Predictive analytics with aviation big data

In this paper, we describe a novel analytics system that enables query processing and predictive analytics over streams of big aviation data. As part of an Internal Research and Development project, Boeing Research and Technology (BR&T) Advanced Air Traffic Management (AATM) built a system that makes predictions based upon descriptive patterns of massive aviation data. Boeing AATM has been receiving live Aircraft Situation Display to Industry (ASDI) data and archiving it for over two years. At the present time, there is not an easy mechanism to perform analytics on the data. The incoming ASDI data is large, compressed, and requires correlation with other flight data before it can be analyzed. The service exposes this data once it has been uncompressed, correlated, and stored in a data warehouse for further analysis using a variety of descriptive, predictive, and possibly prescriptive analytics tools. The service is being built partially in response to requests from Boeing Commercial Aviation (BCA) for analysis of capacity and flow in the US National Airspace System (NAS). The service utilizes a custom tool developed by Embry Riddle Aeronautical University (ERAU) that correlates the raw ASDI feed, IBM Warehouse with DB2 for data management, WebSphere Message Broker for real-time message brokering, SPSS Modeler for statistical analysis, and Cognos BI for front-end business intelligence (BI) visualization tools. This paper describes a scalable service architecture, implementation and value it adds to the aviation domain.