Skip to main content

Ukraine and NATO develop AI models to predict enemy drone attacks and plan artillery operations

russian attack drone downed near the line of contact
AI model for predicting enemy drone activity now ready for integration into the Armed Forces of Ukraine's situational awareness systems

The NATO-Ukraine Joint Analysis, Training and Education Centre (JATEC) presented two AI-based solutions. The first predicts enemy drone attacks, while the second helps plan Ukrainian artillery operations.

The solutions, code-named "Model No. 13" and "Model No. 32," were jointly developed by NATO's Allied Command Transformation (ACT) and the Armed Forces of Ukraine, with the participation and support of JATEC.

The presentation took place during a three-day seminar in Vilnius, Lithuania, attended by experts from NATO member states and NATO bodies, as well as military experts from several units of the Defence Forces of Ukraine.

AI that predicts enemy drone attacks: "Model No. 13"

It is a tool capable of forecasting enemy drone use near the line of contact based on an analysis of historical data, weather conditions, and the current battlefield situation.

The AI model can determine with a high degree of probability:

  • intensity;
  • locations;
  • timeframes;
  • types of UAVs deployed.

The solution has already been validated using real-world datasets. It has been refined and is ready for integration into the Armed Forces of Ukraine's situational awareness systems.

AI for artillery planning: "Model No. 32"

This decision-support module tests the capability to automatically generate artillery operation plans.

"Model No. 32" factors in mission requirements and current operational data, including:

  • available weapon systems;
  • ammunition;
  • firing positions and constraints.

Based on these factors, the AI model generates viable operational options.

The model first applies parameters related to logistics, ballistics, and engagement zones to rule out infeasible options, then evaluates and ranks the viable alternatives. This reduces the need for "manual" comparison of options, shortens decision-making time, and enhances the efficiency of the fire engagement loop.

Subject to successful testing and validation, the model has the potential to be scaled to other combat units of the Defence Forces of Ukraine involved in delivering fires against the enemy. A prototype has already been handed over to Ukrainian stakeholders for testing and verification.

AI in warfare: Ukraine and NATO deepen cooperation

Ukraine and NATO are deepening cooperation on using modern IT solutions, artificial intelligence, and machine learning technologies in analytical processes. This cooperation facilitates the exchange of expertise and the development of common approaches to using advanced technologies in defense.

As previously reported, the United Kingdom became the first international partner to join Ukraine's Avengers Labs platform. This will allow British defense companies to train their own AI models for unmanned systems using real battlefield data.

Read next

Ministry of Defence launches Brave1 Dataroom, a secure environment for training military AI solutions

Tags