WASHINGTON — A data collection and dissemination program the military has used for the past five years in Africa could be a model for how military intelligence analysts make better sense of the information they face every day. .
The Africa Data Science Center started as a pilot project in 2018 using data science tools to sift through thousands of incident or intelligence reports to find the relevant information an intelligence soldier needs to analyze to his command.
Colonel Mark Denton, commander of the 207th Military Intelligence Brigade, told an audience at the Association of the American Army’s annual gathering on Tuesday that the days when analysts sifted through stacks of paper reports or created their own spreadsheets to track data were over.
The current system can “easily consolidate 3,000 reports in seconds,” Denton said.
“What it does is turn chaos into clarity,” said Major General Todd Wasmund, commander of Task Force Southern Europe-Africa.
Denton has put together a map of the African continent for the public. Large sections of it were saturated with overlapping purple bubbles. Each bubble was a report of a “conflict event,” such as a bombing, riots, or other significant development in a city, state, nation, or region.
“The purple stuff is the chaos that happens that the analyst has to understand,” Denton said.
The system used by the data center uses machine learning tools and natural language programming to find the data an analyst will need and combine it into a readable report that doesn’t require a computer programmer to decipher it.
Most data analysis done by hand is complicated, time-consuming and makes it difficult to spot trends quickly, Denton said.
By using natural language processing, which allows computers to deliver information in a language a human can understand rather than a computer programming language, analysts can categorize textual reports and use machine learning tools to automate the process.
During the Data Science Center pilot, users saw a 70-90% reduction in irrelevant reports returned from searches. The tools also allow analysts to create visualized reports, with charts, graphs and maps that can give commanders better context and a faster understanding of the intelligence picture.
Programmers and data scientists sit side-by-side with analysts to determine what types of questions the analyst can ask about the available data and how the answer will be provided. The analyst tells the data scientists what they need to know and the scientist uses programming and algorithms to interrogate the data to get the answer.
Once the system provides these data summaries, users can provide feedback to make the machine learning model more accurate. A user can tell the system what was useful and what was not. This step should help improve the models over time, making them more efficient and accurate, Denton said.
Currently, the Data Science Center only works for US Africa Command initiatives. But, Denton added, intelligence branch commanders and other combatant commands are working to develop their own data collection and analysis tools.
The idea is to create a kind of “hub and spoke” system so that all Army intelligence is linked across regions, Denton said. This will allow analysts to find patterns or extract data to inform operations in their own domain, he added.
Todd South has written about crime, the courts, government and the military for several publications since 2004 and was named a 2014 Pulitzer Finalist for a co-authored project on witness intimidation. Todd is a Navy veteran of the Iraq War.