-

For a decrease of agricultural crop losses, it is essential to estimate of paddy layers´ moisture content at the end of a drying process. In this study, intelligent method of artificial neural network was employed to predict paddy layers´ moisture content in a range of final moisture contents of 10 to 14% (w.b.). Drying experiments were carried out with the paddy samples at an initial moisture content of 18.7 to 20.5% (w.b.) and at a depth of 5 to 30 cm. A controlled environment temperature of 43°C was applied in all the experiments. Moisture content of paddy layers were predicted through three parameters of: average moisture content of paddy, layer depth, and total depth of paddy drying in each experiment. Application of two methods of multi layer perceptron network and radial basis function network revealed that the artificial neural network can estimate each layer of paddy moisture content with a coefficient of determination of over 99% thus with a negligible error.