Wheat Cultivation Suitability Evaluation with Stripe Rust Disease: An Agricultural Group Consensus Framework Based on...

Area of Science:

• Agricultural Science
• Computational Biology
• Plant Pathology

Background:

• Plant modeling is crucial for precision agriculture, aiding crop monitoring and resource management.
• Wheat stripe rust poses a significant threat to global food security by reducing yield stability.
• Current methods for assessing stripe rust severity are challenged by limited regional data and inconsistent expert evaluations.

Purpose of the Study:

• To develop a framework for evaluating wheat cultivation suitability considering stripe rust disease.
• To address the multi-attribute, multi-decision-maker consensus problem in disease severity assessment.
• To enhance participation and consensus among wheat pathologists using artificial intelligence.

Main Methods:

• Utilized artificial-intelligence-generated content (AIGC) with Claude 3.7 for simulating expert scoring via role-playing and chain-of-thought prompting.
• Employed a graph neural network (GNN) for trust propagation and expert weighting within social networks.
• Integrated secretary bird optimization (SBO), K-means, and three-way clustering for subgroup detection and opinion divergence reduction.
• Implemented a two-stage optimization to balance group fairness and adjustment costs for practical consensus.

Main Results:

• The proposed wheat cultivation suitability evaluation with stripe rust disease (WCSE-AGC) framework effectively models expert trust and identifies subgroups.
• The integration of optimization techniques improved consensus inclusiveness, convergence, and practicality.
• Experimental validation on real-world datasets from Ethiopia, India, Turkey, and China demonstrated the framework's effectiveness and robustness.

Conclusions:

• The WCSE-AGC framework offers a robust solution for evaluating wheat cultivation suitability under stripe rust pressure.
• AIGC techniques can successfully simulate expert judgment, overcoming limitations in expert availability and consistency.
• The study enhances precision agriculture strategies by providing a more reliable method for disease-related risk assessment and management.