Rosneft held a computer vision hackathon

Translation. Region: Russian Federation –

Source: Rosneft – An important disclaimer is at the bottom of this article.

Rosneft's Ufa Research Institute held a Student Hackathon, bringing together over 340 participants from 45 Russian cities. The competition was held online as part of the Company's IT Marathon.

The teams had 48 hours to develop a computer vision model that could automatically highlight areas on a map with different oil well placement patterns. The challenge was to find a solution that would allow for the most accurate contouring of the desired segments. Knowledge of the Python programming language was required to complete the task correctly.

The authors of the top 10 solutions presented their projects to the hackathon jury. The prizes were awarded as follows:

1st place and 200,000 rubles went to the RebootingMSU team (Moscow State University, Moscow); 2nd place and 150,000 rubles went to the Lando team (Central University, Moscow); 3rd place and 100,000 rubles went to the ITMOOOOONSTERKILL team (ITMO, Moscow).

The victory in the special nomination and 50,000 rubles were awarded to the Skaldfire team (Moscow, Moscow Technical University of Communications and Informatics).

The hackathon participants' best ideas will be incorporated into an updated version of the RN-KIN software, which contains information on most of the Company's fields. Implementation of the new model will enable the achievement of maximum oil recovery rates during the development of new deposits.

In 2025, the Rosneft IT Marathon will include four competitions: the Student Hackathon, the Academic Tournament, the Geosteering League, the Additive Technologies and Reverse Engineering Cup, and information modeling competitions for the Company's employees. The winners and runners-up of all IT competitions will meet in December at the finals in Moscow.

Department of Information and Advertising of PJSC NK RosneftNovember 20, 2025

Please note: This information is raw content obtained directly from the source. It represents an accurate account of the source's assertions and does not necessarily reflect the position of MIL-OSI or its clients.