PulseAugur
EN
LIVE 09:59:06

AI models achieve high-resolution weather forecasting using data scaling and stretched grids

By PulseAugur Editorial · [2 sources] ·

Two new research papers explore advanced machine learning techniques for high-resolution weather forecasting. The first paper introduces BaguanHR, a framework that uses super-resolution to synthesize high-resolution data from existing lower-resolution datasets, outperforming current ML-based methods and operational models. The second paper presents a probabilistic data-driven model utilizing a stretched grid to achieve 2.5 km resolution in specific regions, showing improved accuracy over operational forecasts for certain variables. AI

IMPACT These advancements in AI-driven weather modeling could lead to more accurate and timely forecasts, improving disaster preparedness and resource management.

RANK_REASON Two research papers published on arXiv detailing novel machine learning approaches for weather forecasting.

Read on arXiv cs.AI →

AI-generated summary · Google Gemini · from 2 sources. How we write summaries →

AI models achieve high-resolution weather forecasting using data scaling and stretched grids

COVERAGE [2]

  1. arXiv cs.AI TIER_1 English(EN) · Yang Zhao, Peisong Niu, Tian Zhou, Ziqing Ma, Guanlong Ma, Rong Jin, Huiling Yuan, Liang Sun ·

    Pushing the Limits of High-Resolution Weather Forecasting through Data Scaling

    arXiv:2608.14652v1 Announce Type: cross Abstract: The development of 0.1$^{\circ}$ global weather forecasting models based on machine learning (ML) is constrained by the limited availability of high-resolution data, as decades of reanalysis are only available at 0.25$^{\circ}$ re…

  2. arXiv cs.AI TIER_1 English(EN) · Even Marius Nordhagen, H{\aa}vard Homleid Haugen, Magnus Sikora Ingstad, Aram Farhad Shafiq Salihi, Thomas Nils Nipen, Ivar Ambj{\o}rn Seierstad, Inger-Lise Frogner, Mariana Clare, Simon Lang, Matthew Chantry, Peter Dueben, J{\o}rn Kristiansen ·

    High-Resolution Probabilistic Data-Driven Weather Modeling with a Stretched-Grid

    arXiv:2511.23043v2 Announce Type: replace-cross Abstract: We present a probabilistic data-driven weather model providing ensembles of high spatial resolution realizations of 87 variables at arbitrary ensemble size and forecast length. The model uses a global stretched grid, dedic…

RELATED ENTITIES

RELATED TOPICS