Novel Segmentation Method for Subtropical Highs: Integrating Machine Learning with Fengyun-4 Satellite Observations

The subtropical high is a fundamental large-scale meteorological system that governs tropical and subtropical regions. Its structural variations, driven by interactions between tropical circulation and mid-to high-latitude systems, are closely related to regional heavy rainfall, summer heatwaves, and other extreme weather events. Consequently, accurately characterizing both the intensity and spatial features of the subtropical high is critical for weather forecasting and short-term climate predictions. In this study, we introduce FY_STH, a machine learning model that synthesizes brightness temperature data from Fengyun-4's Advanced Geosynchronous Radiance Imager (AGRI) with satellite-retrieved outgoing longwave