US works on AI to forecast Ukraine's ammunition and weapons needs

US works on AI to forecast Ukraine’s ammunition and weapons needs

FRANKFURT, Germany—In a large office building amid short grass, the International Donor Coordination Center, or IDCC, one of the U.S. military’s top data brains develops machine learning algorithms to predict military needs. ammunition and reparations from Ukraine, rather than simply reacting to it. But an older problem persists, according to the Department of Defense’s inspector general: The Pentagon isn’t doing enough to track what goes where.

Weapons and other aid sent by the United States and other countries to Ukraine are counted by the International Donor Coordination Center, or IDCC, here. British, American and Ukrainian officials are tracking the transfer of donated weapons and supplies down to individual bullets, IDCC officials told reporters this week.

Essentially, the Ukrainian Ministry of Defense will request, for example, armored vehicles or bullets, and IDCC officials at the center’s joint operations center will see if there is a donor country or entity that has the ‘article. Coalition officials then devise a process to get that material to the Ukrainians who then smuggle it across the border. Along the way, coalition officials document exactly what was requested, what was given, and what was received.

The requests also allow the IDCC to calculate and track how quickly Ukrainians are using the material.

“It’s important to understand their utilization rates to understand how quickly they need to be replaced,” a coalition official told reporters.

The IDCC is also working on security issues, such as when an arms shipment from Macedonia was spotted on social media. Authorities adjusted the timing of the shipment to avoid attracting public attention. They said that while some of the shipments were very visible at first – think armored vehicles on flatbed trucks – the shipments have since become much harder for the outside world to detect. IDCC officials have found ways to ship items without flight numbers or other tracking indicators that could alert Russian intelligence to try to intercept or destroy aid in transit.

Demands from Ukrainians for more supplies are both constant and urgent, officials say. That’s partly why the next step is to take the vast amounts of data the coalition collects and develop AI-based techniques to anticipate those needs in advance, rather than just respond as they arise. they arrive, said Jared Summers, director of technology for the 18th Airborne Corps, which works with the IDCC in Germany.

It’s the kind of thing big companies like Amazon do to make sure they can keep up with demand. But large retail companies have a few advantages that IDCC doesn’t. They can add sensors to shipments to get a full picture of the data. Summers said IDCC plans to circumvent this revenue shortfall by developing predictive models from existing data.

“You can start seeing failure rates and failure rates once we get enough data. And we can actually build that model without having to invest in sensors,” he said.

Knowing when an item might break is key to knowing when to ask for a replacement. He said models to predict Ukrainian needs were “in development” and expressed cautious optimism that they would be in place by the end of the year.

This kind of predictability could make a vital difference for Ukraine and its allies as they seek to ensure that Ukraine can continue to accept aid and fight on into next year and into the future. -of the. It could also help address some of the concerns of lawmakers and others about accountability for the aid that has been given and requested.

But there are big differences between how the IDCC tracks and maintains data for its operations and how the Department of Defense’s inspector general would prefer it to do so.

In July, the DOD Inspector General’s Office said the Pentagon was not using the year-old Analytics Center that was supposed to simplify data collection and sharing. Instead, the Department of Defense used journal vouchers. “The use of summary journal vouchers is a concern because journal vouchers have the potential to limit fund transparency, particularly if the summary journal vouchers do not trace back to supporting transaction details” , says the report.

On Tuesday, the IG office released a new report, reminding the Department of Defense to follow its own rules for accounting procedures, and cites a DOD memo from March that “indicates that Advana will be the only and single authoritative source to report additional Ukrainian funds and that DoD components are required to update Advana weekly with their direct funds execution.

The new report notes that the Office of the Secretary of Defense has “enhanced the functionality of Advana to increase traceability, transparency, and notification of the execution of additional Ukrainian funds.” But the analytics center was still not being used on a large scale or consistently enough. The result is that parts of the MoD are working with different figures on what kind of aid was allocated, used, etc.

Summers said using Advana as directed by the inspector general’s office would slow transfers, with potentially fatal effects. “For us, the ability to acquire the data in near real-time or real-time is pretty important to us,” he said. “Also, when you’re dealing with tactical datalinks, what we’re doing…it’s also near real-time…And an analytics platform, by design, doesn’t operate at that speed.”

The coalition needs to use all the data it has as quickly as possible, rather than running it through an analytics platform before it can see and execute requests.

“The preference is to be able to pull that information directly from the source to drive our decision-making in our processing instead of taking it out of the system somewhere else to work on something else and then passing it to us,” he said. said.

Summers said he is currently working on it with Craig Martell, the Pentagon’s head of digital and artificial intelligence. “We speak with his team, several times a week, even daily on a variety of topics,” he said.


#works #forecast #Ukraines #ammunition #weapons

Leave a Comment

Your email address will not be published.