent error structures. more
-
Geospatial Diffusion-based Evolution Synthesis (GeoDES) for Storm-Centered Weather Augmentation¶
While machine learning-based weather models hold significant promise, they struggle to predict the detailed structure of large-scale weather systems such as cyclonic storms. Regional models are...While machine learning-based weather models hold significant promise, they struggle to predict the detailed structure of large-scale weather systems such as cyclonic storms. Regional models are constrained by limited historical records within fixed geographic boundaries, while global models are computationally expensive and often operate at resolutions too coarse to capture fine-grained storm dynamics. To bridge this gap, we introduce the Geospatial Diffusion-based Evolution Synthesis (GeoDES) model, a custom image-to-video diffusion model. By focusing generation strictly on the evolving storm structure, GeoDES synthesizes physically consistent, high-fidelity weather events suitable for stress-testing forecast models and expanding meteorological datasets. Evaluations demonstrate that GeoDES outperforms prior methods on key metrics, achieving \(52\%\) lower Peak Vorticity Error and \(8\%\) higher Anomaly Correlation Coefficient than the next strongest methods on the North Atlantic test set. more
-
Apeliotes: A Diffusion-Based Modeling Framework for km-scale Multi-Level Atmospheric Fields¶
High-resolution atmospheric data are required to resolve mesoscale and localized meteorological structures, however such datasets remain limited in many regions of the world. Existing high-resolution...High-resolution atmospheric data are required to resolve mesoscale and localized meteorological structures, however such datasets remain limited in many regions of the world. Existing high-resolution weather products are typically produced through dynamical downscaling, which is computationally expensive and difficult to scale across locations, variables, and forecast scenarios. These limitations motivate machine-learning-based downscaling systems that can generate multiple weather variables stochastically while producing new high-resolution fields directly. In this paper we present Apeliotes, a framework for high-resolution weather forecasting. Built on the global re-analysis atmospheric data, a pre-trained global weather foundation model, and a regionally trained generative diffusion model, Apeliotes not only provides accurate kilometer-scale weather variables, but also multi-level atmospheric fields which are not directly available in the existing global atmospheric data. Our comprehensive evaluation demonstrates that Apeliotes achieves highly competitive performance. The model predicts vertical wind profile with less than 3% error between truth and predicted fields, achieving correlations of 0.91 for 10-m wind speed and 0.99 for 2-m temperature, with NRMSE values of 0.42 and 0.17, respectively. more
-
HourGlass: A probabilistic data-driven temporal downscaler for global and regional weather forecasting¶
Many forecast applications require high frequency temporal resolution, yet most state-of-the-art data-driven weather forecasting systems operate at 6-hourly resolution. Although direct hourly...Many forecast applications require high frequency temporal resolution, yet most state-of-the-art data-driven weather forecasting systems operate at 6-hourly resolution. Although direct hourly forecasting is possible, it suffers from error accumulation and temporal inconsistency. We introduce HourGlass, a probabilistic data-driven temporal downscaling method that reconstructs the evolution between forecast states. HourGlass is trained using variants of the continuous ranked probability score (CRPS) preserving small-scale spatial variability while encouraging temporal consistency. Unlike existing deterministic temporal downscaling approaches, which tend to produce overly smooth fields, HourGlass generates realistic probabilistic forecasts. Training on forecast trajectories rather than reanalysis or analysis data also avoids the temporal inconsistencies present in datasets used by previous methods. We evaluate HourGlass in two settings: AIFS-HourGlass, applied globally to ECMWF's AIFS-Single and AIFS-ENS forecast systems, and Bris-HourGlass, applied regionally to MET Norway's high-resolution stretched-grid ensemble model, Bris. Verification against observations shows that both models retain the skill of their underlying forecasting systems while producing temporally coherent hourly forecasts with realistic small-scale variability. Case studies demonstrate physically consistent evolution during rapidly developing weather events, including extratropical cyclones and organised convection. Hourly precipitation remains challenging: HourGlass improves the spatial realism of precipitation fields but still underestimates the most intense extremes, a common limitation of data-driven weather forecasting models. These results demonstrate that HourGlass effectively bridges the gap between 6-hourly data-driven forecasts and the hourly products required for operational regional and global forecasting. more
