<![CDATA[Rice production is a critical component in sustaining national food security, especially Indonesia. The availability of sufficient, affordable, and equitable food is a major challenge for Indonesia. One approach to addressing this challenge is by developing reliable and accurate models for predicting food production. In this study, a hybrid approach that combines Artificial Neural Network (ANN) and Particle Swarm Optimization (PSO) algorithms is used to optimize the performance of modeling and prediction of rice production in Central Java, Indonesia. This study uses secondary data in the form of monthly time series data from the Central Java Provincial Statistics Agency (BPS), Meteorology, Climatology, and Geophysics Agency (BMKG), and satellite imagery data with an observation period from January 2019 to December 2024. The input variables in this study include harvested area, precipitation, number of rainy days, atmospheric pressure, wind speed, NDWI, and NDVI while the output variable is rice production in Central Java. The test results using the ANN model provided an RMSE value of 0.1312 and a MSE of 0.0172, while the ANN-PSO model provided an RMSE value of 0.0259 and a MSE of 0.00067. These results indicate that the PSO algorithm is able to optimize the performance of the ANN model in predicting rice production in Central Java. ]]>
Copyrights © 2026
