The 2009 Mars Science Laboratory (MSL) will attempt the first precision landing on Mars using a modified version of the Apollo Earth entry guidance program. The guidance routine, Entry Terminal Point Controller (ETPC), commands the deployment of a supersonic parachute while converging the range to the landing target. For very dispersed cases, ETPC is unlikely to converge the range to the target and command parachute deployment within Mach number and dynamic pressure constraints. A full-lift-up abort can save 85% of these failed trajectories while abandoning the precision landing objective. In order to implement an abort, a failed trajectory needs to be recognized in real time. The application of artificial neural networks (ANNs) as an abort determination technique was evaluated. An ANN was designed, trained and tested using Monte Carlo simulations of MSL descent for a severe dust storm scenario. When incorporated into ETPC, the ANN correctly classifies 87% of descent trajectories as abort or non-abort, reducing the probability of losing MSL in a severe dust storm from 18% to 3.5%. This research shows that ANNs are capable of recognizing failed descent trajectories and can significantly increase the survivability of MSL for very dispersed cases.