-
From Global to Local: Efficient Regional Weather Downscaling with Global Weather Foundation Model¶
Accurate regional weather prediction requires resolving fine-scale structure while remaining consistent with global dynamics. Traditional limited area models rely on computationally expensive...Accurate regional weather prediction requires resolving fine-scale structure while remaining consistent with global dynamics. Traditional limited area models rely on computationally expensive simulations, while many learning-based approaches frame the problem as super-resolution, overlooking statistical and physical mismatches across scales. We propose a foundation-model-driven downscaling framework that learns regional refinements of global forecasts by augmenting a pretrained weather model backbone with lightweight, multi-scale prediction heads operating directly in its latent space. Despite being trained on substantially coarser inputs, the pretrained backbone supports regional adaptation at resolutions corresponding to a two-order-of-magnitude increase in grid-cell resolution, without the need for retraining. The proposed approach uses regional numerical simulations as training targets and is evaluated not only against gridded datasets but also against ground-based weather station observations, enabling analysis of systematic biases between global reanalysis, regional simulations, and in-situ weather station observations. Our experiments show improved accuracy in comparison to NWP on most of the metrics at the fraction of computational cost. Moreover, we observe that building on a latent space of globally pre-trained weather foundation model offers better downscaling capabilities than the standard image-based super-resolution approaches. more
-
Scaling Storm-Resolving Atmospheric AI Simulation to the Entire Planet¶
Kilometer-scale convection shapes precipitation extremes, tropical organization, and cloud feedbacks, but most global atmospheric models approximate these processes at 25-100 km resolution. Global...Kilometer-scale convection shapes precipitation extremes, tropical organization, and cloud feedbacks, but most global atmospheric models approximate these processes at 25-100 km resolution. Global storm-resolving physics models resolve convective systems explicitly, but at a cost -- roughly one MWh per simulated day on exascale supercomputers -- that limits long-duration simulation. We introduce STRATA (Storm-resolving Tile-based autoRegressive Atmosphere Transformer Architecture), the first autoregressive AI emulator for global storm-resolving atmospheric dynamics. STRATA is trained on the highest-resolution atmospheric dataset yet used for global AI emulation: 17 days of SCREAM physics-model output at 4.9-km resolution (~25 million grid cells) sampled every 10 minutes. Our central premise is that on 10-minute timescales atmospheric dynamics are predominantly local, so training on small spatial tiles trades scarce global temporal samples for abundant local spatial samples and enables global rollout via overlapping-tile blending. STRATA combines 3D patch embedding and local 3D neighborhood attention, a novel Stereographic Rotary Position Embedding (StereoRoPE) for grid-invariant encoding, and a pixel-space de-aliasing decoder that suppresses patch-scale rollout artifacts. An iso-FLOP scaling study reveals that km-scale emulation requires ~10x more FLOPs per grid point than coarse-resolution AI weather models, consistent with the higher information density of convective-scale dynamics. Trained on only 17 days of data, STRATA produces stable 24-hour global rollouts with realistic km-scale dynamics across diverse regimes, though large-scale biases develop with lead time. It achieves 48 simulation days per megawatt-hour -- about 50 times better energy efficiency than the SCREAM physics model -- and 741 simulated days per wall-clock day at 512 H100 GPUs. Code and dataset are publicly available. more
-
From stable online coupling to decade-long climate simulations: A machine learning parameterization for cloud microphysics in ICON¶
