Sugarcane (Saccharum officinarum L) is an industrial crop with high economic value due to its glucose-rich stalks, making it widely cultivated for sugar production. However, in recent years, sugar production has declined while sugar consumption continues to rise. One of the factors affecting the quality and production of sugarcane is disease, which has caused significant losses for both farmers and the sugar processing industry. This study develops an expert system for identifying sugarcane diseases using the Naïve Bayes method to address this issue. The aim of this research is to detect disease types based on observed symptoms and provide information on possible solutions using an expert system. The Naïve Bayes method was chosen for its ability to process data independently and efficiently. Based on testing with 15 test datasets, the expert system achieved an accuracy rate of 87%, demonstrating its reliable performance. Functional testing using the Black Box method showed a system success rate of 100%. This Naïve Bayes-based expert system is expected to be an effective solution for improving the efficiency of sugarcane disease identification, reducing losses caused by diseases, and supporting increased sugar production in the future.