(60z) Prediction of Slow Release Fertilizer Kcl with Vermicompost By Using Artificial Neural Networks

Slow Release fertilizers (SRF) are currently the most popular and offer great advantages over conventional fertilizers. To understand the release rate, a generalized regression neural network was used to predict KCL release profiles. A total of 56 samples were used for the experiment, and KCL release profiles in water were obtained to train the Neural Network model. Input vectors of the model were controlled-release parameters, diameter of the pellet, weight of the pellet and output vectors of the model were KCL release profiles. The results showed that the predicted values were in fairly good agreement with the observed ones, and the performance of the Neural Network model was superior to a theoretical model in controlling KCL release. The Neural Network model was a useful tool in solving non-linear prediction problems in the development of SRF, and the KCL release profile could be optimized with Neural Network by adjusting slow release parameters, which provides an alternative method to obtain the SRF characteristics.