The representation of cloud microphysics and its nonlinear character and scale-dependence is a remaining source of uncertainty in Earth system models (ESMs). Here, we develop and couple online a...The representation of cloud microphysics and its nonlinear character and scale-dependence is a remaining source of uncertainty in Earth system models (ESMs). Here, we develop and couple online a machine learning (ML)-based cloud microphysics parameterization with the Icosahedral non-hydrostatic modeling framework (ICON). The primary challenge is achieving numerically stable, long-term online coupling when transitioning from training with km-scale data to application in coarse-scale simulations, where the coupled system encounters atmospheric states and feedbacks not seen during training. The training data is obtained from a global convection-permitting ICON simulation at 5 km resolution. The ML microphysics scheme uses a two-stage design: a classifier to identify active grid cells and a regressor to predict cloud microphysical tendencies. Physical constraints such as enforcing mass positivity and overshoot prevention prove essential for numerical stability in the coupled system. We demonstrate that achieving stable online coupling requires enforcing physical constraints and careful dataset curation, and that strong offline performance alone is insufficient. The coupled model maintains numerical stability over decade-long simulations with a performance in reproducing the observed climate comparable to the classical graupel scheme. The ML-based scheme eliminates two microphysics-specific tuning parameters of the classical graupel scheme, though systematic improvements in long-term mean-state biases are not yet realized. This study demonstrates that stable, decade-long climate simulations with an ML-based cloud microphysics scheme trained on convection-permitting data are feasible, providing a foundation for future hybrid ESMs. more
-
PRecover 1.0: Process Rate Recovery with Machine Learning¶
Comprehensive information on cloud microphysical process rates from numerical simulations allows for better understanding of precipitation formation pathways and aerosol-cloud interactions. However,...Comprehensive information on cloud microphysical process rates from numerical simulations allows for better understanding of precipitation formation pathways and aerosol-cloud interactions. However, resource limitations often make it impractical to include all microphysical process rates in the model output, limiting in-depth analyses. To address this shortcoming, we introduce PRecover, a data-driven post-processing approach to recover microphysical process rates that are not stored during runtime from standard output of a numerical weather prediction model. In particular, we train random forests, gradient boosting models, and feed-forward neural networks to recover microphysical process rates from a two-moment bulk microphysics scheme in the ICOsahedral Nonhydrostatic (ICON) model. We use cloud variables as input, obtained from high-resolution simulations in a limited-area setup over Europe. Warm-rain and ice microphysical process rates are recovered with a two-step classification-regression approach for both instantaneous and accumulated process rates. As a physics-based baseline, we assess whether process rates can be directly recalculated from stored ICON output variables. Accurate recalculation is possible for process rates such as accretion and self-collection but not for the autoconversion, rain melting or heterogeneous ice nucleation rate. Using PRecover, we successfully recover most of the process rates that are accumulated over output time steps of 10 minutes or less, but the values are increasingly difficult to recover for rates accumulated over longer accumulation intervals. To quantify predictive uncertainty, we provide calibrated prediction intervals through conformalized quantile regression. We demonstrate spatial transferability of the models with two case studies over different regional domains and simulation settings unseen during training. more
-
Skillful high-resolution weather forecasting independent of physical models¶
Accurate and timely weather forecasts are critical for high-impact decisions in modern society. Machine-learning-based weather prediction is emerging as an alternative for producing initial...Accurate and timely weather forecasts are critical for high-impact decisions in modern society. Machine-learning-based weather prediction is emerging as an alternative for producing initial conditions, forecasts, and even both in end-to-end systems. These methods deliver predictions faster and often with higher skill than traditional numerical weather prediction (NWP). However, even end-to-end models typically rely on NWP-generated reanalyses for supervision, thereby inheriting the biases and resolution limitations of those NWPs, and limiting adaptation to settings where suitable reanalysis products are unavailable, infrequently updated, or expensive to produce. Here we introduce ObsCast, a regional system that generates both analysis and predictions, without using any NWP-derived data in either training or inference, while still achieving state-of-the-art performance in short-term high-resolution regional modeling. Over the contiguous United States and Europe, ObsCast outperforms operational NWP for near-surface variables through 18 h and produces skillful precipitation forecasts. It provides a simpler and more adaptable route to build and refine regional forecasting services directly from local observations, without the need to develop complex and costly traditional forecasting pipelines. more
