A two-stage deep learning pipeline (HT-LCNN detector + VGG6 classifier) trained on augmented real and simulated data detects streaks in OmegaCAM frames with F1 > 0.95 on test sets and 0.99 precision on real 2023 data, uncovering 25,335 streaks including >20% uncatalogued objects across 1.2 million f
Secular Brightness Trends of Starlink and OneWeb Satellites
1 Pith paper cite this work. Polarity classification is still indexing.
1
Pith paper citing it
abstract
Magnitudes recorded from 2021 through 2026 for Starlink VisorSats reveal brightening of 0.6 magnitudes, while those of OneWeb show dimming of 0.4. Both trends are significant at 3 sigma. This study is based on 1.6 million magnitudes recorded by the MMT9 robotic observatory.
fields
astro-ph.IM 1years
2026 1verdicts
UNVERDICTED 1representative citing papers
citing papers explorer
-
Streak detection in the VST/OmegaCAM archive using deep learning
A two-stage deep learning pipeline (HT-LCNN detector + VGG6 classifier) trained on augmented real and simulated data detects streaks in OmegaCAM frames with F1 > 0.95 on test sets and 0.99 precision on real 2023 data, uncovering 25,335 streaks including >20% uncatalogued objects across 1.2 million f