The System Wide Information Management (SWIM) Program is a National Airspace System (NAS)-wide information system that supports Next Generation Air Transportation System (NextGen) goals. SWIM facilitates the data-sharing requirements for NextGen, providing the digital data-sharing backbone of NextGen. The SWIM Cloud Distribution Service (SCDS) is a Federal Aviation Administration (FAA) cloud-based service that provides publicly available FAA SWIM content to FAA approved consumers via Solace JMS messaging. In this session we are going to show case the work we did at USDOT-BTS on Automating the required Infrastructure, Configuration, Ingestion and Analysis of the following public SWIM Data Sets:
SWIM provides a lot of information which with proper validation and analysis you can discover interesting insights like:
It could also be extended to analyze and predict multiple scenarios related to flights, airport and passenger behavior. Our initial solution leverages Azure Databricks, Apache Kafka and Spark-XML among others, but it is a flexible environment that could be extended to analyze more SWIM or similar streamed data sources, and since we are using Infrastructure as a code and Configuration Managements tools, it could be deployed and/or extended anywhere.
Marcelo Zambrana is a cloud solution architect at Microsoft focused on infrastructure automation and application development. He has been helping federal, state, and private industry customers for multiple years, including banking and healthcare. Marcelo specializes in enterprise hybrid architecture, cloud migration, cloud service models (PaaS, IaaS, and SaaS), automation, infrastructure and compliance as a code, and configuration management. In short: big DevOps fun with a little bit of an OCD problem on the details.
Sheila Stewart is a Solutions Architect at Databricks focusing on federal civilian customers. She has a BS in Physics from the California Institute of Technology and an MS in Nuclear Engineering and Radiological Sciences from the University of Michigan and has over 15 years of data analysis and algorithmic development experience in feature extraction and classification for Department of Defense customers.
Mehdi Hashemipour is a Data Scientist at USDOT. He has a Ph.D. in Systems Engineering focused on Artificial intelligence from George Washington University, where he is now an Adjunct Professor at the School of Engineering and Applied Science. Mehdi has over 10 years’ experience in Building Machine Learning, Deep Learning, Simulation Modeling, and Decision Support Systems.