Facilitating Noneyed Tropical Cyclone Center Location Utilizing Multiscale Extraction of Geopotential Height and Water Vapor Features

Tropical cyclones (TCs) are destructive weather systems, and it is crucial to accurately locate their positions, estimate their intensity, and predict their trajectories to reduce their potential damage. Due to their excellent ability to extract deep spatial features from satellite images, machine-learning-based methods can fully mine the relationships between image features and TC positions, which have become the mainstream approach in the field of TC center location. However, the existing methods mainly rely on the eye features identified from infrared (IR) channels of satellite images, which can be an invalid approach during the TC generation or extinction phase as the eye structures in these two phases are blurred. To address this problem, this study examines the relationship between the TC center and the low geopotential height (GPH) center and proposes a noneyed TC center location method by fusing the features from satellite images and GPH data. In the proposed method, a water vapor (WV) attention module is used to focus on regions with WV distribution patterns closely related to the TC center. Moreover, a multiscale attention module (MSAM) is designed to mine and fuse knowledge from different spatial scales, aiming to extract the TC structural features fully. The performance of the proposed model is verified through experiments using Gridsat, International Best Track Archive for Climate Stewardship (IBTrACS) and European Center for Medium-Range Weather Forecasts (ECMWF) High-resolution Forecast (HRES) datasets. The results show that compared with the existing methods, the mean distance error (MDE) of the TC’s center location is reduced by at least 11.3% compared with state-of-the-art prediction models.