OREANDA-NEWS  Artificial intelligence will allow you to quickly select the components of the optimal concrete mix for the construction of facilities in regions with extreme climate. A special machine learning model was developed by employees of the Siberian Federal University. The model is able to make recipes for the best concrete samples for certain conditions. She knows what ingredients should be added to the cement so that the mixture is best suited for the construction of buildings in the Far North or, for example, in Africa, on saline soils or in another aggressive environment.

To build this model, scientists used more than four dozen types of concrete of different composition, quality and origin. The recipes of the mixture obtained by the staff of SFU together with artificial intelligence contain more than a dozen varieties of mineral and chemical additives.

- One of the main advantages of the development is the accurate prediction of the properties of the compositions proposed by it and their adaptability to specific weather and climatic conditions, - the university said.