In our previous blog posts, we discussed the “why” for RAIN, briefly touched on what RAIN does, and how the components of RAIN interact. In this post, we’ll discuss the potential real-world uses and applications of RAIN.
It’s commonly stated that operators and analysts who rely on data to perform their mission often spend as much as 80% of their time gathering and sifting through data, sometimes across multiple systems and networks, allowing only about 20% of their time performing analysis. RAIN seeks to flip that ratio by enabling machines to perform the gathering and sifting based on the current tradecraft applied by operators and analysts; and apply AI/ML algorithms for correlation and level-1 fusion emulating user-defined analytics.
Ultra envisions RAIN as a solution for any mission set that relies on disparate data sources within and/or across networks and requires operators or analysts to manually perform analytics. Machines are much more capable than humans in rapidly sifting through large volumes of data to find the necessary elements used needed to accelerate the sense, make sense, act loop. With the amount of time saved by RAIN providing more complete solutions to the operator or analyst, they then can spend the majority of their time on the more complex analytics and tradecraft that require human decision-making.
RAIN is not a one-size-fits-all solution, but rather it is designed to be user-defined and mission driven. Ultra will work directly with the operators and analysts to learn the systems and networks they use to perform their mission(s) along with any tradecraft and analysis methods they apply, then tailor algorithms to accomplish those tasks.
Here are some examples of how RAIN will apply:
Analysts supporting air and missile defense operations must sift through volumes of reports and information they receive, mostly textual, from across multiple systems and networks, identify the key elements of information required, then redact or sanitize the information for dissemination. RAIN can perform these functions based on current operating procedures and present the solutions to the analyst for validation and dissemination. RAIN can also incorporate additional sources that may not be available to analysts today due to classification restrictions or other challenges.
An operator tasked with performing combat identification missions and disseminating near-real-time data to tactical data links. RAIN can effectively monitor and harvest information in real time from a multitude of data and information sources and provide the operator with more timely, accurate, and complete information that may include correlated data from communications intelligence, electronic intelligence, infrared, indigenous radars, open-source information, and more.
Direct Support Operators and Direct Support Analysts supporting special operations aircraft currently have very limited access to information and data. With RAIN, they can tailor their queries and publish/subscribe settings, centered around the aircraft’s location, to receive multi-source, multi-domain correlated and fused information on their single system. This information can include national, theater, tactical, and open-source sources to greatly enhance their situational awareness and threat warning abilities.
Operators and analysts aboard an Aegis cruiser can detect objects at relatively long distances. Once an object is detected, the work begins to identify, decide, and act. Using RAIN and including relevant national source data elements allows that work to be done much more quickly and efficiently, significantly reducing reaction time.
In all cases, RAIN provides pedigree and provenance to the operator/analyst, which allows them to verify and validate the solutions provided.
In the end, RAIN can be tailored to meet any mission need that requires or will benefit from knowledge at the speed and scale of machines, anywhere, anytime.
For more information on RAIN go to Intelligence systems | Intelligence & Communications | Ultra.
Read Ed Campbell’s blog Tomorrow's Wars Are Here Today
Read Richard Ramsey's and Jimmy Kao's blog Solving the Data Intelligence Gap