Determining VTOL departure time in an aviation transport network for efficient resource management

A non-transitory computer-readable storage medium storing executable computer program code that, when executed by one or more processors, causes the one or more processors to perform operations comprising:

• receiving, from a client device, a request for transport services transmitted over a network, the request including data identifying a rider, an origin, and a destination;
• determining based on the origin and the destination that the transport request is eligible to be serviced, at least in part, by a vertical take-off and landing (VTOL) aircraft;
• sending over the network, to the client device, itinerary data for servicing the transport request, the itinerary data identifying a leg serviced by the VTOL aircraft;
• receiving confirmation data indicating that the rider has boarded the VTOL aircraft;
• accessing historical demand data indicating a variation in demand over time and that includes an expected number of riders in a given time period;
• determining, based on a comparison between the historical demand data and a current time and day, that the VTOL aircraft should wait for additional riders, wherein determining that the VTOL aircraft should wait for additional riders comprises:
• calculating, using a machine-learning model trained with the historical demand data by a minimizing a loss function retrained over time with data corresponding to actual transport requests serviced, a value indicative of a probability that an additional rider will board the VTOL aircraft within a specified time, and
• determining that the VTOL aircraft should wait if the probability exceeds a threshold;
• and
• after the VTOL aircraft waits in response to the probability exceeding the threshold, sending an instruction over the network to the VTOL aircraft to take-off responsive to one or more conditions being met.

A computer system comprising:

• one or more processors;
• and
• a non-transitory computer-readable storage medium comprising executable computer program code, the computer program code when executed causing the one or more processors to perform operations including:
• receiving, from a client device, a request for transport services transmitted over a network, the request including data identifying a rider, an origin, and a destination;
• determining based on the origin and the destination that the transport request is eligible to be serviced, at least in part, by a vertical take-off and landing (VTOL) aircraft;
• sending, to the client device, itinerary data for servicing the transport request, the itinerary data identifying a leg serviced by the VTOL aircraft;
• receiving confirmation data indicating that the rider has boarded the VTOL aircraft;
• accessing historical demand data indicating a variation in demand over time and that includes an expected number of riders in a given time period;
• determining, based on a comparison between the historical demand data and a current time and day, that the VTOL aircraft should wait for additional riders, wherein determining that the VTOL aircraft should wait for additional riders comprises:
• calculating, using a machine-learning model trained with the historical demand data by a minimizing a loss function retrained over time with data corresponding to actual transport requests serviced, a value indicative of a probability that an additional rider will board the VTOL aircraft within a specified time, and
• determining that the VTOL aircraft should wait if the probability exceeds a threshold;
• and
• after the VTOL aircraft waits in response to the probability exceeding the threshold, sending an instruction over the network to the VTOL aircraft to take-off responsive to one or more conditions being met.