Schiphol Group is a group of airports, best known for Amsterdam Schiphol Airport. Schiphol is the third busiest airport in Europe. Due to its location, Schiphol is unable to build substantial new infrastructure to increase capacity. In an effort to increase on-time performance, a broad initiative was started to gain insight into the cause of delays. One of these possible causes is the 'turnaround' process. During a turnaround, an arriving aircraft is 'turned-around' to become a departing one. This process includes events such as re-fuelling. The turnaround is fully arranged and coordinated by the airline - resulting in a variety of handlers and differences in (order of) procedures. Schiphol is not involved in organising this, and therefore doesn't have detailed information about the events. Most importantly, whether the aircraft will be able to leave on time. In this talk, we'll discuss how Schiphol approached this problem with an innovative Deep Learning initiative. Our solution generates events as they happen by analyzing a real-time feed of camera images of the aircraft at the gate. We'll focus on how we set up the streaming pipeline and the challenges we faced, such as running GPU-backed infrastructure in production. Our main components are Apache Kafka and Tensorflow, backed by Azure Kubernetes Service. We'll explain how we went from a manual, batch-based Tensorflow process to a fully-automated, near real-time streaming solution.
Daniel van der Ende is a data engineer at GoDataDriven. He enjoys working on high performance distributed computation with Spark, empowering data scientists by helping them to run their models on very large datasets with high performance. He is an Apache Spark and Apache Airflow contributor and speaker at conferences and meetups. In his spare time, he enjoys video games and reading (both fiction and non-fiction) and can sometimes be found trying out new tech on his home-built server.
Tim van Cann is a Machine Learning Engineer at GoDataDriven. His drive is getting models to production quickly and automated, taking away complexity from Data Scientists and letting them focus on building models. Tim enjoys working on distributed systems and has a passion for streaming pipelines. He is fluent in Python and Scala and loves diving in to function programming.
With degrees in Artificial Intelligence, mathematics and teaching, knowledge sharing runs through his veins and gives trainings, and speaks at meetups and conferences.
In his spare time he experiments with home automation, contributes to open-source and spends a considerable time in the gym.