CNN Profiler on Polar Coordinate Images for Tropical Cyclone Structure Analysis
This work addresses the challenge of objectively analyzing TC structure, which is crucial for meteorology but has been subjective and underdeveloped, though it is incremental in applying existing deep learning techniques to a new domain-specific problem.
The study tackled the problem of objectively profiling tropical cyclone (TC) structure by applying convolutional neural networks (CNN) on satellite images, using a newly released benchmark dataset with labels derived from meteorological domain knowledge, and demonstrated the robustness of a specialized model operating on polar coordinates.
Convolutional neural networks (CNN) have achieved great success in analyzing tropical cyclones (TC) with satellite images in several tasks, such as TC intensity estimation. In contrast, TC structure, which is conventionally described by a few parameters estimated subjectively by meteorology specialists, is still hard to be profiled objectively and routinely. This study applies CNN on satellite images to create the entire TC structure profiles, covering all the structural parameters. By utilizing the meteorological domain knowledge to construct TC wind profiles based on historical structure parameters, we provide valuable labels for training in our newly released benchmark dataset. With such a dataset, we hope to attract more attention to this crucial issue among data scientists. Meanwhile, a baseline is established with a specialized convolutional model operating on polar-coordinates. We discovered that it is more feasible and physically reasonable to extract structural information on polar-coordinates, instead of Cartesian coordinates, according to a TC's rotational and spiral natures. Experimental results on the released benchmark dataset verified the robustness of the proposed model and demonstrated the potential for applying deep learning techniques for this barely developed yet important topic.