How Scientists Can Better Predict Flight Delays
Good news for anyone who has let out a sigh of exasperation waiting for a delayed flight.
Air travelers are familiar with the sting of frustration after arriving at an airport and seeing their flight listed as “delayed” on the departures board.
Researchers at Binghamton University claim they have invented a new computer model that can more accurately predict flight delays than any system currently in use, allowing airlines to give information on delays more quickly and accurately.
The system works to improve upon the artificial neural network currently used to predict delays, according to research published in Procedia Computer Science. By adding multiple levels of input factors, including qualitative elements such as weather, the model can more easily predict the outcome of flight delays, according to researchers.
“Airlines can use the proposed method to provide more accurate delay information to the customers, and hence gain customer loyalty,” said Sina Khanmohammadi, lead author of the study, in a statement from Binghamton. “Air traffic controllers at a busy airport can also use this information as a supplement to improve the management the airport traffic.”
Binghamton’s model predicted flight delays with 20 percent more accuracy in 40 percent less time than the existing model, according to the researchers.