Observation-Guided Meteorological Field Downscaling at Station Scale: A Benchmark and a New Method
This work addresses the challenge of aligning downscaled meteorological data with actual station observations, which is crucial for accurate weather forecasting, though it is incremental in applying data assimilation techniques to this domain.
The paper tackles the problem of downscaling meteorological fields to arbitrary station scales, which previous deep learning methods struggled with due to systematic biases. The proposed HyperDS method integrates observational data and achieves significant improvements, such as a 67% reduction in MSE for wind speed and 19.5% for surface pressure compared to baselines.
Downscaling (DS) of meteorological variables involves obtaining high-resolution states from low-resolution meteorological fields and is an important task in weather forecasting. Previous methods based on deep learning treat downscaling as a super-resolution task in computer vision and utilize high-resolution gridded meteorological fields as supervision to improve resolution at specific grid scales. However, this approach has struggled to align with the continuous distribution characteristics of meteorological fields, leading to an inherent systematic bias between the downscaled results and the actual observations at meteorological stations. In this paper, we extend meteorological downscaling to arbitrary scattered station scales, establish a brand new benchmark and dataset, and retrieve meteorological states at any given station location from a coarse-resolution meteorological field. Inspired by data assimilation techniques, we integrate observational data into the downscaling process, providing multi-scale observational priors. Building on this foundation, we propose a new downscaling model based on hypernetwork architecture, namely HyperDS, which efficiently integrates different observational information into the model training, achieving continuous scale modeling of the meteorological field. Through extensive experiments, our proposed method outperforms other specially designed baseline models on multiple surface variables. Notably, the mean squared error (MSE) for wind speed and surface pressure improved by 67% and 19.5% compared to other methods. We will release the dataset and code subsequently.