From Global to Local: Efficient Regional Weather Downscaling with Global Weather Foundation Model

• URL: http://arxiv.org/abs/2607.03279v1
• Date: Fri, 03 Jul 2026 12:49:06 GMT
• Title: From Global to Local: Efficient Regional Weather Downscaling with Global Weather Foundation Model
• Abstract summary: We propose a foundation-model-driven downscaling framework that learns regional refinements of global forecasts.<n>We use regional numerical simulations as training targets and are evaluated not only against gridded datasets but also against ground-based weather station observations.<n>Our experiments show improved accuracy in comparison to NWP on most of the metrics at the fraction of computational cost.
• Score: 0.0
• License: http://creativecommons.org/licenses/by/4.0/
• Abstract: 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.

Related papers

• StretchCast: Global-Regional AI Weather Forecasting on Stretched Cubed-Sphere Mesh [0.0]
  We introduce StretchCast, a global-regional AI forecasting framework built on a variable-resolution stretched cubed-sphere (SCS) mesh.<n>We develop a one-step predictor, SCS_Base Model, and a rollout-oriented multistep predictor, SCS_FCST4 Model, to test the feasibility of SCS-based forecasting.<n>With 83M parameters and training cost on the order of hours, SCS_FCST4 Model delivers competitive medium-range anomaly-correlation evolution over the target region.
  arXiv  Detail & Related papers  (2026-03-28T14:40:29Z)
• Demystifying Data-Driven Probabilistic Medium-Range Weather Forecasting [63.8116386935854]
  We demonstrate that state-of-the-art probabilistic skill requires neither intricate architectural constraints nor specialized trainings.<n>We introduce a scalable framework for learning multi-scale atmospheric dynamics by combining a directly downsampled latent space with a history-conditioned local projector.<n>We find that our framework design is robust to the choice of probabilistic estimators, seamlessly supporting interpolants, diffusion models, and CRPS-based ensemble training.
  arXiv  Detail & Related papers  (2026-01-26T03:52:16Z)
• STCast: Adaptive Boundary Alignment for Global and Regional Weather Forecasting [35.64570745321468]
  We propose a novel AI-driven framework for adaptive regional boundary optimization and dynamic monthly forecast allocation.<n>Specifically, our approach employs a Spatial-Aligned Attention (SAA) mechanism, which aligns global and regional spatial distributions.<n>We also design a Temporal Mixture-of-Experts (TMoE) module, where atmospheric variables from distinct months are dynamically routed to specialized experts.
  arXiv  Detail & Related papers  (2025-09-21T05:27:52Z)
• A comparison of stretched-grid and limited-area modelling for data-driven regional weather forecasting [0.493599216374976]
  Limit-area model (LAM) and stretched-grid model (SGM) approaches have emerged for generating high-resolution regional forecasts.<n>This study aims to understand how the differences in model design impact relative performance and potential applications.
  arXiv  Detail & Related papers  (2025-07-24T12:54:08Z)
• RainShift: A Benchmark for Precipitation Downscaling Across Geographies [21.183274939386088]
  We introduce RainShift, a dataset and benchmark for evaluating downscaling under geographic distribution shifts.<n>We evaluate state-of-the-art downscaling approaches including GANs and diffusion models in generalizing across data gaps between the Global North and Global South.<n>Our work advances the global applicability of downscaling methods and represents a step toward reducing inequities in access to high-resolution climate information.
  arXiv  Detail & Related papers  (2025-07-07T12:25:14Z)
• OneForecast: A Universal Framework for Global and Regional Weather Forecasting [67.61381313555091]
  We propose a global-regional nested weather forecasting framework (OneForecast) based on graph neural networks.<n>By combining a dynamic system perspective with multi-grid theory, we construct a multi-scale graph structure and densify the target region.<n>We introduce an adaptive messaging mechanism, using dynamic gating units, to deeply integrate node and edge features for more accurate extreme event forecasting.
  arXiv  Detail & Related papers  (2025-02-01T06:49:16Z)
• Efficient Localized Adaptation of Neural Weather Forecasting: A Case Study in the MENA Region [62.09891513612252]
  We focus on limited-area modeling and train our model specifically for localized region-level downstream tasks. We consider the MENA region due to its unique climatic challenges, where accurate localized weather forecasting is crucial for managing water resources, agriculture and mitigating the impacts of extreme weather events. Our study aims to validate the effectiveness of integrating parameter-efficient fine-tuning (PEFT) methodologies, specifically Low-Rank Adaptation (LoRA) and its variants, to enhance forecast accuracy, as well as training speed, computational resource utilization, and memory efficiency in weather and climate modeling for specific regions.
  arXiv  Detail & Related papers  (2024-09-11T19:31:56Z)
• MambaDS: Near-Surface Meteorological Field Downscaling with Topography Constrained Selective State Space Modeling [68.69647625472464]
  Downscaling, a crucial task in meteorological forecasting, enables the reconstruction of high-resolution meteorological states for target regions. Previous downscaling methods lacked tailored designs for meteorology and encountered structural limitations. We propose a novel model called MambaDS, which enhances the utilization of multivariable correlations and topography information.
  arXiv  Detail & Related papers  (2024-08-20T13:45:49Z)
• FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather Forecasting [56.73502043159699]
  This work presents FengWu-GHR, the first data-driven global weather forecasting model running at the 0.09$circ$ horizontal resolution. It introduces a novel approach that opens the door for operating ML-based high-resolution forecasts by inheriting prior knowledge from a low-resolution model. The hindcast of weather prediction in 2022 indicates that FengWu-GHR is superior to the IFS-HRES.
  arXiv  Detail & Related papers  (2024-01-28T13:23:25Z)
• Residual Corrective Diffusion Modeling for Km-scale Atmospheric Downscaling [58.456404022536425]
  State of the art for physical hazard prediction from weather and climate requires expensive km-scale numerical simulations driven by coarser resolution global inputs. Here, a generative diffusion architecture is explored for downscaling such global inputs to km-scale, as a cost-effective machine learning alternative. The model is trained to predict 2km data from a regional weather model over Taiwan, conditioned on a 25km global reanalysis.
  arXiv  Detail & Related papers  (2023-09-24T19:57:22Z)
• Increasing the accuracy and resolution of precipitation forecasts using deep generative models [3.8073142980733]
  We train a conditional Generative Adversarial Network -- coined CorrectorGAN -- to produce ensembles of high-resolution, bias-corrected forecasts. CorrectorGAN, once trained, produces predictions in seconds on a single machine. Results raise exciting questions about the necessity of regional models, and whether data-driven downscaling and correction methods can be transferred to data-poor regions.
  arXiv  Detail & Related papers  (2022-03-23T09:45:12Z)

This list is automatically generated from the titles and abstracts of the papers in this site.

This site does not guarantee the quality of this site (including all information) and is not responsible for any consequences.