Multi-Source Context Fusion for SIGINT: Marrying SDR Streams with Astrophysical (JWST),Orbital (ISS),and HEP (LHC) Telemetry to Enrich Classification

We study multi-source context fusion for signal classification from software-defined radio (SDR) streams. We explore
enriching SDR features with contemporaneous, public-domain
telemetry from astrophysical (e.g., observatory scheduling and
environment), orbital (e.g., satellite attitude/visibility windows),
and high-energy physics (e.g., collider run states) sources. We
present a time-aligned fusion architecture and an evaluation
harness that reports AUROC/F1 alongside latency. On placeholder
metrics, fusion improves AUROC from 0.820 (SDR-only) to 0.892
(all-context fused), with modest latency overhead (p50 from
4.40 ms to 6.10 ms).