<![CDATA[Prediction is a process for estimating how many needs will be in the future. This study aims to predict the amount of rice production by province. The role of the agricultural sector in the national economy is very important and strategic. The rice plant (Oryza sativa L.) is an important food crop which is a staple food for more than half of the world's population because it contains nutrients that the body needs. Domestic production made the government still carry out the food import policy even though a number of regions claimed to have surplus rice production. This causes a lot of the country's foreign exchange to be used because of the operational costs of rice imports. By using Artificial Neural Networks and backpropagation algorithms, an architectural model will be sought to predict the amount of rice production by province in order to determine the steps to meet domestic rice demand based on the amount of rice consumption of the community. This study uses 6 input variables, namely data from 2010 to 2016 with 1 target, the data of 2017. Using 5 architectural models to test the data to be used for prediction, namely the 6-4-1 model, 6-8-1 , 6-16-1, 6-2-3-1 and 6-3-2-1. Obtained the results of the best architectural model is 6-8-1 architectural model with truth accuracy of 100%, the number of epochs 145 and MSE is 0.010250963.]]>
Copyrights © 2018
