Pendekatan Machine Learning Berbasis Fitur Geospasial Imputasi Nilai AADT yang Hilang: Studi Kasus Texas
DOI:
https://doi.org/10.30865/jurikom.v13i2.9703Keywords:
Machine Learning, AADT, Geospasial, Random Forest, Data ImputationAbstract
Annual Average Daily Traffic (AADT) is an important indicator in transportation planning and road network performance evaluation. However, missing values due to sensor interference or unrecorded data can reduce the quality of the analysis. This study aims to estimate missing AADT values using a geospatial feature-based machine learning approach with a case study in Texas, United States. Automatic Traffic Recorder (ATR) data is integrated with road network attributes from OpenStreetMap (OSM) through a spatial join process to produce features such as road classification, number of lanes, and speed limits. A Random Forest model is used to build an estimation model based on valid data (AADT > 0). The evaluation results show a coefficient of determination (R²) of 0.548, indicating that geospatial features can significantly explain variations in AADT. The imputation process successfully produced a dataset with a 100% convenience level and a spatial distribution pattern consistent with the road network hierarchy and metropolitan area. This approach demonstrates that the integration of spatial data and machine learning is effective in improving the integrity of traffic data to support data-driven decision making.
References
[1] A. Y. Nugroho, “Analisis Tingkat Kemacetan Lalu Lintas Menggunakan Data CCTV Pemerintah Kabupaten Sleman Berbasis Sistem Informasi,” JIMU: Jurnal Ilmiah Multidisipliner, vol. 04, no. 01, 2025, [Online]. Available: https://24jam.slemankab.go.id/
[2] J. Jusnidar, R. Riskayanti, Y. Setiawan, K. Khomsiah, A. Diath Yogmar, and D. Tribuana, “IMPLEMENTASI WEB-BASED TRANSPORTATION MANAGEMENT SYSTEM DI INDUSTRI TRANSPORTASI: SEBUAH TINJAUAN SISTEMATIS LITERATUR,” Jurnal Teknologi dan Bisnis Cerdas, vol. 1, no. 3, pp. 194–209, Dec. 2025, doi: 10.64476/jtbc.v1i3.15.
[3] Abdullah, L. P. Wardani, and Y. Siregar, “Prediksi Kemacetan Kota Semarang Berbasis Artificial Intelligence Sebagai Dasar Kebijakan Transportasi Cerdas Dan Smart Mobility,” Jurnal Mahasiswa, vol. 7, no. 4, 2025, doi: 10.51903/jurnalmahasiswa.v7i4.1438.
[4] P. E. Syaputra, “KAJIAN INTEGRASI TRANSPORTASI MULTI MODA UNTUK MENEKAN BIAYA LOGISTIK PADA WILAYAH KEPULAUAN (STUDI KASUS PADA PULAU BAWEAN),” Jurnal Transportasi, vol. 24, no. 1, pp. 49–61, 2024.
[5] D. Budi Hartanto, “PREDIKSI KUALITAS UDARA MENGGUNAKAN MODEL KOMBINASI ALGORITMA GAUSSIAN PROCESS REGRESSION DAN GENETIC ALGORITHM,” JURNAL INFORMATIKA TEKNOLOGI DAN SAINS (JINTEKS), vol. 7, no. 4, pp. 1660–1668, 2025.
[6] V. Anggraini, M. I. Faturohman, and H. Q. Karima, “Perencanaan Rute Distribusi Logistik Perkotaan Berbasis Data Geospasial Menggunakan Pendekatan Vehicle Routing Problem,” WALUYO JATMIKO PROCEEDING, vol. 18, no. 1, pp. 451–468, Jan. 2026, doi: 10.33005/wj.v18i1.186.
[7] A. Fikri, “Prediksi Kemacetan Lalu Lintas Urban Menggunakan Model Pembelajaran Mesin dan Data Mobilitas Real-time,” Journal of Engineering and Technological Science, vol. 1, no. 2, pp. 61–67, 2025, doi: 10.70716/jets.v1i2.133.
[8] A. H. Nurmakhlufi and E. Zuliarso, “PENERAPAN MACHINE LEARNING DALAM ANALISIS POLA PENGGUNAAN BANDWIDTH PADA PROVIDER INTERNET,” JURNAL INOVTEK POLBENG - SERI INFORMATIKA, vol. 10, no. 3, pp. 1331–1341, 2025.