-
AirCast-SR: A Foundation Model for Kilometer-Scale Atmospheric Super-Resolution via Latent Consistency Diffusion¶
Operational weather prediction at kilometer scales remains computationally prohibitive for traditional numerical weather prediction (NWP) models, limiting forecast access for applications in energy,...Operational weather prediction at kilometer scales remains computationally prohibitive for traditional numerical weather prediction (NWP) models, limiting forecast access for applications in energy, agriculture, and disaster management that require fine-grained spatiotemporal detail. Here we introduce AirCast-SR, a foundation model for atmospheric super-resolution that downscales global AI weather forecasts from 0.25 degree (~28 km) to 1 km horizontal resolution at hourly temporal resolution, producing 67-hour forecasts of eight coupled surface variables simultaneously. EarthMind-SR employs a three-dimensional U-Net conditioned within a Latent Consistency Model (LCM) diffusion framework, trained on patch-based samples over the contiguous United States (CONUS) using GraphCast forecasts as input and NOAA's Analysis of Record for Calibration (AORC) as the target. The model achieves near-zero bias across all variables and lead times, and its radial power spectral density analysis demonstrates preservation of fine-scale atmospheric structure at wavelengths of 10 km to 100 km where coarser models lose spectral power. We validate EarthMind-SR across three CONUS case studies spanning winter, summer, and spring seasons, and demonstrate zero-shot global transferability over India and Germany using independent surface station observations without any retraining or fine-tuning. As an open-weights foundation model, EarthMind-SR establishes a new paradigm for kilometer-scale AI weather prediction and provides a platform for regional fine-tuning, distillation, and downstream applications in climate services and hazard forecasting. more
-
Exascale Hybrid Numerical-AI Ensembles for Operational Flood-Season Forecasting in East Asia: 15-km Decadal Hindcasts and 1-km High-Resolution Capability¶
Seasonal forecasting of summer rainfall in East Asia remains a grand challenge, as predictability at 3 to 6 month lead times is constrained by the spring predictability barrier, weak large-scale...Seasonal forecasting of summer rainfall in East Asia remains a grand challenge, as predictability at 3 to 6 month lead times is constrained by the spring predictability barrier, weak large-scale signals, and localized nonlinear convective extremes. We address this challenge with CAPES, which integrates a kilometer-resolution coupled regional model with atmosphere, land, and ocean components and a data-driven AI seasonal forecasting system. At 15 km resolution, the fused workflow combines 174 numerical members from varying start times, physics schemes, and parameter perturbations with 1,600 AI members generated from initial and physical perturbations. Using the full LineShine system, CAPES completes ten annual 1,774-member hindcasts for 2016 to 2025 within 14.6 hours, improving the mean prediction score from ECMWF's 71.8 to 75.9 and delivering a major gain in operational forecasting capability. The 1-km configuration further enables fine-scale typhoon simulation and establishes the feasibility of kilometer-scale fused ensemble forecasting on a one-week timescale. more
-
Volador 1.0: A Data-Driven Air-Sea Full-Coupling Regional Forecast Model with Submesoscale-Permitting Based on MOE-Swin-Transformer Framework¶
A data-driven air-sea full-coupling regional forecast model with submesoscale-permitting, named "Volador 1.0", is developed for the South China Sea (SCS). The model features a Swin-Transformer...A data-driven air-sea full-coupling regional forecast model with submesoscale-permitting, named "Volador 1.0", is developed for the South China Sea (SCS). The model features a Swin-Transformer framework integrated with a Mixture-of-Experts (MoE) system, a latent space interaction architecture based on Cross-Grid Bidirectional Cross-Attention, and a fast-slow dual-branch architecture. Both the three-month hindcast test and the 15-day operational real-time forecasting demonstrate that Volador 1.0 has a very encouraging and promising performance in 0-72h forecasting of temperature and salinity in the 0-500m upper ocean as well as the sea surface height with root-mean-square-error (RMSE) or mean absolute error (MAE) smaller than or at least comparable to those from the reanalysis datasets REDOS V2.0 and GLORYS12 and the state-of-the-art regional numerical model Regional Ocean Modeling System (ROMS). In particular, Volador 1.0 demonstrates its capability of capturing/forecasting submesoscale processes including internal waves, with an energy spectrum well representing sub- to mesoscale energy cascade as expected by the classical turbulence theory. Further analysis based on ablation experiments shows that the air-sea full-coupling framework, which takes into account the dynamic exchanges of momentum and heat fluxes between the atmosphere and the ocean, indeed helps improve the model's performance compared to the non-full-coupling one. Volador 1.0, though still subject to refinement in the coming future with a large space for improvement, blazes a path for an accurate, fine and fast marine environment forecasting, and thus could help promote our capability of disaster prevention and mitigation in the SCS as well as in other coastal regions where these innovative techniques can be applied. more
