MACHINE LEARNING APPLIED IN THE EVALUATION OF AIRPORT PROJECTS¶
Abstract¶
Brazil is a country with continental dimensions, with air transport as a strategic vector in economic development. Due to a favorable combination of factors, such as: territorial dimension, high geographic and social mobility, among others, Brazil has become one of the emerging countries with high potential for the development of air transport. With regard to the development of an airport project in Brazil, a series of normative prerequisites guide designers during development. Among the documents, we can highlight: i) RBAC (Brazilian Civil Aviation Regulation), ii) Airport Projects Manual, iii) Annex 14, iv) Airport Planning Criteria and Conditions Manual, among others. Considering the high amount of normative documents to be considered in the development phase of an airport project, it is necessary that the team of project analysts have the expertise to carry out the evaluation of these projects. In the current situation, the evaluation and approval process tends to take months and, in some cases, even years, until the final approval of the project. This article presents partial results of a doctoral research in progress that uses Machine Learning techniques in the evaluation phase of airport projects from data contained in digital airport models based on Building Information Modeling (BIM). The preliminary results of this research demonstrate the use of three supervised learning algorithms achieving a prediction accuracy above 90%.
Download¶
Citing¶
@inproceedings{SIT214,
author = {ÍTALO GUEDES DOS SANTOS; MAX LIRA VERAS XAVIER ANDRADE; CLEBER ZANCHETTIN},
title = {MACHINE LEARNING APPLIED IN THE EVALUATION OF AIRPORT PROJECTS},
booktitle = {Proceedings of the 2022 Air Transportation Symposium},
series = {SITRAER 2022},
year = {2022},
pages = {586-595},
publisher = {SBTA - Brazilian Air Transportation Research Society},
address = {São José dos Campos, Brazil,}
}
License¶
The contents of this article can be used given that the authors are cited. The reproduction of the whole article in any medium is forbidden, unless authorized by the authors.