A key challenge in Air Traffic Management is to provide a swift flow of airplanes at and near the airports. The pressure on existing airports will be higher as demand of air transport is predicted to increase over the next decades. Airline companies compete on delivering improved departure and arrival punctuality for their flights. In this paper we present experimental results where we are comparing the performance of traditional tower control decisions versus decisions supported by optimization technology in a simulation environment. We present a mathematical model for the integrated departure management and surface management problem and a solution algorithm based on a heuristic decomposition of the integrated problem. This represents a first attempt to solve the two problems simultaneously. Our approach is designed for dynamic rescheduling and real-time environment, with corresponding response time requirements. Finally, we present computational results that show significant improvements in punctuality and reductions in taxi times.