Learning the LoS Skyline from LEO Satellite Observations for Proactive Handover

2026-07-31

AI Summary

This work addresses the challenge of abrupt line-of-sight link outages in low Earth orbit satellite communications caused by local obstructions. The authors propose a map-free approach that requires no 3D maps, sky cameras, or explicit environmental sensing, instead formulating the local skyline as a binary classification problem in azimuth–elevation space. By leveraging passively observed signal availability labels at the user terminal, the method learns the occlusion boundary. A novel integration of Gaussian processes with a neural network featuring circular azimuth encoding is introduced, along with EphemerisWindow to enable trajectory-level link outage prediction. Experimental results demonstrate that both proposed learning-based estimators significantly outperform empirical bounding methods, accurately reconstructing the skyline and enabling proactive handover before link disruption.

Abstract

In non-terrestrial network deployments, local obstructions may block line-of-sight satellite links before the satellite reaches the geometric elevation mask, causing abrupt and unplanned handovers. To address this limitation, this paper proposes a map-free method for learning the local LoS skyline, defined as the obstruction elevation over azimuth, from binary availability labels derived from passive satellite signal observations at the terminal. The problem is formulated as a binary classification task in the azimuth-elevation space, where the skyline is extracted as the decision boundary of the learned blockage probability surface. Two complementary estimators are investigated, namely a Gaussian Process (GP) classifier and a neural multilayer perceptron (MLP) with circular azimuth encoding and Monte Carlo Dropout uncertainty indicators. The learned obstruction surface is then combined with satellite ephemeris information through EphemerisWindow, a trajectory-level prediction method that estimates future LoS termination events before the serving link is lost. The results show that both learned estimators improve the skyline reconstruction compared with empirical bracketing and enable proactive handover preparation without requiring 3D building maps, sky cameras, or additional environmental sensing.

Problem

• non-terrestrial networks
• line-of-sight blockage
• proactive handover
• LEO satellite
• obstruction skyline

Innovation

• LoS skyline learning
• map-free obstruction modeling
• Gaussian Process classifier
• neural MLP with circular encoding
• proactive handover