Perbandingan Gated Recurrent Unit dan Time Series Transformer untuk Prediksi Kabut Menggunakan Sliding Window
-
Chandra Dwi Pratomo
*
Universitas Pamulang, Tangerang Selatan,
Indonesia
- Agung Budi Susanto Universitas Pamulang, Tangerang Selatan, Indonesia
- Arya Adhyaksa Waskita Universitas Pamulang, Tangerang Selatan, Indonesia (*) Corresponding Author
Abstract
Fog is one of the most hazardous weather phenomena for aviation operations. Dense fog can reduce visibility to below 1,000 meters, potentially causing flight delays, cancellations, and even aviation incidents. To date, fog prediction, particularly at Budiarto Airport, still relies on manual analysis by weather forecasters, making it prone to subjectivity and delays in information delivery. This study proposes and compares two deep learning architectures: the Gated Recurrent Unit (GRU) as an efficient recurrent model, and Time Series Transformer (TST) based on self-attention as a state-of-the-art model for METAR (Meteorological Aerodrome Report) data-based fog event prediction. The METAR data is initially processed using a sliding window technique before becoming a ready-to-use dataset. The dataset comprises 153,838 METAR records from the Budiarto–Curug Meteorological Station spanning from September 2015 to February 2026, which were processed through a METAR code parsing pipeline, BMKG rule-based median imputation, Min-Max normalization, and the construction of a 9-1 sliding window dataset. Experimental results on the test data demonstrate that TST 9-1 delivers the best performance with a Root Mean Squared Error (RMSE) of 0.452427 and a three class classification accuracy (No Fog, Light Fog, Dense Fog) of 88.21%, significantly outperforming GRU 9-1, which achieved an RMSE of 0.883981 and an accuracy of 72.97%. The main novelty of this research lies in the comparative study of GRU and TST architectures for METAR based fog prediction at airports, combined with a sliding window technique and the conversion of visibility regression into a multi class classification of fog events. This research contributes a fog prediction modeling framework capable of processing time-series data sequentially and more effectively, which can serve as a foundation for the development of an accurate, automated early warning system for fog events in airport environments.
Downloads
References
Alwi Aliu, M., & Fitrianto, A. (2023). Pemodelan Regresi Logistik Ordinal Backward dengan Imputasi K-Nearest Neighbour pada Indeks Pembangunan Manusia di Indonesia Tahun 2021. Jurnal Statistika Dan Aplikasinya, 7(1).
Antaranews. (2022). Akibat kabut, tujuh penerbangan di Pekanbaru terganggu. Https://Www.Antaranews.Com/Berita/3112713/Akibat-Kabut-Tujuh-Penerbangan-Di-Pekanbaru-Terganggu.
BMKG. (2024). Peraturan Badan Meteorologi, Klimatologi, Dan Geofisika Republik Indonesia, Nomor 6 Tahun 2024 Tentang Penyediaan Dan Penyebaran Aerodrome Forecast.
BMKG. (2025). Kep 26 KB I 2025 Tentang Stasiun Meteorologi Penanggung Jawab Penyediaan Dan Penyebaran Metar.
Chen, Q. (2025). Comparing Different Transformer Model Structures for Stock Prediction. http://arxiv.org/abs/2504.16361
D. F. Laksana. (2021). Rancangan Aplikasi E-Sched Untuk Personel Penerbangan Sebagai Upaya Pemerataan Traffic Di Bandar Udara Budiarto Curug. Politeknik Penerbangan Surabaya.
Dewita, A., & Alfiandy, S. (2024). Kajian Awal : Prediksi Kabut Berdasarkan Data Observasi di Wilayah Bandara Zainuddin Abdul Madjid. Buletin GAW Bariri, 5(2), 60–69. https://doi.org/10.31172/bgb.v5i2.135
El-Saieed, A. M. (2025). An Adaptive Transformer Model for Long-Term Time-Series Forecasting of Temperature and Radiation in Photovoltaic Energy Generation. Applied Computational Intelligence and Soft Computing, 2025(1). https://doi.org/10.1155/acis/6671565
Hue Dinh Thi Hong. (2021). Fog Prediction Using Deep Learning Models. Texas A&M University.
