Prediction of Safety Incidents, Year 3

Safety incidents, including injuries, property damage and mission failures, cost NASA and contractors thousands of dollars in direct and indirect costs. Our data systems are able to collect and store information on both hazards, through inspections and employee identification programs, and incidents. Additional safety information is collected through audits, surveys, hazard analysis, and risk management. Other relevant data is collected around the center in areas like procurement, Human Resources and the clinic. The leading indicators in this group are plentiful. However, NASA has not connected these sets of data to be able to predict safety incidents and ultimately direct limited resources to the highest risk areas. This project seeks to define, develop and test an algorithm that will use hazard identification data as input to predict when and where there is a high probability of a safety incident occurring. This project was separated into two phases: Data Integration and Predictive Capability. The third year of the project, to be executed in FY2020, brings the two phases together into one application that will access continually updated data and predict areas of high safety risk. The final integrated application will include a dashboard to display the predictive analytics and a capability for basic trending of disparate sets of data. The application will meet the ultimate goal of using data to help decide how to direct limited resources to the highest risk areas. As NASA heads towards the Moon in 2024, there is no doubt that decision velocity will increase. This application will meet the need to make data-driven decisions at a pace that continues to add value, even as we take on new and exciting missions.

This project is broadly applicable across NASA as we try to transform our diverse data collections to better serve our mission. In particular, as we speed towards the Moon 2024 goal and beyond, data must aid NASA with increasing decision velocity. NASA SSC and other centers will benefit from this project through the additional value to data already collected. While the goal of this project is related to safety, the demonstration of data integration and algorithm development is also relevant to programs, projects and operations which collect similar data. This project showcases just one of the many possibilities for the applications of data analytics and machine learning to the NASA mission.

This is early/mid-stage (TRL 3) — the most realistic path in is NASA SBIR/STTR, which funds small businesses and research institutions to develop technology aligned with NASA's needs (equity-free, phased funding). Check whether a current SBIR/STTR solicitation topic overlaps with this project's technology area, or contact the project directly (above) to ask.

None of these are guaranteed paths for this specific project — TechPort itself doesn't have an "apply" button. Reaching out to the contact(s) above with a specific question is usually the fastest way to find out what's actually open.