-
SwAIther-Precip: Lead-Time-Aware Bias Correction Enables Kilometer-Scale Downscaling of Global AI Precipitation Forecasts over Switzerland¶
Skillful medium-range precipitation forecasting at kilometer scale remains challenging over complex terrain because precipitation arises from multiscale nonlinear processes that global models cannot...Skillful medium-range precipitation forecasting at kilometer scale remains challenging over complex terrain because precipitation arises from multiscale nonlinear processes that global models cannot explicitly resolve at affordable cost. Global AI weather models can produce skillful medium-range forecasts, but their native 0.25 degrees resolution limits direct use for local hazard applications. Statistical downscaling can help bridge this gap, yet existing approaches often struggle with state-dependent, and especially lead-time-dependent, biases in global forecasts. We introduce SwAIther-Precip, a lead-time-aware downscaling framework that converts coarse-resolution AIFS forecasts into probabilistic km-scale precipitation fields over Switzerland. First, a U-Net conditioned on lead time via feature-wise linear modulation deterministically corrects systematic biases at coarse resolution. This targeted correction enables a cheaper super-resolution stage conditioned only on corrected precipitation, allowing direct training on observations rather than on the full atmospheric state. A diffusion-based model then generates fine-scale spatial variability independently of lead time. Using AIFS forecasts and CombiPrecip radar-gauge observations, SwAIther-Precip reduces CRPS by 48% relative to raw AIFS. The generated fields reproduce observed spatial variability with spectral fidelity above 0.85 at large scales and 0.88 at small scales, corresponding to an effective resolution of approximately 4 km on a 1 km grid for lead times up to 5 days. Training across lead times further improves long-range performance, yielding a 13% CRPS reduction at 6 days relative to lead-time-specific models. These results show that explicitly correcting lead-time-dependent biases before generative super-resolution is key to efficient km-scale probabilistic downscaling of global AI precipitation forecasts. more
-
Federated Weather Modeling on Sensor Data¶
Federated weather modeling on sensor data is a distributed system underpinned by federated learning, enabling multiple sensor data sources, including ground weather stations, satellites and IoT...Federated weather modeling on sensor data is a distributed system underpinned by federated learning, enabling multiple sensor data sources, including ground weather stations, satellites and IoT devices, to collaboratively train deep learning models without sharing raw data. This method safeguards data privacy and security while leverages diverse, geographically distributed datasets to improve the accuracy and robustness of global/regional weather modeling tasks such as forecasting and anomaly detection. more
-
Explanation of Dynamic Physical Field Predictions using WassersteinGrad: Application to Autoregressive Weather Forecasting¶
As the demand to integrate Artificial Intelligence into high-stakes environments continues to grow, explaining the reasoning behind neural-network predictions has shifted from a theoretical curiosity...As the demand to integrate Artificial Intelligence into high-stakes environments continues to grow, explaining the reasoning behind neural-network predictions has shifted from a theoretical curiosity to a strict operational requirement. Our work is motivated by the explanations of autoregressive neural predictions on dynamic physical fields, as in weather forecasting. Gradient-based feature attribution methods are widely used to explain the predictions on such data, in particular due to their scalability to high-dimensional inputs. It is also interesting to remark that gradient-based techniques such as SmoothGrad are now standard on images to robustify the explanations using pointwise averages of the attribution maps obtained from several noised inputs. Our goal is to efficiently adapt this aggregation strategy to dynamic physical fields. To do so, our first