This project focuses on optimising airline ground operations, a vital element of airlines for optimising efficiency and connectivity. First, we investigate what decisions can be made at different time horizons to efficiently and dynamically plan airline ground workforce and workload with the objective of minimising operating costs. We develop a forecasting framework and a decision model in considered time horizons. Next, we evaluate the impact on airline flight schedules based on critical decisions made at the airline’s ground operation. Additionally, we assess which changes should be made to the flight schedule based on the decisions that support minimising operating costs in airline ground operations. Furthermore, we optimise the dynamic baggage handling route plan for connecting flights while minimising total energy consumption. The study will propose an algorithmic framework considering dynamic baggage transmission and real-time IoT information, likely resorting to techniques such as Reinforcement Learning. Finally, we evaluate the robustness of flight-to-gate assignments given flight delay predictions. We will use a machine learning approach to increase the robustness of flight-to-gate assignments considering Schiphol Airport as a case study. To solve the different problems related to ground operations, we use operations research and machine learning techniques.