About Data Separation for the Artificial Neural Network Training to Predict the Spatial Distribution of the Chemical Element in the Soil

摘要

An algorithm for separate data into training and test subsamples to predict the spatial distribution of chromium in the surface layer of the soil using artificial neural networks (ANN) was proposed. The algorithm takes into account the spatial inhomogeneity of the modelled variable. The data was obtained during the soil screening on the urbanized area in Novy Urengoy city. A model, which used controlled separation, had shown more accurate results.