Gnomon: Physics-Informed Link-State Forecasting for LEO Networks

This paper presents Gnomon, a physics-informed system for forecasting user-perceived LEO downlink/uplink throughput and round-trip time. The physics layer reconstructs serving geometry and four-leg bent-pipe attenuation from public weather, orbital, routing, and licensing data. Gnomon operates in two modes based on data availability: conditioning on the target terminal's own history or leveraging measurements from nearby public terminals. The approach targets RF and signal propagation physics in satellite communication networks.