There are some studies regarding the prediction of agricultural energy flows using Artificial Neural Networks (ANNs). These models are quite sensitive to correlations amongst inputs. And, there are often strong correlations amongst energy inputs for agricultural systems. One potential method to remediate this problem is to use Principal Component Analysis (PCA). Therefore, the purpose of this research was to predict energy flows for an example agricultural system (Iranian tea production) via a novel methodology based on ANNs, using principal components as model inputs, not raw data. PCA results showed that the first and second components could account for more than 99% of variation in the data, thus the dimensions of the data set could be decreased from six to two for the prediction of energy flows for Iranian tea production. Using these principal components as inputs, an ANN model with 2-15-1 structure was determined to be optimal for energy flow modeling of this system. Results from this optimal model demonstrated that the difference between actual and predicted amounts of energy was not significant at the 1.0% level. Ultimately, these results indicate that a PC+ANN model could be used to reliably predict this agricultural system. To conclude, the results of this study highlighted that the use of PC as ANN inputs improved ANN model prediction through reducing its complexity and eliminating data colinearity. Many agricultural systems could benefit from using this methodology for modeling.

Keywords