ASIAS is the primary tool for Improved Aviation Safety
METADATA COLLECTED, COLLATED AND ANALYZED
More Users Coming, more Incongruous Data, Greater Prediction needed
The award-winning Aviation Safety Information Analysis and Sharing (ASIAS) program has issued a Request For Information from vendors to enhance the architecture and power of this problem-solving meta database. In the terms of the RFI:
“The FAA is seeking information on commercial capabilities to design, build and sustain the next generation architecture and associated tools and processes to collect, cleanse, store, organize, integrate, analyze and share aviation safety data and information for the Aviation Safety Information Analysis and Sharing (ASIAS) program. This architecture will support safety analysis and information sharing activities for ASIAS, a collaborative government and industry initiative to proactively discover safety concerns before accidents or incidents occur, leading to timely mitigation and prevention of hazards. The new architecture will replace the legacy system of non-integrated silos of information. ASIAS, as referenced in this RFI, includes industry-proprietary FOQA (Flight Operations Quality Assurance) data and ASAP (Aviation Safety Action Program) data at the core, and is represented on the site asias.aero. ASIAS is not represented on the site asias.faa.gov, which is a separate program element with different data sets and access controls, and not related to this RFI.”
Program data sources include airline operator proprietary safety data (such as digital flight data and safety reports), FAA data (such as radar/surveillance data and navigational information), publicly available safety data, manufacturer information, air traffic voice data, weather data and other sources. This data has been an invaluable source of information to monitor known safety risks, evaluate the effectiveness of deployed safety mitigations, and identify emerging hazards.
Today, ASIAS has data-sharing agreements with over 40 commercial carriers, including all major U.S. domestic airline carriers, and a repository of more than 30 million digital flight records. ASIAS also includes over 120 corporate and business aviation operators, as well as labor associations, flight training entities, government agencies, manufacturers and trade associations. ASIAS is a central conduit for the voluntary exchange of safety information between the FAA and the aviation community, and a national resource for the aggregation, analysis, and dissemination of aviation safety analysis.
The scope of ASIAS analytic capabilities must include analytic tools to identify complex patterns and predict the probability of safety hazards, using historical data and predictive methods. This will include tools for data visualization, data analysis, anomaly detection, trend detection, statistical and inference models, and others. ASIAS must use emerging technologies, such as artificial intelligence and machine learning, to support predictive analytical efforts that enhance aviation safety. ASIAS must provide analysts with controlled access to authorized data and tools, to conduct safety analysis or tool development activities.
ASIAS must have a data fusion capability. Data fusion in the context of ASIAS involves joining extremely large, complex and non-homogeneous data, such as voluntary pilot and controller text reports, digital flight data, radar, weather, and other sources to build a comprehensive understanding of the flight environment and situational context for individual and aggregate flight operations. ASIAS analysts must have ready access to complete information about aircraft flight operations, fused together to develop enhanced metrics and benchmarks for analysis, and to help ASIAS members address safety issues through internal Safety Management Systems.
ASIAS must also mask specific information in accordance with program requirements. The masking, called de-identification, is vital to ASIAS processing to protect the identity and privacy of individuals and stakeholder organizations.
This initiative to increase analytical capacity NOW is prescient as the classes and numbers of ASIAS users are being expanded by Administrator Dickson. The success of the numbers is well supported by trend lines, analyses, individual sector experience statements, the press , lessons learned and its own library.
MORE DATA, COLLECTED FASTER AND MORE ACCURATELY, COLLATED FROM INCONGRUENT DATABASES, ASSESSING NEW DIMENSIONS AND ANALYZING AT A HIGHER LEVEL OF COMPLEXITY- ALL GOOD
The Federal Aviation Administration is conducting market research into vendors’ capabilities and experiences in developing an integrated analytics system to support a public-private initiative aimed at examining and sharing aviation safety data.
In a request for information notice posted Thursday, the agency is interested in the development of an architecture for Aviation Safety Information Analysis and Sharing program as part of efforts to help government and commercial organizations uncover safety risks before an accident or an incident occurs.
FAA intends for the new ASIAS technology to integrate data from the FAA’s Aviation Safety Action Program and the airline industry’s flight operations quality assurance system with other information sources such as text-based reports and air traffic voice communications.
The agency wants the system to feature multiple tools designed for visualization, trend detection and statistical and inference modeling among other functions.
The platform must also use artificial intelligence and machine learning to support aviation safety-related predictive analytics, FAA added.
 2018 Aviation Week Laureate Award for Commercial Safety(An unparalleled collaboration between government and industry to improve aviation safety. Having exceeded its first 10-year goal and reduced U.S. commercial aviation fatality risk by 83%, CAST now aims to reduce the remaining risk (50%) by 2025, leveraging industry data and analytical tools from ASIAS) and 2015 U.S. Department of Transportation Secretary’s Safety Team award)
Share this article: