Agricultural Planting Optimization Strategy Based on Genetic Algorithm and Monte Carlo Algorithm

Abstract

Under the rural revitalization strategy and agricultural modernization, this study addresses the challenges of limited and diverse cultivated land resources in rural areas, aiming to scientifically allocate crop and land resources, optimize planting plans, and promote sustainable rural economic growth. Despite ongoing improvements, current planting plans often overlook critical factors such as crop diversity, land types, and climate impacts. This research explores how to allocate crop and land resources effectively under constraints like crop rotation, avoiding repeated planting, and land area limitations, to maximize income over the next seven years. Land is categorized into two groups: dry flat land, mountainous land, and sloping land in one group, and irrigated land, ordinary greenhouses, and smart greenhouses in another. Decision variables are set as crop planting areas, weighted by quarterly profit per acre, while constraints include planting legumes at least once every three years, total planting area limits, and avoiding the same crop for two consecutive years. A 0-1 integer programming model and value matrix are introduced, and to tackle overproduction and waste, a Monte Carlo algorithm and genetic algorithm are implemented in Python to maximize total revenue, deriving the optimal planting plan and projected annual sales. In the first scenario, the total profit for the next seven years is approximately three million five hundred thousand dollars.