Interpretable semi-supervised clustering enables universal detection and intensity assessment of diverse aviation hazardous winds

Abstract

The identification of aviation hazardous winds is crucial and challenging in air traffic management for assuring flight safety, particularly during the take-off and landing phases. Existing criteria are typically tailored for special wind types, and whether there exists a universal feature that can effectively detect diverse types of hazardous winds from radar/lidar observations remains as an open question. Here we propose an interpretable semi-supervised clustering paradigm to solve this problem, where the prior knowledge and probabilistic models of winds are integrated to overcome the bottleneck of scarce labels (pilot reports). Based on this paradigm, a set of high-dimensional hazard features is constructed to effectively identify the occurrence of diverse hazardous winds and assess the intensity metrics. Verification of the paradigm across various scenarios has highlighted its high adaptability to diverse input data and good generalizability to diverse geographical and climate zones. The identification of aviation hazardous winds is crucial for flight safety, especially during take-off and landing. Here, authors propose an interpretable semi-supervised clustering method to detect diverse hazardous winds from radar/lidar observations, integrating prior knowledge and probabilistic models.