Air traffic management (ATM) systems must accurately estimate flight demand, analyze network delays, and optimize capacity. This research uses a global airline dataset with passenger information, airport characteristics (including geographic markers and continental classifications), flight scheduling data (timing and destination details), crew information, operational status records, and OpenSky Network real-time states data to create an intelligent ATM decision-support framework. Advanced machine learning (ML) methods like gradient boosting and sequential modeling are used to build network models of flight routes between origins and destinations, develop temporal demand patterns for individual airports, analyze delay factors, and predict congestion periods. The research uses mixed-effects statistical models using crew data to measure operational variability and demographic and nationality-based analysis to identify demand trends for improving staffing and security processing during busy times. Strategic airports need coordinated slot management before tactical operations, according to network analysis. The method recommends dynamic take-off and landing slots, optimum gate assignments with turnaround buffers, and smart flight rescheduling to fairly spread peak demand for each airport. Additionally, dependability monitoring tools reveal punctuality probability and risk assessment ratings for delay propagation across linked flight pathways. Minimizing ground delays and aerial holding patterns reduces fuel consumption and emissions while improving schedule dependability and passenger happiness, supporting environmental sustainability objectives. The framework ensures repeatable research, may be used globally, and can include meteorological data and airspace capacity limits to improve real-time traffic flow management. Evaluation metrics will include Mean Absolute Error (MAE), Root Mean Square Error (RMSE), On-Time Performance (OTP), Route Efficiency Index, Fuel Consumption Variance, and CO2 emissions per flight-km