Expert System Design for Rice Disease Diagnosis Based on Forward Chaining and Certainty Factor in Mauliru Village

Abstract

As a staple food in Indonesia, rice is a critical agricultural commodity that supports the basic needs of the population. In Mauliru Village of East Sumba Regency, rice cultivation serves as the primary source of livelihood for the local community. However, farmers face major challenges from diseases such as bacterial leaf blight, blast, and brown spot, which can significantly reduce yields. Limited access to agricultural experts hampers early diagnosis, often leading to delayed and ineffective treatment. To address these issues, this study developed an expert system for diagnosing rice plant diseases using forward chaining and certainty factor methods. The system employs a rule-based reasoning approach and was evaluated through black-box testing on 10 case scenarios. Data were gathered through field observations, interviews, and documentation, with validation from agricultural experts. The results showed that the system achieved an accuracy rate of 80 % and provided confidence values for each diagnosis. This expert system is expected to assist farmers in making timely and accurate decisions, thereby improving productivity and reducing the risk of crop failure.