Ukraine is tapping into a valuable resource to develop its military capabilities in the age of artificial intelligence (AI): millions of hours of drone footage collected from the front lines of the ongoing war with Russia.

As warfare increasingly incorporates AI-based technologies, Ukraine’s archive of drone footage is poised to play a key role in training AI models capable of making decisions in combat situations. fight.

Oleksandr Dmitriev, founder of OCHI, a Ukrainian non-profit digital system, explained that his platform centralizes and analyzes video feeds from more than 15,000 drone crews working on Ukrainian battlefields. Since 2022, the OCHI system has accumulated 2 million hours of drone imagery, a vast pool of data that will be used to train AI models to improve decision-making on the battlefield.

Dmitriev called these images “food for AI,” emphasizing the immense value of data for training AI. “If you want to teach an AI, if you give it 2 million hours (of video), it will become something supernatural,” he said.

The main function of the system is to provide military commanders with an overview of battlefield activity by displaying images from multiple drone crews on a single screen. However, over time, the team behind the system recognized that the drone video could serve as a critical record of the war, prompting them to store it for future use.

According to Dmitriev, on average five to six terabytes of new data from fights are added daily.

This extensive collection of footage will provide invaluable data for training AI systems in various aspects of military operations, such as combat tactics, target identification, and evaluating the effectiveness of weapon systems.

Dmitriev pointed out that AI programs can study the trajectories and angles of weapons to determine the most effective ways to use certain systems.

In addition to training the AI ​​in combat-related activities, the collected images can also help the AI ​​learn to identify different objects on the battlefield.

Samuel Bendett, senior researcher at the US-based Center for a New American Security, explained that such a large and varied data set is crucial for teaching AI how to differentiate between objects such as roads, obstacles natural or ambushes. “Humans can do this intuitively, but machines cannot, and they need to be trained on what is or is not a route, a natural obstacle or an ambush,” Bendett said.

Ukraine’s defense efforts are also supported by another system called Avengers, developed by the Ministry of Defense. The Avengers system centralizes and collects video from drones and CCTV feeds, although the ministry declined to provide additional details on this technology.

Previous reports revealed that Avengers uses AI to spot around 12,000 pieces of Russian equipment every week. This system works in tandem with drone technology to improve surveillance and target recognition.

AI is already used in various aspects of Ukrainian military operations. Many drones use AI to fly autonomously towards targets without a human pilot. Additionally, Ukraine is exploring the possibility of developing drone swarms, in which a group of interconnected drones would execute commands from a single AI-driven system.

As Ukraine continues to refine its use of AI technologies on the battlefield, Russia has also integrated AI into its military strategies.

The Russian military has touted its use of AI, notably in its Lancet attack drones, which have proven deadly against Ukrainian armored vehicles.

Both countries are increasingly relying on AI technologies to augment their military capabilities, marking a new era in modern warfare. As the conflict progresses, the value of AI-based systems and the data they generate will likely continue to grow, further shaping the future of combat.