Q&A: Maxar executives discuss US Army simulation, Project Maven

ST. LOUIS As Russia amassed materials on its border with Ukraine ahead of its invasion in February 2022, commercial satellites orbited overhead.

The images and other readings gleaned from afar were instrumental in understanding the situation in Eastern Europe at the time, and their continued dissemination, including through the press, aids public understanding of the war.

Among those involved in capturing and distributing that information is Maxar Technologies, which provides satellite imagery to the Department of Defense and the intelligence community, among other national security assets.

In February 2023, for example, the Colorado-based company won an additional round of work on the US Army’s One World Terrain, which compiles highly accurate virtual maps of terrain around the world for military purposes. It is considered a key element of the Synthetic Training Environment services, an engaging training and testing tool. The company is also involved in the Maven project, which the Pentagon launched in 2017 to detect targets of interest in footage captured by unmanned systems.

C4ISRNET reporters interviewed two Maxar executives Tony Frazier, executive vice president and general manager of public sector land intelligence, and Jennifer Krischer, vice president and general manager of intelligence programs on the sidelines of the GEOINT symposium in St. Louis.

Portions of the interview below, conducted on May 23, have been edited for length and clarity.

Q: Where do you see the future of One World Terrain and, by extension, the Synthetic Training Environment? What does it look like?

frazier: We started with the goal of helping the Army modernize its training with geospecific data, with the goal of being able to provide soldiers with the most realistic experience possible.

Lieutenant General Maria Gervais, was the first cross-functional team lead for the synthetic training environment. Her vision at the time was: if we can have replays and sets with hundreds of experiences in the virtual environment, then we can help soldiers be safe when they actually deploy.

This continued to be the main focus of the programme. That said, as we exposed the data to different parts of the community, there was an insatiable demand from operational users to apply it to ongoing missions. Whether it was in support of the Afghan withdrawal, the data we provided on Ukraine using it for operational mission planning was very important.

Even the National Defense Authorization Act Fiscal of 2023, there was a reference to One World Terrain, and I think it did a good job of highlighting the variety of use cases that had been demonstrated.

So what we’re seeing is, as we build a more comprehensive global coverage of that capability, to be able to use that as a benchmark level to stack other data sources against it and have all those data sources inherit the same accuracy, that base really allows for a form of sensor fusion that we haven’t been able to see at scale.

One example we’re demonstrating is how we can apply 3D georegistration software that uses that reference as a way to take whether its spacecraft, or aircraft, or even an unmanned surface vehicle is powered by a sensor, and use the terrain as a source of record to fix it, both in terms of its correct position and its correct orientation, so that it can inherit the same accuracy as that base.

Think of a live feed from a drone. This would then let you know exactly within this kind of radius where that pixel is. This, I think, is probably one of the most revolutionary opportunities, in terms of getting it fully operational.

Q: How has the conflict in Ukraine shaped or affected Maxars business? How is this consumption? Is there a greater need for satellite images or your other products?

frazier: We support a global mission and have been providing these capabilities for decades. And you can watch every major event, and Maxar played a part in that, in some way.

I think the particularity of Ukraine was that at all stages, the crisis leading up to the conflict, we were able, through different channels, to expose our capabilities in a way that was useful to the mission.

The Defense Department’s focus now is integrated deterrence, the role that advertising was able to play in bringing transparency to what was happening, with the buildup of troops and, as it rotated towards conflict, what was happening on the field.

The combination of what has been exposed through the media, through our partnerships there, coupled with the fact that the intelligence community, the Department of Defense, allies and partners have all been able to access current images on those areas, it only allowed a level of interoperability and mission planning that, I think, helped sustain the mission, but it also helped a lot of decision makers think about ways that can be applied, more broadly.

I know you recently covered the Global Information Dominance Experiments series.

One of the things that has helped us do is have conversations with different stakeholders across the community, who have looked at how I can take the increase in commercial collection, some of the innovations that are happening with applied machine learning, then the vision artificial, to be able to interpret images quickly, the types of technology that I referred to earlier with our 3D, where we can georeference that data on rapid timelines, and then how they can support different forms of experimentation. This is demonstrating how new however commercial use cases can be applied to missions here and now.

We supported Project Convergence and Scarlet Dragon; those were examples of exercises and trials that we supported with commercial capabilities. I think we’re seeing that there’s a lot of interest.

Q: The big news at GEOINT yesterday was Project Maven, with Vice Admiral Frank Whitworth speaking about its transition to a logging schedule. How do you imagine Maxar will take part in Project Maven and what do you hope to contribute?

Crischer: We are already contributing to the Maven project.

We are generating algorithms around our electro-optical and synthetic aperture radar imaging capabilities. So object tracking, using those different modes.

We’ve also been working with Project Maven for years to provide low-latency imagery so we can run the algorithms against the imagery in a sensor-to-shooter methodology that truly resonates with the fighter. So we’ve done these things before.

We envision the future of Maven to be: How do you bring the vast computer vision algorithms to underpin the different missions, whether it’s the Intel analyst or the fighter in the field, and how do you enable the fighter to do things?

We’re working almost hand-in-hand to figure out what it needs to be and help shape the future, so that it’s not vendor-locked, you really meet the users where they need the information.

frazier: In our conversations, the intent is to enable geospatial AI at scale. And as a result, as these capabilities become more mature, you want to be able to take advantage of all the harvesting that’s happening in the constellation.

For the US government, the constellation includes commercial as part of it. That’s why EOCL is a commercial electro-optical layer. With the contracts that we’ve been awarded, and Planet and BlackSky, and then what’s being done now to add other modes, like radar and radio frequency sensing and the like, the goal is to create an architecture where you can do the algorithms against that source and then feed the information to those users.

We’ve been using our existing systems a lot to apply computer vision against the images that they were hosting and spreading now, throughout the community, and now it’s about how we can actually do that at scale, have more machine-to-machine exploitation at scale. The last two decades have focused on how humans view images.

Q: With Project Maven and with a lot of these things like Joint All-Domain Command and Control, there’s just an incredible amount of collection and data that needs sorting. So you can’t ignore the AI ​​or ML part on your side, right? Does it have to be cooked, basically?

Crischer: Absolutely.

frazier: Correct.

Q: Is there a need for one-space terrain? Maybe with a more artistic name?

frazier: I can see it happening.

Have you heard the director of the National Geospatial-Intelligence Agency, his comments, about how they are supporting the lunar mission. And I think, yeah, we need to have an accurate representation of all the domains, where we expect to navigate securely, to be able to mitigate threats, et cetera.

Colin Demarest is a reporter at C4ISRNET, where he covers military, cyber and IT networks. Colin previously covered the Department of Energy and its National Nuclear Security Administration, namely Cold War cleanup and nuclear weapons development for a South Carolina newspaper. Colin is also an award-winning photographer.

Courtney Albon is C4ISRNET’s reporter for space and emerging technology. She has covered the US Army since 2012, with a focus on the Air Force and Space Force. You reported on some of the Department of Defense’s most significant procurement, budget and policy challenges.

#Maxar #executives #discuss #Army #simulation #Project #Maven

Leave a Comment