Ekstraksi aturan Decision Tree berbasis information gain untuk mendekati klasifikasi risiko cuaca penerbangan berbasis skor SMB II Palembang

Hesti Annisa Jannah; Afina Meutya Putri; Rendra Gustriansyah

doi:10.35760/tr.2026.v31i2.413

Authors

Hesti Annisa Jannah Universitas Indo Global Mandiri Author
Afina Meutya Putri Universitas Indo Global Mandiri Author
Rendra Gustriansyah Universitas Indo Global Mandiri Author

DOI:

https://doi.org/10.35760/tr.2026.v31i2.413

Keywords:

BMKG, SMOTE, aviation weather risk classification, Decision Tree, information gain

Abstract

Aviation safety is a concern in global air transportation, where adverse weather conditions, including heavy rainfall, high humidity, and strong winds, can disrupt flight operations and threaten passenger and crew safety. Sultan Mahmud Badaruddin II (SMB II) Airport in Palembang, South Sumatra, operates within a tropical climate marked by extreme humidity and frequent heavy rainfall. This study applies the interpretable Decision Tree algorithm using an information gain criterion to reproduce a multivariable weighted-scoring classification of same-day aviation weather risk and generate transparent, auditable decision rules. The study uses meteorological data from the Indonesian Meteorological, Climatological, and Geophysical Agency (BMKG), covering May 2025 to May 2026, comprising 371 daily records with five attributes: average temperature (Tāvg), relative humidity (RH_avg), rainfall (RR), wind direction (DDD_X), and wind speed (FF_avg). Risk labels were derived from a weighted-scoring system grounded in BMKG thresholds and references from the Civil Aviation Safety Regulation (CASR) and International Civil Aviation Organization (ICAO), yielding three classes: Safe (40.7%), Caution (39.1%), and Dangerous (20.2%). Data were split 80:20 with stratified sampling. The Synthetic Minority Over-sampling Technique (SMOTE) was applied to balance the training data. The model achieved 91.89% accuracy on the test set, with perfect recall on the Dangerous class (recall = 1.00, F1-score = 0.94). Because four of the five attributes are also used to construct the scoring labels, this accuracy primarily reflects the Decision Tree model's ability to reproduce the scoring structure rather than independently validating against actual operational risk.

Downloads

Download data is not yet available.

Author Biographies

Hesti Annisa Jannah, Universitas Indo Global Mandiri

Department of Informatics Engineering
Afina Meutya Putri, Universitas Indo Global Mandiri

Department of Informatics Engineering
Rendra Gustriansyah, Universitas Indo Global Mandiri

Department of Informatics Engineering

References

[1] R. Olaganathan and R. G. Ham, “Significance of incorporating weather technology training for GA pilots to curb fatalities,” Int. J. Aviat. Aeronaut. Aerosp., vol. 7, no. 2, Art. no. 13, 2020, doi: 10.58940/2374-6793.1478.

[2] A. Saadah and M. N. Cahyadi, “Identification of cumulonimbus clouds as a trigger for extreme weather at Soekarno-Hatta International Airport on July 24, 2023 based on weather radar, LIDAR, and PWV estimates of the ECMWF-ERA5 numerical model,” J. Penelit. Pendidik. IPA, vol. 11, no. 9, pp. 395–406, 2025, doi: 10.29303/jppipa.v11i9.12604.

[3] A. R. Ramadhan, D. D. Kurniawan, and T. Sutabri, “Penerapan machine learning dalam pelayanan UPT BMKG Palembang di Bandara SMBII Palembang,” J. Sistim Inf. dan Teknol., vol. 5, no. 2, pp. 203–207, 2023, doi: 10.60083/jsisfotek.v5i2.255.

[4] A. Kurniawan and R. Z. A. Aziz, “Prediksi kabut bandar udara di Indonesia menggunakan neural network dan radom forest,” Build. Informatics, Technol. Sci., vol. 6, no. 2, pp. 746–757, 2024, doi: 10.47065/bits.v6i2.5544.

[5] A. Khairunnisa, K. A. Notodiputro, and B. Sartono, “A comparative study of Random Forest and Double Random Forest models from view points of their interpretability,” Sci. J. Informatics, vol. 11, no. 1, pp. 207–218, 2024, doi: 10.15294/sji.v11i1.48721.

[6] S. A. S. S., S. Surono, and A. Thobirin, “Evaluation of hybrid KNN-Naïve Bayes model using cross validation for weather prediction,” JST (Jurnal Sains Dan Teknologi), vol. 14, no. 3, pp. 555–565, 2025, doi: 10.23887/jst-undiksha.v14i3.91956.

[7] A. M. Siregar, S. Faisal, Y. Cahyana, and B. Priyatna, “Perbandingan algoritme klasifikasi untuk prediksi cuaca,” J. Account. Inf. Syst., vol. 3, no. 1, pp. 15–24, 2020, doi: 10.32627/aims.v3i1.280.

[8] A. Prasetiyo, “Pemanfaatan algoritma Decision Tree C4.5 dalam memprakirakan hujan di Stasiun Meteorologi Kelas I Sultan Hasanuddin,” Bul. GAW Bariri, vol. 5, no. 1, pp. 47–55, 2024, doi: 10.31172/bgb.v5i1.120.

