Academic Journal of Computing & Information Science, 2026, 9(4); doi: 10.25236/AJCIS.2026.090407.
Lu Qinghui1, Liu Yi1, Zhang Yun1
1University of Science and Technology Liaoning, Anshan, China
Aiming at the coupling of the three key indicators—flight delay, revenue, and carbon emissions in civil aviation, as well as the problems that traditional single-task prediction fails to mine internal correlations and lacks sufficient accuracy, this paper proposes an integrated prediction method based on multi-task deep neural networks. Based on the PIA 2026 aviation dataset, we complete data preprocessing and feature engineering, then construct and compare the random forest single-task model and the multi-task deep neural network model. The results show that the multi-task model can effectively capture the correlations among indicators, achieve higher accuracy in delay prediction, perform synchronous prediction of the three indicators, and possess stronger generalization ability. It can provide decision support for airline operation and low-carbon development, and improve the theoretical system of intelligent prediction in civil aviation. This study provides a feasible intelligent decision support scheme for the coordinated optimization of safety, benefit, and green development in civil aviation operations.
Civil Aviation Operation Indicators; Integrated Prediction; Multi-Task Deep Neural Network; Flight Delay; Carbon Emission
Lu Qinghui, Liu Yi, Zhang Yun. Integrated Prediction of Multidimensional Civil Aviation Operational Indicators: A Multi-Task Deep Neural Network Approach. Academic Journal of Computing & Information Science (2026), Vol. 9, Issue 4: 56-60. https://doi.org/10.25236/AJCIS.2026.090407.
[1] Bisandu B D ,Chandrakumar M ,Moulitsas I .Deep liquid neural network for prediction of weather- impacted flight delay[J].Intelligent Systems with Applications,2026,30200656.
[2] Shao L ,Huang Z ,He J , et al.A multi-factor flight delay prediction and evaluation method based on artificial neural network and cloud model[J].Proceedings of the Institution of Mechanical Engineers, Part G: Journal of Aerospace Engineering,2026,240(5):860-870.
[3] Murad A ,Ruocco M .Pre-tactical flight-delay and turnaround forecasting with synthetic aviation data[J].CEAS Aeronautical Journal,2026,(prepublish):1-22.
[4] Liu M ,Wang J ,Lyu Z .A flight delay prediction model featuring a multi-strategy enhanced golf optimization algorithm integrated with LightGBM[J].Cluster Computing,2025,28(12):782.
[5] Yuan Y ,Wang Y ,Lai S C .Multi-Attribute Data-Driven Flight Departure Delay Prediction for Airport System Using Deep Learning Method[J].Aerospace,2025,12(3):246.
[6] Zhong Q ,Yu Y ,Huang Y , et al.Prediction and Optimization of Civil Aviation Flight Delays Based on Machine Learning Algorithms[J].International Journal of Computational Intelligence Systems, 2025,18(1):189.
[7] Yin C ,Du X ,Duan J , et al.Unveiling Hidden Dynamics in Air Traffic Networks: An Additional- Symmetry-Inspired Framework for Flight Delay Prediction[J].Mathematics,2025,13(14): 2274.
[8] Keyvandarian A ,Pirnia M ,Scott D .Robust optimal design of sustainable aviation fuel supply chain [J].Computers & Industrial Engineering,2026,216111929.
[9] Christian M ,Ireti A ,Christoph M .Online flight booking: digital nudging to decrease aviation- related carbon emissions[J].Information Technology & People,2024,37(1):29-50.
[10] Wang Y ,Sun H ,Lin Y , et al.An interval-valued estimation method of aircraft route carbon emission: A function of aircraft seat capacity and route flight time[J].Energy,2024,294130937.