Data-Driven Air Traffic Management: Forecasting Demand, Modeling Delay Propagation, and Demand Capacity Balancing

Air Traffic Management (ATM) must be familiar with the exact Aircraft Take-off Weights (ATOWs) of airplanes to make the most use of runways, maintain safety margins high, and keep utilization and resources in balance. This paper aims to present a dependable ATOW forecasting methodology that can assist the air transport industry in enhancing operational decision-making. This research used datasets acquired from the EUROCONTROL Performance Review Commission (PRC) 2024 Aircraft Take-Off Weight Estimation dataset featuring 527,000 flights over Europe containing aircraft details, air trips and flight conditions. Technique comprises structured data input, inspection of missing data, timestamp aggregation to identify demand cycles over time, and domain-specific feature engineering using distance_per_minute, block_minutes, taxiout_ratio, and a strong wake turbulence metric The two supervised learning models used were Linear Regression (LR) for understanding and XGBoost for performance prediction In comparison to LR's 4,409 kg MAE (mean absolute error), 7,061 kg RMSE (root mean square error), and 0.9825 R² value, XGBoost significantly excelled with validation results showing an R² value of 0.9992 and an RMSE of 1,514 kg In the absence of labelled test targets, cross-validation nevertheless showed a constant degree of generalizability The residual diagnostics showed that the model was reliable for practical execution with low-variance deviations that were unbiased An accurate ATOW estimate improves the demand-capacity balance and On-Time Performance (OTP) in ATM, which in turn affects the runway schedule, wake turbulence diversion, slot allocation, and fuel planning The results highlight the need to include ATOW predictions in both tactical and strategic planning to reduce delays, increase airspace usage, and promote sustainable aviation operation and possesses significant improvements will consist of weather and runway conditions, stochastic ambiguity computation, and drift monitoring to keep up with ever-changing operating variables while maintaining accurate forecasts.