The SDA enterprise requires transparent, repeatable, and explainable analytics to evaluate algorithms, understand estimator behavior, and compare modeling approaches. Selene is an experimental Space Domain Awareness (SDA) analytics prototype built to deliver residual‑driven evidence, multi‑sensor experimentation, and truth‑anchored research inside a modular, interactive 3‑D web environment.
By analyzing residual bias, drift, discontinuities, and non‑random structure, Selene provides sensor‑agnostic indicators of maneuvers, anomalies, and sensor/track degradation—offering a transparent, explainable environment for experimentation and evaluation.
Selene is anchored by the Residual Intelligence Suite (RIS)—a collection of prototype experiments that transform raw residuals into interpretable, actionable evidence.
Identifies maneuver signatures in R/I/C coordinates using TLE differencing, drift removal, robust normalization, and residual cues such as discontinuities, χ² spikes, and spectral structure.
Maneuver Fingerprinting via Residual Shape LibraryA physics‑grounded library of RIC residual shapes enables probabilistic, explainable classification of impulsive Δv events, low‑thrust behaviors, drag/SRP effects, plane changes, and station‑keeping patterns.
Unsupervised clustering in whitened residual space separates maneuvering behavior, sensor drift, track inconsistency, and non‑Gaussian anomalies—creating an independent detection channel.
Residual‑driven model selection activates appropriate force‑model fidelity (e.g., higher‑order gravity, SRP, drag) based on bias, whiteness, and spectral structure.
Real‑time trust scoring and adaptive weighting improve fusion stability, estimator consistency, and cross‑sensor coherence.
Synthetic Observation Validator & Truth Gap IndexCompares synthetic and real residual distributions to quantify realism, tune sensor models, and compute a Truth Gap Index summarizing distance to truth bounds.
Orbit Health Score & Explainability LayerUnified metrics combine RMS, χ², bias stability, sensor trust, and maneuver likelihood to provide concise, explainable orbit‑health assessments.
Soteria provides automated RMF workflow support, readiness tracking, and security‑evidence generation—enabling continuous monitoring and reducing time‑to‑ATO.
A natural‑language agent capable of executing and evaluating Selene orbital, fusion, and threat‑analysis workflows.
