The Pentagon’s top research arm is sponsoring development of a first-of-its-kind software that can model the events that contribute to conflicts around the world, and, if not quite predict the future, at least offer a timely heads-up on what might happen next.

The Defense Advanced Research Projects Agency (DARPA) and the Air Force Research Laboratory (AFRL) have given BAE Systems a $4.2 million contract for the first phase of the Air Force’s Causal Exploration of Complex Operational Environments program, which would create an interactive model of the political, economic, ethnic, religious, and territorial factors surrounding regional conflicts, according to an announcement from the company.

A key benefit of the software, which BAE calls CONTEXTS (Causal Modeling for Knowledge Transfer, Exploration, and Temporal Simulation), will essentially be its user-friendliness, delivering its results directly to military planners without having to first go through a gauntlet of specialized tools and technical experts.

Current tools for modeling and simulating complex operational environments tend to be special-purpose tools that are hard to configure and are heavily dependent on databases that are not updated automatically, DARPA says on its website. “These tools are not generally suitable for use directly by operational planners as they require expert modelers to assemble, configure, run, and interpret the outputs,” the agency said.

BAE’s software would automate a lot of what is done either manually or with a lot of technical-expert help, giving commanders simulations they can more easily work with, the company said. “To break down these barriers, CONTEXTS will use reasoning algorithms and simulations with the goal to give planners a quicker and deeper understanding of conflicts to help avoid unexpected and counterintuitive outcomes,” BAE’s Chris Eisenbies said in the company’s announcement.

Predictive software isn’t all that new or uncommon, of course. The texting app on your phone taps into writing patterns to guess what word you’ll use next or “correct” the spelling of the word it thought you were going to use (not always correctly). On a broader scale, scientists are applying predictive analytics to Twitter and other sources in an effort to predict the next pandemic. The government’s EMBERS project, run by Virginia Tech, takes a similar approach to predicting a range of events worldwide. Machine learning also is being applied to model and predict the actions of ISIS.

The Intelligence Advanced Research Projects Activity (IARPA), meanwhile, is putting a lot of effort into a range of Anticipatory Intelligence projects–from cyber operations to political uprisings–by employing artificial intelligence and deep learning. IARPA’s projects look to combine pattern recognition and historical trends with elements such as counterfactual reasoning and human judgement, in order to identify not only likely outcomes but also low-probability events.

The DARPA/AFRL/BAE project would be more narrowly focused than some of the other projects that take a global perspective, concentrating on helping commanders assess a particular situation. But, like IARPA’s projects, it wants to help commanders in expecting the unexpected. And, significantly when compared to current modeling and simulation efforts, it aims to let machines do a lot more of the work.

Read More About
More Topics
Kate Polit
Kate Polit
Kate Polit is MeriTalk's Assistant Copy & Production Editor covering the intersection of government and technology.