A low-Earth-orbit satellite has only minutes to downlink imagery on a limited power budget, and some moments in a pass carry far better channels than others. Spending more power on the good moments and skipping hopeless ones should deliver more images, but the channel cannot be measured in time, so the schedule is planned in advance from weather statistics using a safety margin. That margin is sized so the forecast is statistically reliable, and the scheduler is judged by whether it beats uniform power on average. Both targets are wrong for a satellite that gets one attempt per pass: on real Sentinel-2 imagery, a scheduler gaining one to two images per pass on average still delivers fewer than uniform power on a quarter to a third of individual passes, and a genie knowing the weather exactly does no better. We instead size the margin by measuring, on recorded passes, how often it would have backfired, keeping only settings that provably backfire rarely. The procedure declines to schedule our learned codec and certifies scheduling for codecs with a sharper cliff.

翻译：暂无翻译