A Taxonomy of Food Supply Chain Problems from a Computational Intelligence Perspective

Area of Science:

• Agricultural Science
• Computer Science
• Supply Chain Management

Background:

• Digitalization of Food Supply Chains (FSC) using technologies like the Internet of Things generates vast data.
• Analyzing this complex data for efficiency and sustainability is challenging for human experts.
• Existing literature often focuses on specific Computational Intelligence (CI) methods or FSC stages, leaving a gap in comprehensive classification.

Purpose of the Study:

• To present a comprehensive taxonomy of FSC problems from a Computational Intelligence (CI) perspective.
• To categorize FSC problems based on their CI modeling approaches across all stages (production to retail).
• To review common CI methods applied to different FSC stages and problem categories.

Main Methods:

• Development of a novel taxonomy for classifying Food Supply Chain (FSC) problems.
• Categorization of problems based on Computational Intelligence (CI) modeling.
• Review of existing CI approaches applied to various FSC stages and problem types.

Main Results:

• A new, comprehensive taxonomy classifying FSC problems from a CI viewpoint.
• Identification of suitable CI methods for different FSC stages and problem categories.
• A review of CI applications across agriculture, fish farming, and livestock supply chains.

Conclusions:

• The proposed taxonomy aids researchers and practitioners in selecting appropriate CI methods for FSC challenges.
• Identifies research gaps and opportunities to enhance CI's contribution to digitized FSC.
• Highlights the potential of CI for improving efficiency and sustainability in food supply systems.