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

arXiv: https://arxiv.org/abs/2608.14652 · HTML: https://mlsanity.com/paper/2608.14652/

## Key facts

- No citing papers in the map yet (data through 14 Oct 2026).
- Builds on 23 of its 39 references that are in the map.
- First posted on arXiv 31 Jul 2026.

## Builds on (most cited first, 23 of 23)

- [Swin Transformer: Hierarchical Vision Transformer using Shifted Windows](https://mlsanity.com/paper/2103.14030/) (2021)
- [Scaling Laws for Neural Language Models](https://mlsanity.com/paper/2001.08361/) (2020)
- [Fourier Neural Operator for Parametric Partial Differential Equations](https://mlsanity.com/paper/2010.08895/) (2020)
- [Reproducible scaling laws for contrastive language-image learning](https://mlsanity.com/paper/2212.07143/) (2022)
- [Scaling Vision Transformers](https://mlsanity.com/paper/2106.04560/) (2021)
- [ClimaX: A foundation model for weather and climate](https://mlsanity.com/paper/2301.10343/) (2023)
- [FuXi: A cascade machine learning forecasting system for 15-day global weather forecast](https://mlsanity.com/paper/2306.12873/) (2023)
- [WeatherBench 2: A benchmark for the next generation of data-driven global weather models](https://mlsanity.com/paper/2308.15560/) (2023)
- [Disentangling Physical Dynamics from Unknown Factors for Unsupervised Video Prediction](https://mlsanity.com/paper/2003.01460/) (2020)
- [FourCastNet: Accelerating Global High-Resolution Weather Forecasting using Adaptive Fourier Neural Operators](https://mlsanity.com/paper/2208.05419/) (2022)
- [FengWu: Pushing the Skillful Global Medium-range Weather Forecast beyond 10 Days Lead](https://mlsanity.com/paper/2304.02948/) (2023)
- [Is Model Collapse Inevitable? Breaking the Curse of Recursion by Accumulating Real and Synthetic Data](https://mlsanity.com/paper/2404.01413/) (2024)
- [Scaling transformer neural networks for skillful and reliable medium-range weather forecasting](https://mlsanity.com/paper/2312.03876/) (2023)
- [DeepSD: Generating High Resolution Climate Change Projections through Single Image Super-Resolution](https://mlsanity.com/paper/1703.03126/) (2017)
- [Swin2SR: SwinV2 Transformer for Compressed Image Super-Resolution and Restoration](https://mlsanity.com/paper/2209.11345/) (2022)
- [A Generative Deep Learning Approach to Stochastic Downscaling of Precipitation Forecasts](https://mlsanity.com/paper/2204.02028/) (2022)
- [FengWu-GHR: Learning the Kilometer-scale Medium-range Global Weather Forecasting](https://mlsanity.com/paper/2402.00059/) (2024)
- [Universality of the π2/6 Pathway in Avoiding Model Collapse](https://mlsanity.com/paper/2410.22812/) (2024)
- [Machine learning emulation of a local-scale UK climate model](https://mlsanity.com/paper/2211.16116/) (2022)
- [Scaling Laws of Global Weather Models](https://mlsanity.com/paper/2602.22962/) (2026)
- [Utilizing Strategic Pre-training to Reduce Overfitting: Baguan -- A Pre-trained Weather Forecasting Model](https://mlsanity.com/paper/2505.13873/) (2025)
- [Coarse Graining with Neural Operators for Simulating Chaotic Systems](https://mlsanity.com/paper/2408.05177/) (2024)
- [Learning from Synthetic Data: Limitations of ERM](https://mlsanity.com/paper/2601.15468/) (2026)

## Abstract (arXiv)

The development of 0.1circ 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 0.25circ resolution. While existing approaches fine-tune 0.25circ forecast models on limited 0.1circ samples, we show that this transfer is hindered by the irreversible information loss inherent in coarse-resolution forecasting. Therefore, we propose BaguanHR, a framework that shifts the focus from transferring models to transferring data. We first show that super-resolution (SR) has lower conditional entropy and input amplification than forecasting, making it a more robust vehicle for resolution transfer. By leveraging this advantage through variable-wise SR, we synthesize extensive 0.1circ data from ERA5. BaguanHR's performance on the synthetic-plus-real dataset exceeds both ML-based methods and IFS-HRES, achieving superior performance across over 85% of the lead times within 72 hours. Furthermore, our findings highlight a power-law scaling effect, as a twofold increase in data reduces RMSE by 4.6% for 72-hour forecasting and 4.9% for 120-hour forecasting. Our results demonstrate that scaling high resolution ML-based forecasting is primarily a data bottleneck, and that variable-wise super-resolution provides a simple yet general solution to unlock long coarse-resolution reanalyses for high-resolution training.