[9] A. N. Najah, A. N. Amalina, and R. Hidayat, “Penerapan algoritma Decision Tree C4.5 untuk prediksi cuaca di Kota Semarang,” Indexia, vol. 7, no. 1, pp. 46–52, 2025, doi: 10.30587/indexia.v7i1.9344.

[10] S. Kim and E. Park, “Prediction of flight departure delays caused by weather conditions adopting data-driven approaches,” J. Big Data, vol. 11, no. 1, Art. no. 11, 2024, doi: 10.1186/s40537-023-00867-5.

[11] Badan Meteorologi, Klimatologi, dan Geofisika, “Data Online,” Direktorat Data dan Komputasi BMKG. [Online]. Available: https://dataonline.bmkg.go.id/dataonline-home (Accessed May 15, 2026).

[12] Badan Meteorologi, Klimatologi, dan Geofisika, Stasiun Meteorologi H. Asan Kotawaringin Timur, “Buletin Meteorologi: Edisi Juli 2025,” Sampit, Indonesia, Jul. 2025.

[13] Kementerian Perhubungan Republik Indonesia, “Peraturan Menteri Perhubungan Nomor PM 80 Tahun 2011 tentang Perubahan Ketiga atas Keputusan Menteri Perhubungan Nomor KM 41 Tahun 2001 tentang Peraturan Umum Pengoperasian Pesawat Udara (General Operating and Flight Rules),” Jakarta, Indonesia, 2011.

[14] International Civil Aviation Organization, Annex 3 to the Convention on International Civil Aviation: Meteorological Service for International Air Navigation, 20th ed., ICAO, 2018.

[15] International Civil Aviation Organization, Safety Management Manual (SMM), Doc 9859, 4th ed., ICAO, 2018.

[16] W. Chen, K. Yang, Z. Yu, Y. Shi, and C. L. P. Chen, “A survey on imbalanced learning: Latest research, applications and future directions,” Artif. Intell. Rev., vol. 57, Art. no. 137, 2024, doi: 10.1007/s10462-024-10759-6.

[17] N. V. Chawla, K. W. Bowyer, L. O. Hall, and W. P. Kegelmeyer, “SMOTE: Synthetic minority over-sampling technique,” J. Artif. Intell. Res., vol. 16, pp. 321–357, 2002, doi: 10.1613/jair.953.

[18] J. R. Quinlan, C4.5: Programs for Machine Learning. San Mateo, CA, USA: Morgan Kaufmann, 1993, doi: 10.1016/C2009-0-27846-9.

[19] S. S. Mullick, S. Datta, S. G. Dhekane, and S. Das, “Appropriateness of performance indices for imbalanced data classification: An analysis,” Pattern Recognit., vol. 102, Art. no. 107197, 2020, doi: 10.1016/j.patcog.2020.107197.

[20] M. Romadoni and H. Akhsan, “Karakteristik iklim di Kota Palembang serta implikasinya terhadap bencana kabut asap,” JIPFRI (Jurnal Inov. Pendidik. Fis. dan Ris. Ilmiah), vol. 6, no. 2, pp. 60–66, 2022, doi: 10.30599/jipfri.v6i2.1541.

[21] W. Mardiansyah, D. Setiabudidaya, M. Y. N. Khakim, I. Yustian, Z. Dahlan, and I. Iskandar, “On the influence of ENSO and IOD on rainfall variability over the Musi Basin, South Sumatra,” Science and Technology Indonesia, vol. 3, no. 4, pp. 157–163, 2018, doi: 10.26554/sti.2018.3.4.157-163.

[22] R. Muharomah and B. I. Setiawan, “Identification of climate trends and patterns in South Sumatra,” Agromet, vol. 36, no. 2, pp. 79–87, 2022, doi: 10.29244/j.agromet.36.2.79-87.

[23] Stasiun Klimatologi Sumatera Selatan, Badan Meteorologi, Klimatologi, dan Geofisika, “Prediksi musim hujan tahun 2025/2026,” Sep. 19, 2025. [Online]. Available: https://staklim-sumsel.bmkg.go.id/prediksi-musim-hujan-tahun-2025-2026/. (Accessed: May 23, 2026).

[24] Stasiun Klimatologi Sumatera Selatan, Badan Meteorologi, Klimatologi, dan Geofisika, “Distribusi curah hujan bulan Desember tahun 2025,” Jan. 5, 2026. [Online]. Available: https://staklim-sumsel.bmkg.go.id/distribusi-curah-hujan-bulan-desember-tahun-2025/. (Accessed: May 23, 2026).

[25] M. A. Rahman, M. N. Y. Ali, F. T. Johora, A. A. Khan, and M. N. Huda, “Securing aviation networks: A generalized and robust machine learning solution for monitoring abnormalities in commercial aircraft,” Results Eng., vol. 29, Art. no. 108884, 2025, doi: 10.1016/j.rineng.2025.108884.

[26] K. J. Ruskin and A. C. Ruskin, “Validation of a new method for designing air traffic control alarms,” Transp. Res. Interdiscip. Perspect., vol. 22, Art. no. 100965, 2023, doi: 10.1016/j.trip.2023.100965.

[27] C. D. Wickens and A. Colcombe, “Dual-task performance consequences of imperfect alerting associated with a cockpit display of traffic information,” Hum. Factors, vol. 49, no. 5, pp. 839–850, 2007, doi: 10.1518/001872007X230217.