In Ukraine, among leguminous crops, pea occupies one of the leading places. Modeling as an integral part of yield programming involves the development of a forecast, i.e. a probable idea of the theoretically possible yield, which is provided by various agrobiological indicators. One of the main conditions for increasing the efficiency of production and increasing the gross harvest of green pea is the development and implementation of the latest techniques to increase its productivity in

more »

... ural practice, which is an important and urgent problem. A highly effective modern tool for mathematical modeling, forecasting, situation recognition and decision support are Bayesian networks (BN), which have a number of advantages over other modeling methods. The goal of the research is to study the possibilities of using the apparatus of Bayesian networks to build an information system for decision support (DSS) to model the yield of green pea. Research methods. The paper considers the possibility of using Bayesian networks in the information DSS in planning the yield of green pea at an agricultural enterprise. BNs provide the opportunity to take into account in one model of categorical and ordinary numerical variables, the number of variables reaching several hundred, the availability of alternative methods of forming a probabilistic inference and the correct representation of causal relationships. The main results of the research. The BN apparatus allows combining the available statistical data on agrobiological characteristics of agricultural products in addition to the expert information provided by farmers. The use of DSS based on BN will allow farmers to make decisions under uncertainty of available information about the agrobiological characteristics of growing green pea. Scientific novelty. BN is a powerful and effective mathematical tool for research and reproduction of the truthful overview of processes in DSS, which should be used to solve problems of probabilistic forecasting, modeling and risk assessment in yield planning. Practical relevance. For practical confirmation of the obtained results, an experiment was conducted, the results of which confirmed the practical value of the proposed information technology, which can be used to model the green pea yield. The proposed structure of the database and DSS based on it, will support making of effective decisions on the organization of the harvesting campaign for green pea in different technological and weather conditions.