On the Hybrid Models of Soil Contaminants Concentrations Predicting in Subarctic Region.

Forecasting the soil pollution is a considerable field of study in the light of the concern of environmental protection issues worldwide. The work deals with the application of artificial neural networks combining with residual kriging (ANNRK) to the spatial prediction of the abnormally distributed chemical element Chromium (Cr). It is known that combination of geostatistical interpolation approaches (kriging) and neural networks leads to better prediction accuracy and productivity. In the work, we compared two combined techniques: generalized regression neural network residual kriging (GRNNRK) and multi-layer perceptron residual kriging (MLPRK). The case study is based on the real data sets on surface contamination by Cr at a particular location of the subarctic Novy Urengoy, Russia, obtained during the previously conducted screening. The networks structures have been chosen during a computer simulation based on a minimization of the root mean squared error (RMSE). MLPRK showed the best predictive accuracy comparing to kriging and GRNNRK. [ABSTRACT FROM AUTHOR]