Using multivariate adaptive regression splines to estimate pollution in soil

Abstract

Heavy metal pollution is one of the main factors of the traffic pollution. The public authorities have been monitoring the concentration of heavy metal by means of sampling stations. This paper describes the response surface models and an intelligent regression algorithm, multivariate adaptive regression splines (MARS) models to data collected from soil at the stations where there were high density of buildings, roads, traffic and tramways. The model variables included the number of car and tramways and the concentration levels of Cadmium (Cd), Zinc (Zn) and Lead (Pb), at depth of 0-100mm. The objective of this study was to apply MARS to analyze the model output when there are a few numbers of design points. Several MARS models developed to simulate the concentration of each heavy metal. The performance of MARS was compared to that of response surface methodology (RSM) using 1st and 2nd order response surface models with respect to the accuracy metrics; root mean square error and adjusted R-2. The results showed that MARS models were successful in goodness of fit, suitable and also reliable as compared to the RSM models. Additionally, use of MARS in selection of the variables indicating great contribution on the response was effective