Search papers, labs, and topics across Lattice.
This paper addresses the limitations of high-resolution weather forecasting by introducing BaguanHR, a framework that emphasizes data transfer over model transfer to overcome the challenges posed by coarse-resolution data. By employing variable-wise super-resolution to synthesize extensive 0.1掳 data from existing 0.25掳 reanalysis datasets, the authors achieve superior forecasting performance, surpassing both traditional ML methods and the Integrated Forecasting System High-Resolution model. Notably, their findings reveal a power-law scaling effect, where doubling the data leads to significant reductions in RMSE for 72-hour and 120-hour forecasts, underscoring the critical role of data availability in enhancing forecasting accuracy.
Doubling the data can reduce forecasting errors by nearly 5%, revealing a crucial data bottleneck in high-resolution weather prediction.
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.
