Indonesia is the largest archipelagic country in the world, with seventeen thousand islands stretching more than five thousand kilometers from east to west. Thanks to these unique geographical conditions, the potential for the aviation industry is growing to take advantage of the progress of various sectors. Therefore, Indonesia’s air transportation has a strategic role in supporting national and international connectivity and is the main driver of the Indonesian economy. History records those dozens of national airlines operate in Indonesia in line with the growth in mobility and public demand. Then, as is well-known, aviation activities in Indonesia during the COVID-19 pandemic experienced fluctuating developments and even a significant decline. Therefore, in the post-COVID-19 pandemic period, the government aims to focus on recovery efforts and the normalization of aviation activities. Hence, the purpose of this research is to determine when the number of aviation movements can reach the baseline. The mentioned baseline represents the number of aviation movements before the COVID-19 pandemic in Indonesia (January 2020). Consequently, to provide an overview of future aviation activities, the number of aviation movements is projected using the Multilayer Perceptron (MLP) method. This is secondary data by Airnav Indonesia on the number of daily flight movements in Indonesia from January 2020 to December 2022. Forecasting is carried out for the next two years, from January 2023 to December 2024. According to the MLP method, the model has excellent forecasting performance and has a MAPE value of less than 10% on domestic and international flight movements, domestic flight movements based on city pairs, and international flight movements based on city pairs. Whereas for international flights, the MAPE value of 10.24% indicates a good forecasting performance.

1.
Sugiarti
,
JMM
12
(
1
),
113
122
(
2021
).
2.
N. A.
Hamid
,
N. M.
Nawi
,
R.
Ghazali
, and
M. N. M.
Salleh
, “
Accelerating Learning Performance of Back Propagation Algorithm by Using Adaptive Gain Together with Adaptive Momentum and Adaptive Learning Rate on Classification Problems
” in
Communications in Computer and Information Science
(
Springer
,
Heidelberg
,
2011
).
3.
I.
Goodfellow
,
Y.
Bengio
, and
A.
Courville
,
Deep Learning.
2016
.
4.
A.
Buono
,
A.
Faqih
, and
A. B.
Hermanianto
, “
Optimasi Multi-Layer Perceptron Pada Model Prediksi Karakteristik Musim Hujan Dan Kemarau Di Kabupaten Pacitan
” Master Thesis,
Bogor Agricultural University (IPB
),
2017
.
5.
P.
Young-Seuk
and
L.
Sovan
, “
Artificial Neural Networks: Multilayer Perceptron for Ecological Modeling
” in
Developments in Environmental Modelling.
28
,
123
140
(
2016
).
6.
T.
Marwala
,
Multi-layer Perceptron. Handb. Mach. Learn.
,
2018
.
7.
H.
Alla
,
L.
Moumoun
, and
Y.
Balouk
,
Sci. Program
2021
,
1-12
, (2021). .
8.
N.
Kourentzes
,
D. K.
Barrow
, and
C. F.
Sven
,
Expert Syst. Appl.
4235
4244
(
2014
).
9.
J. J. M.
Moreno
,
A. P.
Pol
,
A. S.
Abad
, and
B. C.
Blasco
,
Psicothema
25
,
500
506
(
2013
).
This content is only available via PDF.
You do not currently have access to this content.