Lightweight Graph Embedding Augmentation for Airport Traffic Forecasting
Electronics · 03.07.2026 · 15 (13) · 2923
DOI: 10.3390/electronics15132923 ↗Kurz gefasst
Fachartikel in der Zeitschrift Electronics, online erschienen am 03.07.2026. Verfasst von Ahmed Alharbi. Die Arbeit wurde bisher 1-mal zitiert (Crossref) und nennt 44 Literaturangaben. Der Volltext ist frei zugänglich (Open Access, CC BY 4.0).
Abstract (Originalsprache)
Short-term airport traffic forecasting faces a structural gap: temporal ensemble models ignore route-network dependencies that shape hub operations, while deep graph neural networks require synchronised multi-airport operational data streams unavailable to single-airport operators, who have access only to their own operational records and publicly available route topology. To our knowledge, this study provides the first systematic evaluation of three graph representation classes—centrality measures, DeepWalk, and Node2Vec—as structural augmentations to Random Forest (RF), XGBoost, and LightGBM for hourly aircraft movement prediction at King Khalid International Airport (RUH), using a two-hop aviation graph combining RUH operational data with the OpenFlights database. Across all three ensemble families, random-walk graph augmentations consistently reduce MAE by approximately 9–17% relative to temporal-only baselines, whereas handcrafted centrality measures provide smaller and less consistent gains. Diebold–Mariano tests confirm that both RF+DeepWalk and RF+Node2Vec significantly outperform all nine baseline models (p
Zitieren
APA
Alharbi, A. (2026). Lightweight Graph Embedding Augmentation for Airport Traffic Forecasting. Electronics, 15(13), 2923. https://doi.org/10.3390/electronics15132923
Vancouver
Alharbi A. Lightweight Graph Embedding Augmentation for Airport Traffic Forecasting. Electronics. 2026;15(13):2923. doi:10.3390/electronics15132923
BibTeX
@article{Alharbi2026,
author = {Alharbi, Ahmed},
title = {Lightweight Graph Embedding Augmentation for Airport Traffic Forecasting},
journal = {Electronics},
year = {2026},
volume = {15},
number = {13},
pages = {2923},
doi = {10.3390/electronics15132923}
}
EUVIMED