Author(s)

Guifang Guo

Corresponding Author

Guifang Guo

Abstract

This paper presents a comprehensive strategy for optimizing crop planting decisions based on Integer Linear Programming (ILP) models and Monte Carlo Simulation (MCS) algorithms. The study begins with data preprocessing, which involves calculating the average selling prices of various crops and determining the expected sales volumes using characteristic equations. Considering land-type constraints, crop rotation requirements, and planting dispersion constraints, an ILP model is formulated to maximize farming profits over the period from 2024 to 2030. To address the uncertainties associated with input parameters, a dynamic stochastic agricultural planning model is developed. This model employs state variables to capture the dynamic changes in prices, yields, costs, and market demands. By integrating dynamic programming with MCS, multiple iterations are conducted to handle these uncertainties. The results are visualized through heatmaps, depicting the dynamic trends of planting acreage and profits for different crops.

Keywords

Integer Linear Programming, Monte Carlo Simulation, Dynamic stochastic agricultural planning model