Track new results across pure and applied mathematics.
Search papers, labs, and topics across Lattice.
This paper introduces BaguanHR, a novel framework that prioritizes data transfer over model transfer to enhance high-resolution weather forecasting at 0.1° resolution. By employing variable-wise super-resolution (SR) techniques, the authors synthesize extensive high-resolution datasets from existing coarse-resolution reanalysis data, overcoming the limitations posed by irreversible information loss in traditional forecasting methods. The results show that BaguanHR outperforms existing ML-based approaches and IFS-HRES, achieving significant reductions in RMSE with a power-law scaling effect, indicating that data availability is the primary constraint in high-resolution forecasting.
Scaling high-resolution weather forecasting is fundamentally limited by data availability, but BaguanHR's innovative approach reveals that super-resolution can unlock vast amounts of usable data from existing coarse datasets.
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$^{\circ}$ resolution. While existing approaches fine-tune 0.25$^{\circ}$ forecast models on limited 0.1$^{\circ}$ 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 0.1$^{\circ}$ 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.