This study proposes an integrated constrained static optimization framework for optimizing crop-planting strategies in rural regions under uncertainty. Unlike conventional deterministic or dynamic programming approaches, the proposed model formalizes the decision process as a static multi-objective optimization problem that simultaneously maximizes economic profit and minimizes production risk. The framework integrates three complementary algorithms–Particle Swarm Optimization (PSO) for global exploration, Simulated Annealing (SA) for local refinement, and Monte Carlo Simulation (MCS) for stochastic robustness evaluation. A real-world case study based on empirical agricultural data from northern Anhui Province (2022–2024) provides empirical evidence of the framework’s potential effectiveness, showing that the hybrid PSO–SA–MCS model increases the expected profit by 12.6% and reduces yield variance by 11.0% compared with the baseline PSO. Convergence and sensitivity analyses confirm stable performance across parameter variations within ±10%. The proposed framework enhances the transparency, reproducibility, and robustness of agricultural decision-making, providing a practical tool for data-driven, sustainable crop planning and resource allocation in rural development. Moreover, the proposed PSO–SA–MCS framework is not limited to the specific study region or crop categories considered in this paper. By adjusting land-use data, yield coefficients, and market parameters, the model can be readily extended to other regions, cropping systems, and agricultural planning scenarios, indicating potential generalizability and scalability, subject to further validation under different regional and agricultural settings.
Dayou et al. (Sat,) studied this question.