Statistical Analysis of Machine Learning-Derived Equatorial Plasma Bubble Characteristics from Airglow Observations in Southern China During a Solar Cycle
The EPB (equatorial plasma bubble) evolutionary behavior in the Chinese sector remains poorly understood due to insufficient long-term statistical characterization. Leveraging prior machine learning frameworks, this work presents the first statistical profile of EPB evolution over an entire solar cycle (2012-2022) in southern China, using airglow observations from Qujing, China (geographical: 25°N, 104°E; geomagnetic: 15.1°N, 176.7°E). The results reveal that: the relative occurrence frequency (ROF) peaks at ~22:15 local time (LT) and exhibits equinoctial asymmetry, with spring and autumn showing double pre-midnight peaks (22:15 and 23:30 LT), while winter displays a single peak (22:15 LT). The peak activities of AREA-FOV (field-of-view coverage area) and PMLE (poleward magnetic latitude extension) exhibit synchronous timing, predominantly occurring at 21:00, 23:00, 01:00, 03:30, and 05:00 LT. Before 02:00 LT, AREA-FOV and PMLE show seasonal variations: spring > autumn > winter. Zonal drift velocity peaks at 22:15 LT (primary), 01:45 LT (secondary), 03:45 LT (tertiary), and 05:45 LT (quaternary). Seasonal variations are notable, with smaller velocity fluctuations in spring/autumn and larger fluctuations in winter. Solar activity strongly influences EPB dynamics: higher AREA-FOVs, PMLEs, and drift velocities occur during high solar activity. Unexpectedly, geomagnetic disturbances weakly increase ROF but suppress drift velocity, PMLE, and AREA-FOV versus quiet times. Notably, our results reveal consistent bimodal variations (sudden decrease followed by increase) in ROF during the 00:00 LT ±30-minute window, which persist regardless of statistical methodology. These findings provide critical insights into EPB evolutionary behavior in the understudied Chinese sector.