LunarFL: Federated Terrain Learning Across Distributed Planetary Surface Assets Under Intermittent, Thermally Gated Connectivity
Year: 2026
Type: article
Abstract: As the Artemis and Moon-to-Mars programs advance toward a sustained lunar presence, semi-autonomous surface assets must perceive terrain on board while sharing a scarce, thermally constrained link budget. Federated learning (FL) fits this setting: assets improve a shared perception model by exchanging updates rather than raw imagery. Existing FL studies, however, assume near-persistent connectivity and evaluate on synthetically partitioned data. This paper reports what is, to the author’s knowledge, the first evaluation of federated terrain segmentation on real planetary rover imagery under a physically motivated model of intermittent, thermally gated connectivity. A naturally non-independent-and-identically-distributed (non-IID) three-client federation is built from the AI4Mars Curiosity dataset and the synthetic Artificial Lunar Landscape dataset; its heterogeneity is measured, not assumed (mean pairwise Jensen–Shannon divergence 0.42). A SegFormer-B0 model is trained with FedAvg while an aggregation probability $p_{\mathrm {agg}}$ and a thermal duty cycle gate every round. Over 113 runs with up to five seeds per condition, accuracy declines monotonically with aggregation scarcity: federation recovers 88.8% of the gap between local-only (0.363 mIoU) and centralized (0.897) training at $p_{\mathrm {agg}}=1$ , 78.6% at 0.3, and 5.9% at 0.05. The deficit scales as $p_{\mathrm {agg}}^{{\,}b}$ with $b=-0.650$ (95% CI $[-0.755,-0.545]$ ), steeper than the optimization-limited $1/\sqrt {p_{\mathrm {agg}}}$ reference and consistent with heterogeneity-driven client drift. Neither a proximal term nor server momentum recovers the scarce regime, and the temporal structure of outages, not the mean rate alone, governs predictability. Uplink volume is reported alongside accuracy at every operating point.
Source: IEEE Access
Author: Anas Shahin
Institution: Syrian Virtual University
Language: English
Subfield: Artificial Intelligence
Field: Computer Science
Domain: Physical Sciences
Open Access status: gold
Estimated APC paid: $2,075
OpenAlex ID: W7214620906