Airport planning depends to a large extent on the levels of activity that are anticipated. In order to plan facilities and infrastructures of an airport system and to be able to satisfy future needs, it is essential to predict the level and distribution of demand. This document presents a short- and medium-term forecast of the demand for air passengers carried out through a specific case study (Colombia), in which the impact of the pandemic period due to COVID-19 on air traffic was taken into account. To make the forecast, an algorithm that implements techniques based on Artificial Neural Networks (ANN) and Machine Learning (ML) was developed. In particular, for the analysis of the available time series, techniques of encoder-decoder networks of the type ConvLSTM2D have been applied. These architectures are a hybrid between Convolutional Neural Networks (CNN), very useful for the extraction of invariant patterns in their spatial position, and Recurrent Neural Networks (RNN), appropriate for the extraction of patterns within their temporal context (time series). The most relevant result of the present research is that the recovery in demand (volume and trend) to the levels reported before the pandemic is forecast for the period between the end of 2022 and the beginning of 2024 (depending on the type of traffic and scenario considered). Finally, the application of the forecasting model based on ML/Deep Learning (DL) presents, as a metric performance, a Mean Absolute Percentage Error (MAPE) values from 3% to 9% (depending on the scenario), which enables predictions of relative precision and introduces a new alternative technical approach to develop reliable air traffic forecasts, at least in the short and medium term.



To view the content in your browser, please download Adobe Reader or, alternately,
you may Download the file to your hard drive.

NOTE: The latest versions of Adobe Reader do not support viewing PDF files within Firefox on Mac OS and if you are using a modern (Intel) Mac, there is no official plugin for viewing PDF files within the browser window.