<?xml version="1.0" encoding="UTF-8"?><xml><records><record><source-app name="Biblio" version="6.x">Drupal-Biblio</source-app><ref-type>47</ref-type><contributors><authors><author><style face="normal" font="default" size="100%">Gomez Gutierrez, A.</style></author><author><style face="normal" font="default" size="100%">Lavado Contador, F.</style></author><author><style face="normal" font="default" size="100%">Schnabel, S.</style></author></authors><secondary-authors><author><style face="normal" font="default" size="100%">Hengl, T.</style></author><author><style face="normal" font="default" size="100%">Evans, I. S.</style></author><author><style face="normal" font="default" size="100%">Wilson, J. P.</style></author><author><style face="normal" font="default" size="100%">Gould, M.</style></author></secondary-authors></contributors><titles><title><style face="normal" font="default" size="100%">Modeling soil properties at a regional scale using GIS and data mining techniques</style></title><secondary-title><style face="normal" font="default" size="100%">Geomorphometry 2011</style></secondary-title></titles><dates><year><style  face="normal" font="default" size="100%">2011</style></year></dates><urls><related-urls><url><style face="normal" font="default" size="100%">http://www.geomorphometry.org/system/files/GomezGutierrez2011bgeomorphometry.pdf</style></url></related-urls></urls><pub-location><style face="normal" font="default" size="100%">Redlands, CA</style></pub-location><pages><style face="normal" font="default" size="100%">79-82</style></pages><abstract><style face="normal" font="default" size="100%">&lt;p&gt;
	In this paper, five topsoil properties (clay, silt, sand, organic matter and bulk density) have been modeled using accessible environmental information in order to improve pedological cartography in Extremadura region (Spain). Independent variables related to topography, climate, lithology and vegetation cover were used to generate the models. The statistical approach was based on using Multivariate Adaptive Regression Splines (MARS) to produce the models. The performance of the models was tested using Root Mean Square Error (RMSE), Generalized Cross Validation (GCV) and r coefficient (regression analysis). The models presented discreet power prediction; being clay content and bulk density the best predicted target variables (with RMSE of 6.52 percent and 154.2 kg m-3, respectively).&lt;/p&gt;
</style></abstract></record></records></xml>