Group Method of Data Handling-Type Neural Network Prediction of Hazelnut Leaf Area Based On Length and Width of Leaf

Artificial neural network have been shown to be powerful tools for system modeling. One sub model of artificial neural network is the group method of data handling-type neural network (GMDH -type NN). The use of such self -organizing network leads to successful application in abroad range of areas. However, in some fields, such as horticultural science, the use of GMDH-type NN is still scare. Accurate and nondestructive methods to determine individual leaf areas of plants are a useful tool in physiological and agronomic research. Determining the individual leaf area (LA) of hazelnuts (Corylus avellana) involves measurements of leaf parameters including: length (L) and width (W) parameters. In this way, a genetic algorithm is deployed in a new approach to design the whole architecture of the GMDH-type NN. This study addressed the question of whether GMDH-type NN could be used to estimate leaf area (outputs) based on specified variables inputs (leaf with, leaf length). Results suggest that GMDH-type NN provide an effective means of efficiently recognizing the patterns in data and accurately predicting a performance index based on investigating inputs, and also can be used to prediction leaf area based on leaf width, leaf length factors.

Keywords:

Corylus avellana , Leaf area , Leaf width , Leaf length , Modeling , Neural network.