Author(s)

Xin Guo

Corresponding Author

Xin Guo

Abstract

Under the challenges of global population growth and climate change, modern agriculture is under increasing pressure, and intelligent and sustainable management methods are urgently needed to balance the growth of food demand and environmental protection. Based on the actual planting of cultivated land and the growth law of crops in specific regions, this paper formulates the optimal planting strategy for crops in the next few years. First, data preprocessing is carried out to estimate the unit price of crop sales and analyze the relationship between planting area and total sales; secondly, single-objective optimization analysis is carried out based on historical data, an optimization model is constructed, and a genetic algorithm is used to solve it, giving the optimal planting strategy for 2024-2030 to maximize agricultural benefits when the expected sales volume is stable. Then, a single sensitivity analysis is used to find out the key variables affecting planting benefits and their expected change rates; then a multi-sensitivity analysis is used to calculate the planting data of crops in each year within a specific floating range, and a Monte Carlo simulation is used to evaluate the comprehensive impact of uncertain parameters; finally, the obtained parameter values are used to simulate the planting strategy model to obtain the optimal planting plan for 2024-2030. In addition, assuming that sales volume is linearly related to variables such as average sales price and planting cost, the sales volume of different crops is predicted based on the linear regression model. The correlation coefficient analysis shows that the sales price is negatively correlated with sales volume, and the planting area is positively correlated with sales volume. The optimal planting plan is obtained with the help of the prediction model and compared with the above plan. The results show that the total profit fluctuates greatly from 2024 to 2030, which is speculated to be related to the parameter selection.

Keywords

Goal Programming, Genetic Algorithm, Monte Carlo Simulation Algorithm, Correlation Analysis