Title: Development of a Rule-Based Expert System for Potato Disease Diagnosis and Treatment Using CLIPS
Authors: Lena Hatem Al-Zaharna
Samy S. Abu-Naser
Volume: 10
Issue: 7
Pages: 130-139
Publication Date: 2026/07/28
Abstract:
Potato is one of the world's most economically important food crops; however, its productivity is frequently threatened by a wide range of diseases that adversely affect both yield and quality. Accurate and timely diagnosis, followed by appropriate treatment, is essential for effective disease management and sustainable agricultural production. This paper presents the design and implementation of a rule-based expert system for the diagnosis and treatment of common potato diseases using the CLIPS expert system shell integrated with the Delphi programming environment. The system's knowledge base was developed in collaboration with agricultural experts and represented as production rules that model expert reasoning. The proposed system covers eleven of the most common potato diseases and conducts an interactive consultation by analyzing user-reported symptoms to identify the most probable disease. Once a diagnosis is established, the system provides appropriate treatment recommendations together with disease management and prevention guidelines. The developed expert system was evaluated by agricultural engineers, experienced farmers, and agriculture teachers to assess its diagnostic accuracy, usability, and overall effectiveness. The evaluation demonstrated that the system provides accurate, consistent, and timely diagnostic recommendations while offering an intuitive user interface suitable for users with different levels of agricultural expertise. The proposed expert system represents an effective decision-support tool that can assist farmers, agricultural extension specialists, educators, and students in improving disease diagnosis, supporting timely intervention, and reducing crop losses. Furthermore, the system illustrates the continued applicability of rule-based artificial intelligence techniques for agricultural decision support in domains where expert knowledge can be explicitly represented and efficiently utilized.