Optimization of Backpropagation Method with PSO to Improve Prediction of Land Area and Rice Productivity

This research aims to optimize the Backpropagation method using Particle Swarm Optimization (PSO) optimization to improve the accuracy of prediction of harvest area and rice productivity. The results show that the best architecture for prediction of harvest area is 3-15-1, with a Mean Squared Error (MSE) value of 0.0049980 for standard Backpropagation, and 0.00092376 after being optimized with PSO. Meanwhile, for rice productivity prediction, the best architecture is also 3-15-1, with an MSE value of 0.0049998 for standard Backpropagation, and 0.000435762 after using PSO. PSO optimization significantly reduces the MSE value, which indicates that this method is more accurate than standard Backpropagation. Predictions from 2024 to 2026 show more consistent results with some provinces experiencing an increase or decrease in harvested area and rice productivity that is different from the standard Backpropagation method. Based on the prediction accuracy that reaches 100% and the lower MSE value, it can be concluded that Backpropagation with PSO optimization is a superior method. The results of this study are useful for government, farmers, researchers, and policy makers in more effective agricultural planning and better risk management