Geoduck: Nanosatellite Constellation Scheduling for Low Latency Event Detection

Commercial companies have launched hundreds of small, low-cost nanosatellites for Earth observation tasks, such as monitoring forest fires, landslides, and lake algae. These time-critical events require low-latency detection. Previous work has shown that capture latency, defined as the duration between an event occurrence and a satellite capturing an image covering the event region, is the major latency component. In this work, we ask what the minimum capture latency is under physical orbital dynamics and energy constraints. We first characterize how region location and satellite orbital configuration affect the capture latency. Next, we explore the scheduling of satellite captures when energy constraints prevent the capture of all images. We introduce Geoduck, a satellite capture scheduler specifically designed to minimize capture latency. Geoduck leverages the insight that the timing of many events follows a prior distribution; for example, forest fires are more likely to occur in summer. We analyze the impact of different capture schedules on latency and propose a dynamic programming algorithm to choose the optimal captures. Our evaluation shows that Geoduck reduces capture latency by 1.5--2.1×.