Comparison Airport Traffic Prediction Performance Using BiGRU and CNN-BiGRU Models

Willy Riyadi; Jasmir; Xaverius Sika

doi:10.15575/join.v10i1.1362

Authors

Willy Riyadi Department of Computer Engineering, Universitas Dinamika Bangsa Jambi, Indonesia
Jasmir Department of Computer Engineering, Universitas Dinamika Bangsa Jambi, Indonesia
Xaverius Sika Department of Information Systems, Universitas Dinamika Bangsa Jambi, Indonesia

DOI:

https://doi.org/10.15575/join.v10i1.1362

Keywords:

Accuracy Prediction, Airport Traffic, BiGRU, CNN-BiGRU, COVID-19

Abstract

COVID-19 pandemic has significantly disrupted the aviation industry, highlighting the critical need for accurate airport traffic predictions. This study compares the performance of BiGRU and CNN-BiGRU models to enhance airport traffic forecasting accuracy models from March to December 2020. Data preprocessing was performed using Python's Pandas library. This involved filtering, scaling using min-max normalization, and splitting the data into 80:20 training-testing split using Python's Pandas library. Various optimization techniques—RMSProp, Adam, Nadam, Adamax, AdamW, and Lion—were applied, along with ReduceLROnPlateau, to optimize model performance. The models were evaluated using Mean Absolute Percentage Error (MAPE), Mean Absolute Error (MAE), and Mean Squared Error (MSE). The best predictive performance was observed in the United States using the CNN-BiGRU model with the Adam optimizer, achieving the lowest MAE of 0.0580, MSE of 0.0097, and MAPE of 0.0979. The use of a balanced dataset, representing each airport's traffic as a percentage of a baseline period, significantly improved prediction accuracy. This research provides valuable insights for stakeholders seeking effective airport traffic prediction methods during unprecedented times.

References

[1] Z. Yang, Y. Wang, J. Li, L. Liu, J. Ma, and Y. Zhong, “Airport Arrival Flow Prediction considering Meteorological Factors Based on Deep-Learning Methods,” Complexity, vol. 2020, p. 6309272, 2020, doi: 10.1155/2020/6309272.

[2] S. V Gudmundsson, M. Cattaneo, and R. Redondi, “Forecasting temporal world recovery in air transport markets in the presence of large economic shocks: The case of COVID-19,” J Air Transp Manag, vol. 91, p. 102007, 2021, doi: https://doi.org/10.1016/j.jairtraman.2020.102007.

[3] X. Zhang, H. Liu, Y. Zhao, and X. Zhang, “Multifractal detrended fluctuation analysis on air traffic flow time series: A single airport case,” Physica A: Statistical Mechanics and its Applications, vol. 531, p. 121790, 2019, doi: https://doi.org/10.1016/j.physa.2019.121790.

[4] H. Liu, X. Zhang, and X. Zhang, “Multiscale multifractal analysis on air traffic flow time series: A single airport departure flight case,” Physica A: Statistical Mechanics and its Applications, vol. 545, p. 123585, 2020, doi: https://doi.org/10.1016/j.physa.2019.123585.

[5] D. C. Tascón and O. Díaz Olariaga, “Air traffic forecast and its impact on runway capacity. A System Dynamics approach,” J Air Transp Manag, vol. 90, p. 101946, 2021, doi: https://doi.org/10.1016/j.jairtraman.2020.101946.

[6] P. B. Weerakody, K. W. Wong, G. Wang, and W. Ela, “A review of irregular time series data handling with gated recurrent neural networks,” Neurocomputing, vol. 441, pp. 161–178, 2021, doi: https://doi.org/10.1016/j.neucom.2021.02.046.

[7] R. Tang, Z. Yang, J. Lu, H. Liu, and H. Zhang, “Real-time Trajectory Prediction of Unmanned Aircraft Vehicles Based on Gated Recurrent Unit,” 2022, pp. 585–596. doi: 10.1007/978-981-16-5429-9_45.

