This paper is devoted to the development of information systems for precision farming, which make it possible to use fertilizer and fuel more efficiently on the basis of information technologies and intelligent predictive models, which reduces the cost of production and increases the efficiency of agricultural production. In addition, a long-term agronomic and ecological effect can be achieved due to more careful tillage and reduced use of nitrogen fertilizers. Description of the creating a knowledge base and models of grain yield depending on the mode of mineral fertilizer application based on intelligent associative search algorithms describes.