Sina Khanmohammadi, a PhD candidate in systems science, leads a Binghamton University study that has developed a more accurate way of predicting airline flight delays. (Jonathan Cohen)

Researchers at Binghamton University have devised a new computer model that can more accurately predict delays faster than anything currently in use. The multilevel input layer artificial neural network handles categorical variables with a simple structure to help airlines easily see the relationships between input variables (such as weather) and outputs (flight delays).

Air traffic controllers at a busy airport can also use this information as a supplement to improve the management the of airport traffic. The team plans to continue to explore variables that could be applied to the new model. The group also wants to apply the work beyond flight scheduling and use fuzzy logic — computing based on degrees of truth rather than the usual true/false dichotomy — to expand to more real-world applications.