Imam Sonhaji. (2022). Peran Politeknik Penerbangan Iindonesa (PPI) Curug Pada Pengembangan Aerowisata Provinsi Banten. Jurnal Manajemen Dirgantara Vol.15, No.1, Juli 2022. https://doi.org/10.56521/manajemen-dirgantara.v15i1.574
Kişmiroğlu, C., & Isik, O. (2025). Temperature Prediction Using Transformer–LSTM Deep Learning Models and Sarimax from a Signal Processing Perspective. Applied Sciences (Switzerland), 15(17). https://doi.org/10.3390/app15179372
Kurniawan, A., & Abdul Aziz, R. (2024). Prediksi Kabut Bandar Udara di Indonesia Menggunakan Neural Network dan Radom Forest. Building of Informatics, Technology and Science (BITS), 6(2), 746–757. https://doi.org/10.47065/bits.v6i2.5544
Liu, G. (2024). Predicting Winter Fog over Complex Terrain using Machine Learning. University of Utah.
Shankar, A., Kumar, A., & Sinha, V. (2024). Machine Learning Approach in the Prediction of Fog: An Early Warning System. Mausam, 75(4), 1039–1050. https://doi.org/10.54302/mausam.v75i4.5919
Sharma, S., Bajaj, K., Deshpande, P., Bhattacharya, A., & Tripathi, S. (2024). Short-Term Fog Forecasting using Meteorological Observations at Airports in North India. https://mesonet.agron.iastate.edu/
Wikipedia. (2025, February 4). Musibah Bandar Udara Tenerife. Https://Id.Wikipedia.Org/Wiki/Musibah_bandar_udara_Tenerife. https://id.wikipedia.org/wiki/Musibah_bandar_udara_Tenerife
Wiujianna, A., Setio Pribadi, F., Djuniadi, D., & Sunarno, S. (2025). Komputika: Jurnal Sistem Komputer Prediksi Kabut Menggunakan RNN dan LSTM dengan Attention Mechanism di Bandara Ruteng. 14(1), 87–93. https://doi.org/10.34010/8e86yg15
WMO. (1992). World Meteorological Organization International Meteorological Vocabulary.
Wonda, D., & Pratama, I. (2023). Implementasi Data Mining Menggunakan Neural Network Untuk Prediksi Penjualan (Studi Kasus: Burjo Burneo Seturan Raya).
Zhou, H., Zhang, S., Peng, J., Zhang, S., Li, J., Xiong, H., & Zhang, W. (2021). Informer: Beyond Efficient Transformer for Long Sequence Time-Series Forecasting. http://arxiv.org/abs/2012.07436
Bila bermanfaat silahkan share artikel ini
Berikan Komentar Anda terhadap artikel Perbandingan Gated Recurrent Unit dan Time Series Transformer untuk Prediksi Kabut Menggunakan Sliding Window
Pages: 1158-1167
Copyright (c) 2026 Chandra Dwi Pratomo, Agung Budi Susanto, Arya Adhyaksa Waskita
This work is licensed under a Creative Commons Attribution 4.0 International License.
Authors who publish with this journal agree to the following terms:
- Authors retain copyright and grant the journal right of first publication with the work simultaneously licensed under Creative Commons Attribution 4.0 International License that allows others to share the work with an acknowledgment of the work's authorship and initial publication in this journal.
- Authors are able to enter into separate, additional contractual arrangements for the non-exclusive distribution of the journal's published version of the work (e.g., post it to an institutional repository or publish it in a book), with an acknowledgment of its initial publication in this journal.
- Authors are permitted and encouraged to post their work online (e.g., in institutional repositories or on their website) prior to and during the submission process, as it can lead to productive exchanges, as well as earlier and greater citation of published work (Refer to The Effect of Open Access).
