Хочете будувати кар’єру в Data Science та AI? Vodafone Big Data Lab відкриває новий набір —>
Наталя ХандусенкоWar
29 October 2026, 16:15
2026-10-29
AI from NATO and Ukraine predicts the movement of Russian drones on the front lines: how "Model 13" works
NATO, together with Ukrainian forces, have developed a new artificial intelligence model called Initiative 13 (“Model 13”), which predicts enemy drone activity for the next day with high probability.
NATO, together with Ukrainian forces, have developed a new artificial intelligence model called Initiative 13 (“Model 13”), which predicts enemy drone activity for the next day with high probability.
This was reported by Business Insider, citing a spokesman for the NATO Joint Analysis, Training and Education Center (JATEC).
Earlier this month, dev.ua already wrote that Ukraine had announced this program , but now JATEC is revealing new details about its work.
The system collects an array of disparate data and transforms it into a clear map of expected enemy actions, covering an area from 5 to 50 km behind the line of contact.
How the forecasting model works
For analysis, the territory is divided into geographical areas ("sectors"). For each of them, the AI determines:
the expected intensity of strike and reconnaissance UAVs;
the level of threat and the dynamics of its change;
range of possible risk factors.
The model is trained on real combat data. It takes into account the previous activity of Russian drones, their types, times and methods of use, as well as weather conditions, terrain and distance to the front.
"The system helps commanders identify high-risk areas in order to more effectively deploy forces and equipment. At the same time, "Model 13" does not replace operational data on the current situation and the decisions of the command itself," JATEC explained.
Integration into the Ukrainian Delta system
In mid-October, the Ministry of Defense of Ukraine reported that the Model 13 is ready for integration into national situational awareness systems, in particular the Delta battlefield management system.
The algorithm was developed by the Ukrainian military together with the NATO Command Transformation with the support of JATEC, a joint NATO-Ukraine organization based in Poland.
In addition, the Ministry of Defense notes that another AI model, “No. 32,” is in the prototype stage and is designed to plan artillery deployment. Artificial intelligence is increasingly integrated into the war in Ukraine, from autonomous navigation of strike drones to the deployment of unmanned ground systems.
“This is one of the steps that brings us closer to the collaborations that we are now waiting for.” L7 Simulators receives NATO codification for its entire line of simulators
Як нейромережі бачать вільну та незалежну Україну? Тест dev.ua
Нейронні мережі для генерації зображень бачать світ по-своєму, їхню логіку зрозуміти часом зовсім неможливо. Але таки хочеться. На честь Дня Незалежності України редакція dev.ua вирішила провести невеликий експеримент.
Ми задали чотирьом різним нейронним мережам п’ять однакових запитів: «прапор України», «День Незалежності України», «український Крим», «перемога України» та «українці». Отриманими результатами ми ділимося з вами нижче.
У TikTok тепер можна генерувати фон за допомогою нейромережі. Ми протестували її та ділимося результатами
У TikTok з’явилася нова функція «Розумний фон». З її допомогою як фон для тіктоків можна підставляти згенеровані нейромережею зображення. Редакція dev.ua протестувала цю технологію і ділиться своїми враженнями.