We introduce a topological data analysis (TDA) framework to characterize departure‐delay co-occurrence in Japan’s domestic airline networks. By constructing a delay‐based filtration on daily delayed flight networks for All Nippon Airways (ANA) and Japan Airlines (JAL), we track how airports form delay co-occurrence loops through persistent homology using Vietoris–Rips complex filtration technique. We find JAL’s network is more fragmented, while ANA shows wider, longer-lasting delay loops before COVID-19. In winter, airports take longer to join into connected groups, and delay loops last longer. During COVID-19, delays shrink for both airlines. As flights recover, multi-airport loops return, and some last longer than before. Tokyo Haneda Airport and its primary feeder airports emerge as central to the most delay loops, suggesting targeted buffering and schedule adjustments at these airports. Our findings demonstrate TDA’s unique ability to uncover higher‐order delay dynamics and assist departure delay management strategies.
Sadeek et al. (Mon,) studied this question.