Exploration of Crop Planting Strategies Based on Monte Carlo Simulation and D-MOPSO

The aim of this paper is to explore the crop planting strategy based on Monte Carlo simulation with Dynamic Multi-Objective Particle Swarm Optimization algorithm (D-MOPSO). By building a comprehensive optimization model, an effective solution for agricultural production planting planning is provided under the consideration of various economic indicator factors of crop cultivation. In this paper, Monte Carlo simulation is firstly applied to generate multiple future scenarios and introduce stochastic variables in order to solve the optimal planting plan that maximizes the return and minimizes the risk. A Robust Non-Dominated Sorting Genetic Algorithm (Robust NSGA-II) is used for model solving to ensure a robust planting strategy in the face of market fluctuations. Correlation analysis and Kmeans clustering were used to further optimize the substitutability and complementarity between crops to enhance the overall planting efficiency.