III MIPT and GeoDelta: AI platform for climate analysis

The main articles are:

• Big Data
• Data mining Data mining

2025: Development of an AI platform for climate analysis

On November 17, 2025, the Institute of Artificial Intelligence MIPT and GeoDelta presented a jointly developed AI platform for climate analysis, which turns a rough weather forecast into a detailed map of climate risks with a resolution of up to several meters. This will help public utilities anticipate the threat of a weather emergency, designers - the impact of buildings on the microclimate of the district, and citizens - health risks.

𝓲

Фото: MIPT

As reported, the usual weather forecasts usually describe the situation on a scale of tens of kilometers, while inside the city the conditions change from street to street. In the center of the metropolis, the air is often 10 degrees or more warmer than on the outskirts, and the geometry of streets and dense buildings forms "heat traps" and "street canyons" of wind, noticeably changing the local microclimate. All this increases the peak load on the power system and can overload city services - from storm sewers to public transport.

The AI platform for climate analysis, which was developed by scientists from the Institute of Artificial Intelligence of the Moscow Institute of Physics and Technology and GeoDelta, will help to avoid these problems. It is based on downscaling technology: algorithms analyze the general forecast for the city and "land" it to the streets, filling it with real data from city cameras, weather stations, sensors and metering devices.

If standard models predict the weather for sections in increments of 25-30 kilometers, Geo Delta narrows it to 30-50 meters - within one house.

The AI platform does not just transmit data, but constantly analyzes how and why atmospheric processes occurred at a specific point with known parameters (high-rise buildings, asphalt, green zones). She uses the accumulated relationships to further increase the accuracy of forecasts.

For example, our system will be able to predict that the wind in a narrow lane between skyscrapers in this direction will triple, and in one of the areas, due to the "heat island" effect, the temperature will be 10 degrees higher than in the park around the corner. told Denis Lobas, Head of Industrial Products, Institute of Artificial Intelligence, MIPT

The platform visualizes threats on an interactive map and gives services a convenient tool for real-time monitoring.

So developers can assess in advance how the architecture of new buildings will affect the climate of a particular area, utilities - not just respond to emergencies, but anticipate them, and residents of the area - receive personal warnings about heat, rain or strong winds.