The study is aimed at estimating and forecasting the transfer coefficient of radionuclides from soil to agricultural plants based on the real data collected in the areas affece by the Chornobyl disaster. The model was developed using a dynamic Bayesian network, which is an element of novelty, since the use of this tool for radio-ecological modelling was not previously carried out. The problem considered in this study is of a high priority, since the human body internal exposure is mainly caused by the presence of contaminated plants on the lower level of the food chain, and mathematical modeling of the process is not common in general. The factors affecting the radionuclide transfer coefficient were analyzed, and the dependencies transfer level change were identified, depending on the humidity, acidity, soil type, depth of the root system, the content of K + and 2Ca +. Dynamic approach allows tracking changes of plant contamination over 80 months with a time step equal to 1 month. Junction tree algorithm was used for inference, as the network consists both of continuous and discrete nodes. The results obtained demonstrate the high accuracy in accordance with general criteria: the standard deviation does not exceed , mean absolute percentage error does not exceed 5% for all measurements, the variance is close to zero, that justifies the use of dynamic Bayesian network to solve this problem. Also the possibility of this approach usage while solving problems of the same calss in general was considered. The model allows creating long-term scenarios to identify the possible ways of agriculture development over the areas affected by the Chornobyl disaster and similar anthropogene disasters.