Unlocking GOES: A Statistical Framework for Quantifying the Evolution of Convective Structure in Tropical Cyclones
Tropical cyclones (TCs) rank among the most costly natural disasters in the United States, and accurate forecasts of track and intensity are critical for emergency response. Intensity guidance has improved steadily but slowly, as processes which drive intensity change are not fully understood. Because most TCs develop far from land-based observing networks, geostationary (Geo) satellite imagery is critical to monitoring these storms. Modern high-resolution Geo observations provide an unprecedented scientific opportunity. These complex data are however challenging to analyze by forecasters in real time, whereas off-the-shelf machine learning algorithms have limited applicability due to their "black box" structure. This study presents analytic tools that quantify convective structure patterns in infrared Geo imagery for over-ocean TCs, yielding lower-dimensional but rich representations that support analysis and visualization of how these patterns evolve during a rapid intensity change. The proposed ORB feature suite targets the global Organization, Radial structure, and Bulk morphology of TCs. Combined with a functional basis, the resulting representation of convective structure patterns on multiple scales serves as input to powerful but sometimes hard-to-interpret machine learning methods. This study uses the logistic lasso, a penalized generalized linear model, to relate predictors to rapid intensity change. Using ORB alone, binary classifiers identifying the presence (versus absence) of such events achieve accuracy comparable to classifiers using environmental predictors alone, while a combined predictor set further reduces nowcasting errors. More complex nonlinear machine learning methods did not improve accuracy over our linear logistic lasso model.
READ FULL TEXT