Abstract: Apparatuses, methods, systems, and program products are disclosed for compression and distribution of meteorological data using machine learning. An apparatus includes a processor and a memory that stores code executable by the processor to receive a raw meteorological data set for a time frame, the raw meteorological data set comprising a plurality of dimensions. The code is executable by the processor to compress the raw meteorological data set using a machine learning encoding model to create an encoded meteorological data set that has a storage size that is smaller than a storage size of the raw meteorological data set, wherein the encoded meteorological data set can be decoded to create a decoded meteorological data set that is substantially similar to the raw meteorological data set. The code is executable by the processor to make the encoded meteorological data set accessible to one or more end users.

Abstract: Examples are disclosed that related to providing flight-delay estimations of airborne flights in a real-time environment. In one example, an aircraft information message for a current aircraft flight is received. The aircraft information message has a designated format consumable by a machine learning model previously trained to assess delay predictions for aircraft flights. The aircraft information message includes one or more aircraft flight-plan parameters, one or more aircraft surveillance parameters, and one or more weather parameters for the current aircraft flight. The aircraft information message is provided as input to the machine learning model to assess a real-time delay prediction for the current aircraft flight based at least on the one or more flight-plan parameters, the one or more aircraft surveillance parameters, and the one or more weather parameters included in the aircraft information message.

Abstract: A device includes one or more processors configured to receive an indication that a geographical area is expected to be regulated during a particular time window. The one or more processors are also configured to perform a comparison of the geographical area to route segments of a filed flight plan of a flight of an aircraft. The one or more processors are further configured to, based on determining that a route segment of the filed flight plan traverses at least a portion of the geographical area during the particular time window, determine alternate flight plans that do not traverse the geographical area during the particular time window. The one or more processors are also configured to select one of the alternate flight plans that satisfies a selection criterion as an updated flight plan of the flight, and to send the updated flight plan to a second device.

Abstract: Apparatuses, methods, systems, and program products are disclosed for dynamic selection of an aeronautical data provider. An apparatus includes a processor and a memory that stores code executable by the processor to receive a first stream of real-time aeronautical data from a first aeronautical data provider, receive at least one second stream of real-time aeronautical data from at least one second aeronautical data provider simultaneously with the first stream, provide data from the first stream and the at least one second stream to a decision model for predicting which data has a higher accuracy, and switch using data from the first stream to data from one of the at least one second streams in response to the one of the at least one second streams having a higher predicted accuracy than the first stream.

Abstract: A method of flight data prediction for an aircraft includes receiving, at a device, arrival input data for a flight of the aircraft to an arrival airport. The arrival input data includes flight plans for a plurality of aircraft expected to arrive at or depart from the arrival airport during an arrival time range, predicted weather information for the arrival airport during the arrival time range, and facilities data for the arrival airport. The method includes generating, at the device based on the arrival input data, one or more arrival sets for the aircraft. Each arrival set comprising a predicted gate arrival time for the aircraft at an arrival gate using a particular runway and a probability associated with the aircraft using the particular runway. The method also includes generating, at the device, an output based on at least one of the one or more arrival sets.

Abstract: A parking stand prediction system uses statistical analysis and historical data to provide an available parking stand for an aircraft at an arrival airport. The system receives real-time surveillance data relating to airlines, on-air flights, and airline and airport ground services. The surveillance data is sorted or pre-filtered according to airport. The system also receives airport map or layout data. Parking stand identification logic is applied to the surveillance data, airport map data, and historical surveillance data. Portions of this data are stored in a parking stand database which is continuously updated with current surveillance and parking stand availability data. A user inputs parking stand search parameter data into the system and receives a parking stand prediction for the aircraft of interest at an arrival airport.