Artificial Neural Network Methodology for Modelling and Forecasting Maize Crop Yield Reportar como inadecuado

Artificial Neural Network Methodology for Modelling and Forecasting Maize Crop Yield - Descarga este documento en PDF. Documentación en PDF para descargar gratis. Disponible también para leer online.

A particular type of “Artificial neural network (ANN)”, viz. Multilayered feedforward artificial neuralnetwork (MLFANN) has been described. To train such a network, two types of learning algorithms,namely Gradient descent algorithm (GDA) and Conjugate gradient descent algorithm (CGDA), havebeen discussed. The methodology has been illustrated by considering maize crop yield data as responsevariable and total human labour, farm power, fertilizer consumption, and pesticide consumption aspredictors. The data have been taken from a recently concluded National Agricultural TechnologyProject of Division of Agricultural Economics, I.A.R.I., New Delhi. To train the neural network,relevant computer programs have been written in MATLAB software package using Neural networktoolbox. It has been found that a three-layered MLFANN with (11,16) units in the two hidden layersperforms best in terms of having minimum mean square errors (MSE) for training, validation, and testsets. Superiority of this MLFANN over multiple linear regression (MLR) analysis has also beendemonstrated for the maize data considered in the study. It is hoped that, in future, research workerswould start applying not only MLFANN but also some of the other more advanced ANN models, like‘Radial basis function neural network’, and ‘Generalized regression neural network’ in their studies.

Subject(s): Crop Production/Industries

Issue Date: 2008

Publication Type: Journal Article

PURL Identifier: Published in: Agricultural Economics Research Review, Volume 21, Number 1 Page range: 5-10

Total Pages: 6

Record appears in: Agricultural Economics Research Association (India) > Agricultural Economics Research Review

Agricultural Economics Research Review

Autor: Singh, Rama Krishna ; Prajneshu


Documentos relacionados