Abstract: An aircraft landing event system is disclosed including a processor, the processor being configured to receive aircraft braking performance information from a plurality of aircraft that have performed a landing event on a particular runway. The processor is configured to determine an aircraft braking performance indicator on the basis of the aircraft braking performance information of the plurality of aircraft, and communicate the aircraft braking performance indicator to an aircraft landing system of an approaching aircraft that is about to perform a landing event on the particular runway.

Abstract: An aircraft landing event system including a processor communicatively coupled with memory storing aircraft landing event data. The processor is configured to receive environment information representative of an environmental condition of a runway approached by an aircraft and receive retardation information representative of a retardation demand of the aircraft during an anticipated landing event of the aircraft on the runway. The processor is further configured to select aircraft landing event data from the memory based on the environment information and the retardation information and determine a performance indicator for the landing event based on the aircraft landing event data selected by the processor. The processor is further configured to communicate the performance indicator to a landing system of the aircraft.

Abstract: A method of training a neural network to control an aircraft system. The method includes obtaining an operational mode data space representing a set of operational modes for the aircraft system, wherein each operational mode represents a configuration of the aircraft system where performance of an aircraft component is impaired according to an aircraft system model. Each operational mode includes probability data indicating a respective probability of the operational mode occurring, according to the model. The method includes generating a reduced operational mode data space including operational modes having a probability greater than a theoretical operational probability threshold, and generating a training operational mode data space including operational modes within the reduced operational mode data space that have a probability less than a real-world operational probability threshold. The method includes training the neural network using operational modes within the training operational mode data space.