A Boeing 787-9 Dreamliner flying from Newark Liberty International Airport (EWR) to Leonardo da Vinci-Fiumicino Airport (FCO) requires approximately $68K in jet fuel for the 8.5-hour journey. Adjusting flight paths for wind conditions can reduce consumption and save thousands of dollars. While firms like Jeppesen offer commercial solutions, Scikit-decide provides an open-source alternative developed over six years.

This framework for reinforcement learning, automated planning, and scheduling optimizes flight paths, airline workforce schedules, and drone swarm paths. It integrates with OpenAP, an aircraft performance model by Dr. Junzi Sun, a tenured assistant professor at TU Delft in the Netherlands with a PhD in air traffic management. The author demonstrates the system using an Airbus A320 model on a high-end workstation featuring a 5.7 GHz AMD Ryzen 9 9950X CPU, 96 GB DDR5 RAM, and Ubuntu 24 LTS via WSL on Windows 11 Pro.

The tutorial details installing Python 3.12, Scikit-decide, OpenAP, OpenTop, DuckDB with spatial extensions, and QGIS 4.2.1 for rendering maps, showcasing a complete open-source toolkit for trajectory optimization.