Predictions on the time needed to adopt new technologies can be used for planning purposes. These predictions should be calculated using a Markov planning model, which is a probabilistic approach to estimating the speed of adoption. In a research project, a data-driven model was developed to simulate the adoption rate of an enhanced, drought-resistant rain-fed hard wheat (Triticum aestivum L.) cultivar in Kurdistan, Iran. The growers’ decision-making on cultivar replacement was mapped onto the transition matrix, state probability, transition diagram, and tree of the states of the Markov process to compute the limiting probability of the stochastic model, thereby simulating the adoption rate of the wheat cultivar. The mathematical model, which achieves a convergence of 82% adoption for the enhanced wheat cultivar within five years, simulates farmers' behavior and knowledge to enhance food security. Simulating the future of new technology in food and agricultural systems using the proposed methodology can assist policymakers in making informed decisions.
