Prediction of annual coffee production yield using artificial neural network and multiple linear regression techniques

Crop yield and its prediction are crucial in agriculture production planning. This study investigates and analyzes annual coffee yield prediction in order to match the market demand, using artificial neural networks and multiple linear regression. Data were collected for six variables, including areas, productivity zones, rainfalls, relative humidity, and minimum and maximum temperature. The predicted yield of the cherry coffee crop continuously increases each year. It was found that the prediction accuracy of the R 2 and RMSE were 0.9524 and 0.0642, respectively. The multiple linear regression showed potential in determining the relationship of cherry coffee yield.