Articles
DESCRIPTIVE MODELLING OF CROP QUALITY IN CROP PRODUCTION SYSTEMS BY MULTIVARIATE ANALYSIS AND ARTIFICIAL NEURAL NETWORKS.
Article number
476_28
Pages
243 – 250
Language
Abstract
Analysis of the agricultural production system frequently produces large and complex sets of data from surveys.
These data are sometimes required to be used in making predictions about optimum methods of production with respect to particular sets of conflicting goals (e.g. maximum yield and low environmental impact). As an initial step in modelling such data it can be helpful to produce descriptive multivariate models which indicate the main sources of variation present.
We briefly describe two approaches to this objective using oilseed quality as an example.
These data are sometimes required to be used in making predictions about optimum methods of production with respect to particular sets of conflicting goals (e.g. maximum yield and low environmental impact). As an initial step in modelling such data it can be helpful to produce descriptive multivariate models which indicate the main sources of variation present.
We briefly describe two approaches to this objective using oilseed quality as an example.
Publication
Authors
N. McRoberts, G.N. Foster, S. Wale, K. Davies, R.G. McKinlay, A. Hunter
Keywords
multivariate analysis, neural networks, oilseed quality
Online Articles (43)