The increased system complexity resulting from interaction of human and automated systems in aviation programs introduces new challenges that need to be addressed. Many notable flight incidents can be wholly or partially attributed to crew error, either due to inexperience with the aircrafts automated control systems or in response to component failures or adverse conditions. Flight safety experts can piece together information and data from multiple sources to identify the cause after an accident or incident has occurred whether it is due to human errors, machine failures or a combination of both. It is therefore reasonable to expect that much of the information is already dispersed in various databases and, with the right tools, flight safety experts can identify deficiencies and factors that may provide indicators or serve as precursors of accidents. Such actionable knowledge will lead to better training, design and/or onboard systems to ensure safety. In response to this need, SSCI proposes to build Analytics to Improve Reliability & SAfety in Flight Environments (AIRSAFE), a software toolbox that assists flight safety analysts in discovering key factors and their interactions among a large number of potentially relevant factors, testing one's hypothesis on the key factors to safety, and identifying previous incidents that support the hypothesis. The software toolbox is built on our previous and on-going efforts, such as DARPA's XDATA program, in BigData machine learning.