A Categorical Model for Airport Capacity Estimation Using Hierarchical Clustering

Motivated by the need for very inexpensive, easily updated, first-order-accurate estimates of airport capacity required in system-wide analyses, we propose a novel approach to generate a predictive categorical model. The underlying hypothesis tested in this work is that for the same weather conditions airports with a similar runway configuration and fleet mix will have similar capacities. Accordingly, if airport categories with known capacity are defined a-priori on the basis of similarity in fleet mix and runway configuration, then a membership function to the set of categories essentially constitutes a predictive model. We test this hypothesis by formulating and implementing such a model in order to examine its feasibility and discuss key practical considerations. Verification demonstrates model fit error within 4% with a categorical ∗Corresponding Author: Gokcin Cinar, Graduate Researcher, School of Aerospace Engineering, Georgia Institute of Technology, Atlanta, GA 30332, USA. E-mail: gokcin.cinar@gatech.edu †Research Engineer, School of Aerospace Engineering, Georgia Institute of Technology. ‡S.P. Langley Distinguished Regents Professor and Director of Aerospace Systems Design Laboratory, School of Aerospace Engineering, Georgia Institute of Technology.