IDAO 2020: Online stage

The Online Stage of International Data Analysis Olympiad (IDAO 2020) has finished. IDAO 2020 is a traditional machine learning contest organized on the Yandex.Contest platform.

It is organized for the 3rd time and this year it brings 2756 participants from 83 countries.

Based on the Online Round results, 86 participants qualifies to the Final – 31 teams from 13 countries. They will be joined by 3 more teams – IDAO 2019 winners and prize holders. This year there are more experts from industry among finalists – 48 participants.

The goal of the online stage was to build a model that predicts the position of space objects using simulation data. The task was developed by the Laboratory of Methods for Big Data Analysis and one of the partners of the Olympiad – the Russian Astronomical Science Center (ASC). ASC is engaged in the creation and operation of automated optoelectronic systems for observing space objects and automated systems for processing information about space objects. This problem has special relevance to them. For example, maintaining the Catalog of Earth Satellite Orbits requires repeated observations of space objects. To do such observations, it is necessary to know where to target the telescopes. Predicting the position of satellites is one of the most important tasks in astronomy. For example, information on the exact position of satellites in orbit is necessary to avoid extremely dangerous satellite collisions. Each collision leads not only to satellites destruction, but also results in thousands of space debris pieces. For instance, Iridium-Coscos collision in 2009 increased number of space debris by approximately 13%. Further collisions may result in Kessler syndrome and the inaccessibility of outer space. Also, a more accurate prediction of satellite position will help calculate more efficient maneuvers to save propellant and extend satellite life in orbit. At the same time, it is difficult to predict the exact position of a space object, since the form and other parameters might be unknown. Furthermore, mathematical-physical models cannot fully take into account many factors, such as the Earth’s Surface Roughness and Solar pressure.

The Final will be held in Moscow on April 2020 at the central headquarters of Yandex, where participants will have 36 hours to define the winners. The task for the Final Stage will be provided by our platinum partner – QIWI Group.