Frankfurt, Germany-In a large office building amid tight grass, the International Donor Coordination Center, or IDCC, one of the US military’s top data minds is developing machine learning algorithms to predict, rather than simply respond to, Ukraine’s needs for ammunition and repair. But the old problem persists, according to the Defense Department’s Inspector General: The Pentagon isn’t doing enough to keep track of what’s going on.
Arms and other aid sent from the United States and other countries to Ukraine by the International Donor Coordination Center, or IDCC, are recorded here. IDCC officials told reporters this week that British, US and Ukrainian officials are tracking the transfer of donated weapons and supplies down to single bullets.
Basically, the Ukrainian Ministry of Defense will order, say, armored vehicles or bullets, and IDCC officials at the center’s Joint Operations Center will see if a donor country or entity possesses this item. Then coalition officials design a process to get that equipment to the Ukrainians, who then seize it across the border. Along the way, coalition officials document exactly what was requested, what was donated, and what was received.
The applications also allow IDCC to calculate and track how quickly Ukrainians are using the materials.
“Understanding their rates of use is important to understanding how quickly they need to be replaced,” a coalition official told reporters.
IDCC also works on security issues, such as when an arms shipment from Macedonia was picked up on social media. Officials adjusted the timing of the shipment to avoid drawing public attention. They said that while some of the cargoes were very visible at first – think armored vehicles on flatbed trucks – it has since become harder for the outside world to detect. IDCC officials have discovered ways to ship items without flight numbers or other tracking indicators that might alert Russian intelligence trying to intercept or destroy aid in transit.
Officials said requests from Ukrainians for more supplies were ongoing and urgent. Jared Summers, the company’s chief technology officer, said that’s partly why the next step is to take the large amounts of data the alliance collects and develop AI-based technologies to anticipate those needs early, rather than just responding as they come in. XVIII Airborne Corps, which operates with IDCC in Germany.
It’s the kind of thing that big companies like Amazon do to ensure they can meet demand. But large retail clothing has some advantages that IDCC does not. They can add sensors to shipments to get a complete data picture. Summers said the IDCC plans to overcome this shortcoming by developing predictive models from existing data.
“You can start seeing failure rates and breakdown rates once we have enough of that data,” he said. “And we can actually build this model without having to invest in sensors.”
Knowing when an item might break is key to knowing when to require a replacement. He said Ukrainian needs forecasting models were “under development” and expressed cautious optimism that they would be ready by the end of the year.
This kind of predictability can make a vital difference to Ukraine and its allies as they strive to do so make sure that tHat Ukraine can continue to accept help and fight until next year and beyond. It may also help satisfy some Fears of the legislators and others regarding accountability for assistance provided and requested.
But there are some big differences between how IDCC tracks and retains data for its operations and how the DOD’s Inspector General prefers to do so.
In July, the Office of the Inspector General of the Ministry of Defense He said The Pentagon was not used One year old Analytics Center It’s meant to simplify data collection and sharing. Instead, the Department of Defense was using journal vouchers. “Using summary journal vouchers is a concern because journal vouchers have the potential to reduce the transparency of funds, especially if summary journal vouchers do not refer to supporting transaction details,” the report said.
On Tuesday, the IG office released a file new reportto remind the DoD to follow its own rules on accounting procedures, and cites a March DoD memo that “states that Advana will be the only reliable source for reporting supplementary funds in Ukraine and that DoD components are required to update Advana weekly with its direct fund execution services.”
The new report noted that the Office of the Secretary of Defense had “made improvements to jobs.” Advana To increase the traceability, transparency and reporting of the implementation of supplementary funds in Ukraine.” But the Analytics Center is still not used widely or consistently enough. The result is that parts of the Ministry of Defense are operating with different numbers on what kind of assistance has been allocated, used, etc.
Using Advana as required by the OIG would slow transmissions — with potentially fatal effects, Summers said. “For us, the ability to get data in near real-time or in real time is somewhat important to us,” he said. “Also, when you’re dealing with tactical data links, which we do…that’s also close to real time…and an analytics platform, by design, doesn’t run that fast.”
The alliance needs to use all the data it has as quickly as it can get, rather than running it through some analytics platform before they can see and fulfill the requests.
“The preference is to be able to take this information directly from the source to go and drive the decision-making process in our processing rather than take it out of the system somewhere else to work with something else and then feed it to us,” he said.
Summers said he is currently working on it with Craig Martell, the Pentagon’s chief digital and artificial intelligence officer. “We speak with his team several times a week, if not on a daily basis on a variety of topics,” he said.