contribution is to identify a fundamental failure mode when averaging perturbed attribution maps on dynamic physical fields: stochastic input perturbations do not induce stationary amplitude noise in attribution maps, but instead cause a geometric displacement of the attributions. Consequently, pointwise averaging blurs these spatially misaligned features. To tackle this issue, we introduce WassersteinGrad, which extracts a geometric consensus of perturbed attribution maps by computing their entropic Wasserstein barycenter. The results, obtained on regional weather data and a meteorologist-validated neural model, demonstrate promising explainability properties of WassersteinGrad over gradient-based baselines across both single-step and autoregressive forecasting settings. more
-
Global Attention with Linear Complexity for Exascale Generative Data Assimilation in Earth System Prediction¶
Accurate weather and climate prediction relies on data assimilation (DA), which estimates the Earth system state by integrating observations with models. While exascale computing has significantly...Accurate weather and climate prediction relies on data assimilation (DA), which estimates the Earth system state by integrating observations with models. While exascale computing has significantly advanced earth simulation, scalable and accurate inference of the Earth system state remains a fundamental bottleneck, limiting uncertainty quantification and prediction of extreme events. We introduce a unified one-stage generative DA framework that reformulates assimilation as Bayesian posterior sampling, replacing the conventional forecast-update cycle with compute-dense, GPU-efficient inference. At the core is STORM, a novel spatiotemporal transformer with a global attention linear-complexity scaling algorithm that breaks the quadratic attention barrier. On 32,768 GPUs of the Frontier supercomputer, our method achieves 63% strong scaling efficiency and 1.6 ExaFLOP sustained performance. We further scale to 20 billion spatiotemporal tokens, enabling km-scale global modeling over 177k temporal frames, regimes previously unreachable, establishing a new paradigm for Earth system prediction. more
-
OTProf: estimating high-resolution profiles of optical turbulence (\(C_n^2\)) from reanalysis using deep learning¶
Accurate high-resolution vertical profiles of optical turbulence (\(C_n^2\)), which reflect local meteorology and topography, are crucial for ground-based optical astronomy and free-space optical...Accurate high-resolution vertical profiles of optical turbulence (\(C_n^2\)), which reflect local meteorology and topography, are crucial for ground-based optical astronomy and free-space optical communication. However, measuring these profiles or generating them with numerical weather models requires substantial operational or computational effort. In this work, we present OTProf, a deep-learning method that estimates high-resolution \(C_n^2\) profiles from widely available coarse-resolution ERA5 reanalysis data. We evaluate the approach in the Netherlands and compare it with the commonly used Hufnagel-Valley model. Overall, OTProf reproduces the vertical structure of \(C_n^2\) more accurately than Hufnagel-Valley and yields more accurate estimates of the Fried parameter \(r_0\) and the scintillation index \(σ_I^2\). As typical in machine learning, the \(C_n^2\) predictions are slightly smoothed compared to reference data, especially in cases of rare strong turbulence. This smoothing affects the integrated parameters, sometimes leading to overly optimistic \(r_0\) and \(σ_I^2\) values. Despite this limitation, OTProf offers a more accurate, efficient, and physically consistent alternative to traditional analytical models and computationally expensive mesoscale models. more
-
Assessing the ability of a stretched-grid deep-learning weather prediction model to capture physical balances¶
Weather forecasting has traditionally relied on Numerical Weather Prediction (NWP) models, which simulate weather by solving the governing fluid equations. Recently, the emergence of Deep Learning...Weather forecasting has traditionally relied on Numerical Weather Prediction (NWP) models, which simulate weather by solving the governing fluid equations. Recently, the emergence of Deep Learning Weather Prediction (DLWP) models has opened a new era in weather forecasting, offering a data-driven alternative to classical NWP approaches. Regional DLWP models such as the stretched-grid model Bris developed by Met Norway, have demonstrated performance on par with, or even slightly better than regional NWP models across a range of standard forecast metrics. By overcoming the coarse horizontal resolution that constrained earlier global data-driven models, the operational use of regional DLWP systems now appears increasingly promising. Nevertheless, the performance of such models during extreme events is generally inferior