[8] X. Li, X. Ma, F. Xiao, C. Xiao, F. Wang, and S. Zhang, “Time-series production forecasting method based on the integration of Bidirectional Gated Recurrent Unit (Bi-GRU) network and Sparrow Search Algorithm (SSA),” J Pet Sci Eng, vol. 208, p. 109309, Jan. 2022, doi: 10.1016/j.petrol.2021.109309.

[9] J. Huang and W. Ding, “Aircraft Trajectory Prediction Based on Bayesian Optimised Temporal Convolutional Network–Bidirectional Gated Recurrent Unit Hybrid Neural Network,” International Journal of Aerospace Engineering, vol. 2022, pp. 1–19, Dec. 2022, doi: 10.1155/2022/2086904.

[10] S. Liu, W. Lin, Y. Wang, D. Z. Yu, Y. Peng, and X. Ma, “Convolutional Neural Network-Based Bidirectional Gated Recurrent Unit–Additive Attention Mechanism Hybrid Deep Neural Networks for Short-Term Traffic Flow Prediction,” Sustainability, vol. 16, no. 5, p. 1986, Feb. 2024, doi: 10.3390/su16051986.

[11] D. Zhou, X. Zhuang, J. Cai, H. Zuo, X. Zhao, and J. Xiang, “An ensemble model using temporal convolution and dual attention gated recurrent unit to analyze risk of civil aircraft,” Expert Syst Appl, vol. 236, p. 121423, Feb. 2024, doi: 10.1016/j.eswa.2023.121423.

[12] F. Meng, T. Song, D. Xu, P. Xie, and Y. Li, “Forecasting tropical cyclones wave height using bidirectional gated recurrent unit,” Ocean Engineering, vol. 234, p. 108795, Aug. 2021, doi: 10.1016/j.oceaneng.2021.108795.

[13] Q. Yuan, J. Wang, M. Zheng, and X. Wang, “Hybrid 1D-CNN and attention-based Bi-GRU neural networks for predicting moisture content of sand gravel using NIR spectroscopy,” Constr Build Mater, vol. 350, p. 128799, Oct. 2022, doi: 10.1016/j.conbuildmat.2022.128799.

[14] N. Zhao, H. Gao, X. Wen, and H. Li, “Combination of Convolutional Neural Network and Gated Recurrent Unit for Aspect-Based Sentiment Analysis,” IEEE Access, vol. 9, pp. 15561–15569, 2021, doi: 10.1109/ACCESS.2021.3052937.

[15] L. Zeng, W. Ren, and L. Shan, “Attention-based bidirectional gated recurrent unit neural networks for well logs prediction and lithology identification,” Neurocomputing, vol. 414, pp. 153–171, Nov. 2020, doi: 10.1016/j.neucom.2020.07.026.

[16] P. Li et al., “Bidirectional Gated Recurrent Unit Neural Network for Chinese Address Element Segmentation,” ISPRS Int J Geoinf, vol. 9, no. 11, p. 635, Oct. 2020, doi: 10.3390/ijgi9110635.

[17] T. Shin, “COVID-19’s Impact on Airport Traffic,” kaggle. Accessed: Jan. 10, 2023. [Online]. Available: https://www.kaggle.com/datasets/terenceshin/covid19s-impact-on-airport-traffic

[18] I. M. Pires, F. Hussain, N. M. M. Garcia, P. Lameski, and E. Zdravevski, “Homogeneous Data Normalization and Deep Learning: A Case Study in Human Activity Classification,” Future Internet, vol. 12, no. 11, p. 194, Nov. 2020, doi: 10.3390/fi12110194.

[19] Z. Zhang et al., “An Improved Bidirectional Gated Recurrent Unit Method for Accurate State-of-Charge Estimation,” IEEE Access, vol. 9, pp. 11252–11263, 2021, doi: 10.1109/ACCESS.2021.3049944.

[20] W. Choi, M.-J. Kim, M.-S. Yum, and D.-H. Jeong, “Deep Convolutional Gated Recurrent Unit Combined with Attention Mechanism to Classify Pre-Ictal from Interictal EEG with Minimized Number of Channels,” J Pers Med, vol. 12, no. 5, p. 763, May 2022, doi: 10.3390/jpm12050763.