Description: We build machine learning capabilities that enables the Shadow Mode Assessment using Realistic Technologies for the NAS (SMART NAS) system to synthesize, optimize, and "auto-suggest" optimized Traffic Management Initiatives (TMIs). Multi Level Multi View (MLMV) machine learning is used to identify similar historical situations (days, scenarios, or airport conditions) in the NAS. TMIs used in historically similar situations are locally modified to optimize the parameters of the TMI to be used in the current day situation. SMART NAS is used to evaluate TMIs and to present fast time simulations to the end user to review the TMI and associated performance metrics before implementation.

Benefits: NASA's Airspace Operations and Safety Program (AOSP) projects, including: Traffic Flow Management (TFM) optimization, Trajectory-Based Operations (TBO), Super Density Operations (SDO), Integrated Arrival/Departure/Surface Operations (IADS), Weather Integrated Decision Making (Wx Integration), Dynamic Weather Routes (DWR), Interval Management (IM), Efficient Descent Advisor (EDA), Precision Departure Release Capability (PDRC), Choke Point Analysis, Network Enabled ATM, and Fully Automated ATM/Airspace Operations System (AutoMax).

A commercial product can be customized and implemented under contract to AOCs for use by dispatchers and ATC coordinators. In such applications, when the ATSP is deciding on taking a certain TMI action, for instance, as discussed in a CDM telecom, the AOC user can run forward in time through the remainder of the schedule for the day to see if delays will propagate, if the ATM-Wx impacts will cause cancellations, or if crew curfew limits will be negatively affected.