[9] M. J. Faisti, R. Hadapiningradja Kusumodestoni, G. Wahyu, and N. Wibowo, “Mental Health Classification Using Naïve Bayes and Random Forest Algorithms,” Journal of Applied Informatics and Computing (JAIC), vol. 9, no. 4, p. 1740, 2025, [Online]. Available: http://jurnal.polibatam.ac.id/index.php/JAIC
[10] R. Arisandi, “PERBANDINGAN MODEL KLASIFIKASI RANDOM FOREST DENGAN RESAMPLING DAN TANPA RESAMPLING PADA PASIEN PENDERITA GAGAL JANTUNG,” Jurnal Gaussian, vol. 12, no. 1, pp. 136–145, May 2023, doi: 10.14710/j.gauss.12.1.136-145.
[11] B. Riznov and J. Santoso, “Pembangunan Model Klasifikasi untuk Menilai Lokasi Strategis Usaha Laundry Berdasarkan Analisis Geospasial dan Data Open-Source,” MALCOM: Indonesian Journal of Machine Learning and Computer Science, vol. 6, no. 1, pp. 73–84, 2026, doi: 10.57152/malcom.v6i1.2358.
[12] H. Utama, A. Masruro, and T. Indriyatmoko, “Integrasi Augmentasi Data dan Machine Learning dalam Prediksi Magnitudo Gempa Bumi,” BHATARA: Jurnal Multidisiplin, vol. 2, no. 3, pp. 97–108, 2025, [Online]. Available: https://earthquake.usgs.gov/earthquakes/feed/v1.0/csv.php
[13] W. Setyadi, Y. Nurhadryani, and I. Hermadi, “Pengembangan Sistem Manajemen Data Spasial Aset Jalan Tol (Studi Kasus Ruas Jalan Tol Bakauheni-Terbanggi Besar),” JGISE: Journal of Geospatial Information Science and Engineering, vol. 7, no. 1, p. 62, Aug. 2024, doi: 10.22146/jgise.97651.
[14] M. Gopinda, “STUDI PERBANDINGAN ALGORITMA MACHINE LEARNING UNTUK PREDIKSI PENJUALAN RETAIL,” Jurnal Ilmu Komputer dan Teknologi Informasi, vol. 1, no. 1, pp. 22–28, 2026, [Online]. Available: https://ojs.feliciajurnal.com/index.php/jikti/index
[15] D. Manurung, B. Zealtiel, and A. H. Lubis, “Prediksi Produksi Tanaman Padi di Indonesia dengan Menggunakan Algoritma Random Forest Regressor,” Journal of Computing and Informatics Research, vol. 4, no. 3, p. 345, 2025, doi: 10.47065/comforch.v4i3.2125.
[16] Z. Arsyad and S. Umaroh, “Penerapan Geo-Spatial Business Intelligence dalam Analisis dan Visualisasi Survey Kondisi Jalan,” INTERNAL (Information System Journal, vol. 7, no. 2, pp. 152–166, 2024, doi: 10.32627.
[17] M. R. Rahman, B. Jaya, and R. Latief, “Pengaruh Nilai Tanah Terhadap Rencana Detail Tata Ruang Di Kawasan Emas Garongkong Kabupaten Barru,” Urban and Regional Studies Journal, vol. 8, no. 1, pp. 94–109, Dec. 2025, doi: 10.35965/ursj.v8i1.7645.
[18] A. Riansah, O. Nurdiawan, and R. Herdiana, “PENERAPAN ALGORITMA RANDOM FOREST DAN DECISION TREE UNTUK MENINGKATKAN AKURASI KLASIFIKASI PENJUALAN PADA TOKO BANGUNAN,” JATI (Jurnal Mahasiswa Teknik Informatika), vol. 9, no. 3, pp. 4242–4249, 2025.
[19] A. P. Argadianata, D. A. Fatah, and H. Sukri, “KLASIFIKASI KUALITAS BUAH APEL MENGGUNAKAN METODE RANDOM FOREST,” JATI (Jurnal Mahasiswa Teknik Informatika), vol. 9, no. 2, pp. 2016–2022, 2025.
[20] E. R. Br Sebayang, Y. H. Chrisnanto, and Melina, “Klasifikasi Data Kesehatan Mental di Industri Teknologi Menggunakan Algoritma Random Forest,” IJESPG Journal, vol. 1, no. 3, pp. 237–253, 2023, [Online]. Available: http://ijespgjournal.org
[21] S. S. Putro et al., “Classification of diabetes mellitus disease at Rato Ebuh Hospital-Indonesia using the K-Nearest neighbors method based on missing value,” BIO Web Conf., vol. 146, Nov. 2024, doi: 10.1051/bioconf/202414601081.
