FL-SPDP: Spatially Modulated Differentially Private Federated Learning for Robust Satellite Image Recognition

Satellite image recognition increasingly relies on data collected by geographically distributed institutions, but centralizing geospatial imagery is often infeasible due to policy and privacy constraints. Federated learning enables collaborative training, yet standard aggregation (e.g., FedAvg) degrades under strong geographic non-IID shifts, and adding client-level differential privacy (DP) can further reduce utility—especially for rare land-cover classes—due to gradient clipping and injected noise. We propose FL-SPDP, a spatially modulated DP federated framework that leverages coarse spatial priors to reweight and aggregate client updates among geographically related clients, improving robustness to heterogeneity while preserving formal privacy guarantees. Experiments on SEN12MS and BigEarthNet show that FL-SPDP improves accuracy and macro-F1 at a fixed privacy budget (ε≤3.5, δ=10−5) and strengthens rare-class performance, demonstrating an effective privacy–utility trade-off for satellite image analysis.