Sistem Prediksi Waktu Keberangkatan Pesawat Berbasis Machine Learning
Abstract
Keterlambatan keberangkatan (departure delay) merupakan tantangan operasional utama di Bandara Pattimura Ambon yang berdampak signifikan pada efisiensi maskapai dan kepuasan penumpang. Penelitian ini bertujuan membangun sistem prediksi waktu keberangkatan pesawat menggunakan algoritma Machine Learning, yaitu Random Forest dan Support Vector Machine (SVM), dengan memanfaatkan data operasional penerbangan dan data cuaca. Dataset terdiri dari 4.901 data keberangkatan tahun 2024 yang diperoleh dari AirNav dan BMKG. Penelitian ini menerapkan tahapan pra-pemrosesan yang ketat, termasuk penghapusan variabel bocoran (data leakage) seperti waktu aktual keberangkatan (ATD), serta penanganan ketidakseimbangan kelas menggunakan teknik SMOTE. Hasil evaluasi menunjukkan bahwa algoritma Random Forest lebih superior dibandingkan SVM. Random Forest mencapai akurasi sebesar 94,09% dan mampu mendeteksi kejadian keterlambatan (Recall) sebesar 34,21%. Kinerja ini lebih baik dibandingkan SVM yang memiliki akurasi 93,17% namun hanya mencatatkan Recall keterlambatan sebesar 10,53%. Berdasarkan hasil tersebut, model Random Forest diimplementasikan ke dalam aplikasi berbasis web menggunakan Streamlit, yang memungkinkan petugas operasional memprediksi status penerbangan secara real-time berdasarkan jadwal dan kondisi cuaca.
Downloads
References
I. Hatıpoğlu and Ö. Tosun, “Predictive Modeling of Flight Delays at an Airport Using Machine Learning Methods,” Appl. Sci., vol. 14, no. 13, 2024, doi: 10.3390/app14135472.
Y. Wu, G. Mei, and K. Shao, “Revealing influence of meteorological conditions and flight factors on delays Using XGBoost,” J. Comput. Math. Data Sci., vol. 3, no. March, p. 100030, 2022, doi: 10.1016/j.jcmds.2022.100030.
Federal Aviation Administration, “Types of Delay,” U.S. Department of Transportation. Accessed: Oct. 20, 2024. [Online]. Available: https://aspm.faa.gov/aspmhelp/index/Types_of_Delay.html
M. Dai, “A hybrid machine learning-based model for predicting flight delay through aviation big data,” Sci. Rep., vol. 14, no. 1, pp. 1–16, 2024, doi: 10.1038/s41598-024-55217-z.
Prof. Swati Dhadake, Tuljai Kadam, Amanoddin Shaikh, Sumit Sabale, and Bhagyashri Shinde, “Flight Delay Prediction by Machine Learning,” Int. J. Adv. Res. Sci. Commun. Technol., vol. 3, no. 2, pp. 233–236, 2023, doi: 10.48175/ijarsct-8384.
S. M. Malakouti, A. R. Ghiasi, and A. A. Ghavifekr, “AERO2022-flying danger reduction for quadcopters by using machine learning to estimate current, voltage, and flight area,” e-Prime - Adv. Electr. Eng. Electron. Energy, vol. 2, no. November, p. 100084, 2022, doi: 10.1016/j.prime.2022.100084.
A. Renaldi and W. Maharani, “Depression Detection of User in Media Social Twitter Using Random Forest,” J. Inf. Syst. Res., vol. 3, no. 4, pp. 410–416, 2022, doi: 10.47065/josh.v3i4.1837.
W. Apriliah et al., “Prediksi Kemungkinan Diabetes pada Tahap Awal Menggunakan Algoritma Klasifikasi Random Forest,” vol. 10, pp. 163–171, 2021.
Y. Akkem, B. S. Kumar, and A. Varanasi, “Streamlit Application for Advanced Ensemble Learning Methods in Crop Recommendation Systems – A Review,” INDIAN J. Sci. Technol., 2023.
M. S. Lewa, P. Ariawan, and P. Budiarnaya, “Evaluasi Perkerasan Landasan Pacu Pada Bandara Pattimura Dengan,” vol. 3, no. 2, pp. 1–8, 2020.
V. Ganesan, “Machine Learning in Mobile Applications,” Int. J. Comput. Sci. Mob. Comput., vol. 11, no. 2, pp. 110–118, 2022, doi: 10.47760/ijcsmc.2022.v11i02.013.
A. Rajamanickam and C. Kamalakannan, “Land Use and Land Cover Prediction in Tamilnadu of India, Using Random Forest Machine Learning Technique,” Curr. World Environ., vol. 20, no. 1, pp. 206–220, 2025, doi: 10.12944/cwe.20.1.16.
H. A. Salman, A. Kalakech, and A. Steiti, “Random Forest Algorithm Overview,” Babylonian J. Mach. Learn., vol. 2024, pp. 69–79, 2024, doi: 10.58496/bjml/2024/007.
N. Ulfa and K. Surendro, “SMOTE-LOF for noise identification in imbalanced data classification,” J. King Saud Univ. - Comput. Inf. Sci., vol. 34, no. 6, pp. 3413–3423, 2022, doi: 10.1016/j.jksuci.2021.01.014.
S. Wang, Y. Dai, J. Shen, and J. Xuan, “Research on expansion and classification of imbalanced data based on SMOTE algorithm,” Sci. Rep., no. 0123456789, pp. 1–11, 2021, doi: 10.1038/s41598-021-03430-5.
Y. Li and Y. Mu, “Research and performance analysis of random forest-based feature selection algorithm in sports effectiveness evaluation,” pp. 1–15, 2024.
V. Sheth, U. Tripathi, and A. Sharma, “A Comparative Analysis of Machine Learning Algorithms for Classification Purpose Application Analysis of Machine Learning Algorithms for,” Procedia Comput. Sci., vol. 215, pp. 422–431, 2022, doi: 10.1016/j.procs.2022.12.044.
J. M. Nápoles-Duarte, A. Biswas, M. I. Parker, J. P. Palomares-Baez, M. A. Chávez-Rojo, and L. M. Rodríguez-Valdez, “Stmol: A component for building interactive molecular visualizations within streamlit web-applications,” Front. Mol. Biosci., vol. 9, no. September, pp. 1–10, 2022, doi: 10.3389/fmolb.2022.990846.
B. Gavrilović and J. Mitrović, “Comparative analysis of the traffic accidents in the territory of the city of Užice for 2021 and 2022 using open data and the Streamlit application,” Vojnoteh. Glas., vol. 71, no. 3, pp. 616–633, 2023, doi: 10.5937/vojtehg71-44007.
BMKG, “Data Online.” [Online]. Available: https://dataonline.bmkg.go.id/
This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.
