Optimization allocation strategy of agricultural production resources based on SSA-BP algorithm.

Area of Science:

• Agricultural Science
• Artificial Intelligence
• Optimization Theory

Background:

• Inefficient agricultural resource allocation leads to reduced yields and ecological impact.
• Climate change and diminishing arable land necessitate optimized resource management for sustainable agriculture.
• Balancing crop yield maximization with ecological benefits presents a critical challenge for modern farming.

Purpose of the Study:

• To develop a hybrid optimization model for enhancing agricultural resource allocation and crop yields.
• To address limitations of traditional methods, such as local optima and slow convergence.
• To provide tools for intelligent agricultural management, supporting real-time decision-making and climate adaptation.

Main Methods:

• A hybrid model combining Sparrow Search Algorithm (SSA) for global exploration and Back-propagation Neural Network (BP) for nonlinear fitting.
• SSA simulates sparrow foraging and alert behaviors to optimize resource allocation.
• Differential evolution strategy integrated into SSA to improve model robustness.

Main Results:

• The hybrid model achieved an average fitness of 3 within 8 iterations.
• Accuracy in yield prediction exceeded 98.5% with 2 hidden layer nodes.
• A resource cost-output ratio above 1.15 demonstrated cost-effectiveness.

Conclusions:

• The proposed SSA-BP hybrid model effectively optimizes agricultural resource allocation for improved crop yields and ecological benefits.
• The model offers real-time decision-making capabilities for intelligent agricultural platforms, aiding resource scheduling and climate adaptation.
• Enhanced resource utilization through real-time adjustments of water and fertilizer ratios contributes to dual economic and ecological gains.