<![CDATA[This study discusses the application of the Fuzzy Inference System method to predict rice yields in Magelang City as an effort to support food security planning. The data used included harvest area, production, and productivity with the period 2021–2022 as training data and 2023–2024 as test data. The prediction process is carried out through the stages of fuzzification, formation of fuzzy rules, inference using min–max operators, and defuzzification using the centroid method. The prediction system is designed to be web-based so that it can be used by farmers, government agencies, and related parties in decision-making. The results of the study show that the Fuzzy Mamdani method is able to produce predictions that are close to actual data with a low error rate. For example, the prediction of 109.20 tons in a harvest area of 18 Ha is close to the actual data of 106.56 tons, and an RMSE value of 1.43 tons is obtained which is better than the seasonal naïve and linear regression methods. With stable accuracy and flexibility in updating regulations, this system is suitable for use as an agricultural planning tool, especially for food distribution strategies, planting planning, and rice stock management in Magelang City.]]>
Copyrights © 2026
