6th International Conference on Trends in Agricultural Engineering (TAE), Prague, Czech Republic, 7 - 09 September 2016, pp.658-665
Soil compaction is a major problem affecting negatively the soil physical, chemical and biological properties and impedes plant root growth. Soil penetration resistance values should be collected from many points of the production area to determine the effects of these problems on plant growth. Soil penetration value collection from large production areas is time-consuming and tedious application for researchers. Also, the number of measurement points to what extent will be sufficient to evaluation on whole production area is not clear. To eliminate this ambiguity, soil penetration values of the unmeasured points should be estimated to evaluate the whole area. Artificial neural networks are one of the most popular mathematical computing and modelling method used to estimate unknown data values with known data values. In this study, we collected 1603 samples of geographical position and soil penetration value from 40 cm depth within the 20 ha field. From the 1603 values, 24% records were selected for testing and the remaining 76% records were used for educating and validating. Soil penetration values of the unmeasured points were estimated using Generalized Regression Neural Network (GRNN) method in Matlab. In addition to mean squared error (MSE), root mean square error (RMSE), mean absolute error (MAE) and R-2 has been also used for evaluation of prediction accuracy on GRNN method. The results showed very good agreement between the predicted and the measured real values of soil penetration resistance.