DeepDownscale: a Deep Learning Strategy for High-Resolution Weather Forecast
This addresses the need for affordable high-resolution weather forecasts for sectors like agriculture, transportation, and energy, though it is an incremental improvement over existing methods.
The paper tackles the problem of generating high-resolution weather forecasts from low-resolution models, which is computationally expensive, by proposing a deep learning strategy that learns high-resolution representations from low-resolution inputs. The results show significant improvement over standard practices and the method is lightweight enough to run on modest systems.
Running high-resolution physical models is computationally expensive and essential for many disciplines. Agriculture, transportation, and energy are sectors that depend on high-resolution weather models, which typically consume many hours of large High Performance Computing (HPC) systems to deliver timely results. Many users cannot afford to run the desired resolution and are forced to use low resolution output. One simple solution is to interpolate results for visualization. It is also possible to combine an ensemble of low resolution models to obtain a better prediction. However, these approaches fail to capture the redundant information and patterns in the low-resolution input that could help improve the quality of prediction. In this paper, we propose and evaluate a strategy based on a deep neural network to learn a high-resolution representation from low-resolution predictions using weather forecast as a practical use case. We take a supervised learning approach, since obtaining labeled data can be done automatically. Our results show significant improvement when compared with standard practices and the strategy is still lightweight enough to run on modest computer systems.