The article presents an approach to the creation of information systems for digital farming, which allows more rational planning of land use, the use of fertilizers and fuel based on information technologies and intelligent forecasting models, which reduces the cost of production and increases the efficiency of agricultural production. In addition, a long-term agronomic and environmental effect can be achieved due to more gentle tillage and a decrease in the use of nitrogen fertilizers. The principles of creating a knowledge base and constructing models of grain yield depending on the regime of applying fertilizers based on intelligent identification algorithms, as well as models for predicting prices for digital agriculture products, have been developed.