to that of regional NWP models, and comprehensive evaluations of their ability to generate physically realistic forecasts are still lacking. Here, we present a study comparing the physical consistency of the deterministic version of Bris with the control run of the operational MetCoOp Ensemble Prediction System (MEPS) in forecasting the severe extratropical cyclone Poly, which hit the Netherlands on 5 July 2023. We examine whether Bris accurately represents deviations from key atmospheric balances and whether it reproduces expected dynamics of the storm. We show that, despite its relatively good performance in terms of RMSE, Bris struggles to capture important mesoscale features of the event and that it significantly disrupts several atmospheric balances. This unrealistic disruption is mainly linked to the fine-scale noise evidenced in its output fields, which leads to incorrect and unrealistic spatial gradients. These results raise critical questions for improving AI-based models to better represent extreme events and how to ensure physical consistency in their predictions. more
-
Skillful Kilometer-Scale Regional Weather Forecasting via Global and Regional Coupling¶
Data-driven weather models have advanced global medium-range forecasting, yet high-resolution regional prediction remains challenging due to unresolved multiscale interactions between large-scale...Data-driven weather models have advanced global medium-range forecasting, yet high-resolution regional prediction remains challenging due to unresolved multiscale interactions between large-scale dynamics and small-scale processes such as terrain-induced circulations and coastal effects. This paper presents a global-regional coupling framework for kilometer-scale regional weather forecasting that synergistically couples a pretrained Transformer-based global model with a high-resolution regional network via a novel bidirectional coupling module, ScaleMixer. ScaleMixer dynamically identifies meteorologically critical regions through adaptive key-position sampling and enables cross-scale feature interaction through dedicated attention mechanisms. The framework produces forecasts at \(0.05^\circ\) (\(\sim 5 \mathrm{km}\) ) and 1-hour resolution over China, significantly outperforming operational NWP and AI baselines on both gridded reanalysis data and real-time weather station observations. It exhibits exceptional skill in capturing fine-grained phenomena such as orographic wind patterns and Foehn warming, demonstrating effective global-scale coherence with high-resolution fidelity. The code is available at https://anonymous.4open.science/r/ScaleMixer-6B66. more
-
Calibrated Conformal Prediction Intervals for Microphysical Process Rates¶
Conformal prediction can yield statistically valid prediction intervals for any regression model, with no model modifications and small computational costs. To assess its practical value, we apply...Conformal prediction can yield statistically valid prediction intervals for any regression model, with no model modifications and small computational costs. To assess its practical value, we apply conformal methods to quantify uncertainty in machine learning emulators of six microphysical process rates. Microphysical process rates describe small-scale processes in atmospheric clouds such as precipitation formation and aerosol-cloud interactions, and help understand weather and climate. The emulators are trained on simulation output from the ICOsahedral Nonhydrostatic (ICON) model in a limited-area numerical weather prediction configuration. We compare split conformal prediction for deterministic emulators with conformalized quantile regression for quantile regression emulators. Both conformal prediction methods yield well-calibrated and sharp prediction intervals on average, but conformalized quantile regression provides more consistent intervals across several orders of magnitude, making it preferable for the uncertainty quantification of climate variables. more
-
Developing Machine Learning-Based Watch-to-Warning Severe Weather Guidance from the Warn-on-Forecast System¶
While machine learning (ML) post-processing of convection-allowing model (CAM) output for severe weather hazards (large hail, damaging winds, and/or tornadoes) has shown promise for very short lead...While machine learning (ML) post-processing of convection-allowing model (CAM) output for severe weather hazards (large hail, damaging winds, and/or tornadoes) has shown promise for very short lead times (0-3 hours), its application to slightly longer forecast windows remains relatively underexplored. In this study, we develop and evaluate a grid-based ML framework to predict the probability of severe weather hazards over the next 2-6 hours using forecast output from the Warn-on-Forecast System (WoFS). Our dataset includes WoFS ensemble forecasts valid every 5 minutes out to 6 hours from 108 days during the 