Optimised Decision Making Method Based on D-MOPSO Algorithm

The effective utilization of farmland resources and the promotion of organic agriculture tailored to local conditions are of critical importance to the sustainable growth of rural economies. In this paper, a crop planting decisionmaking method based on the Dynamic Multi-Objective Particle Swarm Optimization (D-MOPSO) algorithm is proposed. Key factors influencing crop planting, including sales volume, planting costs, per-acre yield, and price fluctuations, are first analyzed. Through Monte Carlo simulations, multiple future scenarios are generated to determine optimal planting strategies that maximize profits and minimize risks. Constraints related to crop substitutability and complementarity are constructed, in conjunction with land resources, crop rotation requirements, and inter-crop correlations, to scientifically plan planting schemes. Ultimately, the model employs the D-MOPSO algorithm to generate a set of Pareto-optimal solutions, balancing profit maximization and risk minimization. By simulating fluctuations in crop prices, sales, and costs over the next seven years, different planting strategy recommendations are provided. These include increasing the proportion of legume crops to reduce risk, decreasing the area allocated to high-pricevolatility crops such as mushrooms, and adjusting vegetable planting ratios to accommodate market uncertainties. This method provides a scientific basis for rural revitalization strategies, supporting efficient and sustainable agricultural development.