Coastal typhoon deformation plays a critical role in determining typhoon tracks, intensity changes, precipitation and related flooding, storm surges, and typhoon waves, and thus is highly associated with coastal disaster patterns. This study proposes a three-level framework for typhoon wind field modeling through the integration of geometric characterization with physical-informed reconstruction. At its core, an elliptical fitting method is developed based on second-order moments to quantify the structural asymmetries. This geometric fitting method is incorporated into the reconstruction method of Holland–Miyazaki, creating a physically consistent model capable of simulating typhoon deformation processes during landfall. Validation through high-resolution Weather Research and Forecasting (WRF) simulations of Typhoon Chan-hom (2015) demonstrates the framework’s effectiveness, capturing elliptical eyewall deformation with aspect ratios exceeding 1.5, primarily driven by coastal topography and surface friction interactions. The method is further validated through Typhoon Mitag (2019), with mean wind component errors below 1 m/s, the average correlation coefficients surpassing 0.9, and wind direction mean absolute errors largely below 10°. This research provides a practical framework for quantifying and characterizing the wind field deformation during typhoon landfall in coastal regions, thereby supporting ther operational forecasting and disaster reduction in vulnerable coastal regions.