2019--2023 NOAA Hazardous Weather Testbed Spring Forecasting Experiments. We train ML models to generate probabilistic forecasts of severe weather akin to Storm Prediction Center outlooks (i.e., likelihood of a tornado, severe wind, or severe hail event within 36 km of each point). We compare a histogram gradient-boosted tree (HGBT) model and a deep learning U-Net approach against a carefully calibrated baseline generated from 2-5 km updraft helicity. Results indicate that the HGBT and U-Net outperform the baseline, particularly at higher probability thresholds. The HGBT achieves the best performance metrics, but predicted probabilities cap at 60% while the U-net forecasts extend to 100%. Similar to previous studies, the U-Net produces spatially smoother guidance than the tree-based method. These findings add to the growing evidence of the effectiveness of ML-based CAM post-processing for providing short-term severe weather guidance. more
-
MR-GNF: Multi-Resolution Graph Neural Forecasting on Ellipsoidal Meshes for Efficient Regional Weather Prediction¶
Weather forecasting offers an ideal testbed for artificial intelligence (AI) to learn complex, multi-scale physical systems. Traditional numerical weather prediction remains computationally costly...Weather forecasting offers an ideal testbed for artificial intelligence (AI) to learn complex, multi-scale physical systems. Traditional numerical weather prediction remains computationally costly for frequent regional updates, as high-resolution nests require intensive boundary coupling. We introduce Multi-Resolution Graph Neural Forecasting (MR-GNF), a lightweight, physics-aware model that performs short-term regional forecasts directly on an ellipsoidal, multi-scale graph of the Earth. The framework couples a 0.25° region of interest with a 0.5° context belt and 1.0° outer domain, enabling continuous cross-scale message passing without explicit nested boundaries. Its axial graph-attention network alternates vertical self-attention across pressure levels with horizontal graph attention across surface nodes, capturing implicit 3-D structure in just 1.6 M parameters. Trained on 40 years of ERA5 reanalysis (1980-2024), MR-GNF delivers stable +6 h to +24 h forecasts for near-surface temperature, wind, and precipitation over the UK-Ireland sector. Despite a total compute cost below 80 GPU-hours on a single RTX 6000 Ada, the model matches or exceeds heavier regional AI systems while preserving physical consistency across scales. These results demonstrate that graph-based neural operators can achieve trustworthy, high-resolution weather prediction at a fraction of NWP cost, opening a practical path toward AI-driven early-warning and renewable-energy forecasting systems. Project page and code: https://github.com/AndriiShchur/MR-GNF more
-
AI-Based Regional Emulation for Kilometer-Scale Dynamical Downscaling¶
An AI-based Limited-Area Model (LAM) is developed for dynamical downscaling over the Southern Great Plains and the southeastern United States, with strong generalization abilities under diverse...An AI-based Limited-Area Model (LAM) is developed for dynamical downscaling over the Southern Great Plains and the southeastern United States, with strong generalization abilities under diverse boundary conditions. The model is trained using 0.25-degree, 3-hourly ERA5 as forcings and CONUS404 as targets in 1980--2019, producing 4-km, hourly dynamical downscaling outputs; it is also connected to a post-processing model to derive additional diagnostic variables. The model is evaluated across multiple forcing datasets, time periods, and climate regimes. For present-day downscaling in the 2021--2024 water years, the model produces stable multi-year simulations with no unrealistic drift; its deterministic verification scores are comparable to other weather-forecasting-oriented AI models. The model also generalizes robustly to a 1.0-degree, 6-hourly non-ERA5 forcing dataset, yielding only minor performance changes. Frontal cyclone and hurricane case studies further demonstrate that the model reconstructs realistic, interpretable weather-scale dynamical and thermodynamic structure from coarse boundary information. The AI-based LAM is further tested by downscaling 30-year global climate model runs in 1980--2010 and 2070--2100, and climate model ensembles in 2025-2027. In this application, the model remains stable at hourly downscaling frequencies for all 30 years and effectively captures future climate-change signals, indicating meaningful generalization across different climate regimes. When downscaling ensembles, the model produces well-posed ensemble distributions without collapsing the ensemble spread. Overall, the AI-based LAM of this study offers good downscaling performance and generalization abilities. It provides a practical and transferable example of adapting AI weather prediction models for regional climate applications. more