『Summary
Factorial regression models, based on correspondence analysis,
are built to explain the high nitrate concentrations in groundwater
beneath an agricultural area in the south of Portugal, exceeding
300 mg/l, as a function of chemical variables, electrical conductivity
(EC), land use and hydrogeological setting. Two important advantages
of the proposed methodology are that qualitative parameters can
be involved in the regression analysis and that multicollinearity
is avoided. Regression is performed on eigenvectors extracted
from the data similarity matrix, the first of which clearly reveals
the impact of agricultural practices and hydrogeological setting
on the groundwater chemistry of the study area. Significant correlation
exists between response variable NO3-
and explanatory variables Ca2+, Cl-, SO42-, depth to water, aquifer media
and land use. Substituting Cl- by the EC results in
the most accurate regression model for nitrate, when disregarding
the four largest outliers (model A). When built solely on land
use and hydrogeological setting, the regression model (model B)
is less accurate but more interesting from a practical viewpoint,
as it is based on easily obtainable data and can be used to predict
nitrate concentrations in groundwater on other areas with similar
conditions. This is particularly useful for conservative contaminants,
where risk and vulnerability assessment methods, based on assumed
rather than established correlations, generally produce erroneous
results. Another purpose of the models can be to predict the future
evolution of nitrate concentrations under influence of changes
in land use or fertilization practices, which occur in compliance
with policies such as the Nitrates Directive. Model B predicts
a 40％ decrease in nitrate concentrations in groundwater of the
study area,when horticulture is replaced by other land use with
much lower fertilization and irrigation rates.
Keywords: Factorial regression analysis; Explanatory models; Groundwater
contamination; Nitrate; Agricultural practices; Portugal』
Introduction
Methodology
Application to the study area
Factorial correspondence analysis - results and discussion
Chemical variables
Qualitative variables
Factorial regression analysis - results and discussion
Standard error analysis
Final regression models
Conclusions
Acknowledgements
References