When you see one airline cancel all their flight in anticipation of a storm and another one wait it out, you are seeing airlines take different gambles based on estimates about how the weather will affect their flights.
From the article on it, “Currently, flight delays are predicted by artificial neural network (ANN) computer models that are backfilled with delay data from previous flights.”
What this means is, the ANN looks at delay data from previous flights and tries to find patterns moving forward. So it’s backwards looking to try to predict the future.
The new method takes inputs, such as weather, day of the week, origin, or security alerts, and creates more clear relationships between then and the patterns.
The research won’t eliminate delays, but it will help airlines inform travelers quicker and more accurately about problems. The new model could also help smaller regional airports become more efficient and able to handle more flights per day.
“Airlines can use the proposed method to provide more accurate delay information to the customers, and hence gain customer loyalty,” said Khanmohammadi. “Air traffic controllers at a busy airport can also use this information as a supplement to improve the management the airport traffic.”
According to the article, this method was 20% more accurate and 40% faster.
Unfortunately, this is all academic at this point. But it has the potential to save airlines money and customer frustration. So if it is better, I bet it’ll eventually be incorporated. (Though who knows how quickly!)