<p>Performing accurate deep space orbit determination requires hi-fidelity modeling of orbital motion as well as measurement observables. Unexpected spacecraft events, biased tracking data, or mismodeling of the dynamics can result in an incorrect orbit estimate with potentially catastrophic consequences. The integrity of an orbit estimate is typically verified using an array of different formulations for the orbit determination problem. If the solutions of two or more formulations become statistically inconsistent, this can indicate a flawed model and an inaccurate baseline solution. Since each formulation is sensitive to different errors or anomalies, the pattern of comparisons provides a fingerprint with which to diagnose the error. By first simulating the response of the array to a catalogue of possible orbit determination mismodeling errors for an approaching Mars lander, we train a long short-term memory (LSTM) neural network to perform this diagnosis autonomously. We also develop a second autoencoder neural network for cataloging the unique comparison fingerprint of each mismodeling scenario. We show that the latent space of the fingerprints provides insight into and verification of the LSTM’s decisions, as well as helps develop intuition for the patterns that can be used to train human navigators, prepare operational readiness tests, and design orbit determination formulations.</p>