Volume : 4, Issue : 4, April - 2015

Correlation between digital Landsat levels With Uranium content in soil using Support Vector Machines Regression Algorithms

Luis Hern N Ochoa, Luis Hern N Alvarez

Abstract :

<p>&lt;p&gt;Geophysical and Geochemical Field surveying is a hardly and costly activity where remote sensing tools can be a very&amp;nbsp;&lt;/p&gt; &lt;div&gt;useful tool to increase coverage and resolution in that kind of studies. Here we present the results obtained using a&amp;nbsp;&lt;/div&gt; &lt;div&gt;Support Vector Machine Regression model that relates contents of Uranium measured in laboratory to field soil samples&amp;nbsp;&lt;/div&gt; &lt;div&gt;withlocation coordinates and digital Landsat levels at the sample site. Soil samples were taken during a geochemical field survey made by&amp;nbsp;&lt;/div&gt; &lt;div&gt;the &amp;quot;InstitutoColombiano de Geolog&amp;iacute;a y Miner&amp;iacute;a &amp;ndash; INGEOMINAS&amp;ldquo;in the Vichada and Guain&amp;iacute;a Departments &amp;ndash; Colombia in 2006. The maximum&amp;nbsp;&lt;/div&gt; &lt;div&gt;correlation factor obtained was 0.67 which is quite low but indicates the presence of an important relation between Uranium content and digital&amp;nbsp;&lt;/div&gt; &lt;div&gt;Landsat levels. This research can be considered as an important contribution to the classical geostatistical models because let&amp;rsquo;s to increase model&amp;nbsp;&lt;/div&gt; &lt;div&gt;resolution in areas where sampling density is low getting valuable information from inaccessible areas using remote sensing higher spatial&amp;nbsp;&lt;/div&gt; &lt;div&gt;variabilit&lt;/div&gt;</p>