Crop planting strategy by robust particle swarm optimized-algorithm

Abstract

With the rapid transformation of rural economies, optimizing crop planting structures has become a key strategy to address limited resources, market volatility, and environmental risks. This issue is especially critical in the mountainous regions of North China, where arable land is scarce and topographic constraints pose serious challenges to traditional agriculture. This study develops a multi-objective mathematical model that comprehensively considers key uncertain factors, including yield per mu, planting costs, and sales volume. By integrating Particle Swarm Optimization (PSO) with Robust Optimization techniques, the model identifies an optimal crop planting scheme for the period 2025–2030. The proposed solution remains stable under uncertainty and meets practical requirements for adaptability and feasibility. The results provide valuable theoretical and decision-making support for improving land use efficiency, reducing planting risks, and promoting sustainable agricultural development in resource-constrained mountainous areas. This research offers practical guidance for policymakers and agricultural planners seeking data-driven strategies in the context of rural economic transformation.