<?xml version="1.0" encoding="UTF-8"?>
<rdf:RDF xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns="http://purl.org/rss/1.0/" xmlns:dc="http://purl.org/dc/elements/1.1/">
  <channel rdf:about="http://http://dspace.unitus.it:80">
    <title>Unitus DSpace</title>
    <link>http://http://dspace.unitus.it:80</link>
    <description>The DSpace digital repository system captures, stores, indexes, preserves, and distributes digital research material.</description>
    <items>
      <rdf:Seq>
        <rdf:li rdf:resource="http://hdl.handle.net/2067/2309" />
      </rdf:Seq>
    </items>
    <dc:date>2013-06-20T03:46:14Z</dc:date>
  </channel>
  <item rdf:about="http://hdl.handle.net/2067/2309">
    <title>Experimenting the design-based k-NN approach for mapping and estimation under forest management planning</title>
    <link>http://hdl.handle.net/2067/2309</link>
    <description>Title: Experimenting the design-based k-NN approach for mapping and estimation under forest management planning
Authors: Mattioli, Walter; Quatrini, Valerio; Di Paolo, Silvia; Di Santo, Daniele; Giuliarelli, Diego; Angelini, Alice; Portoghesi, Luigi; Corona, Piermaria
Abstract: Estimation and mapping of forest attributes are a fundamental support for&#xD;
forest management planning. This study describes a practical experimentation&#xD;
concerning the use of design-based k-Nearest Neighbors (k-NN) approach to estimate&#xD;
and map selected attributes in the framework of inventories at forest&#xD;
management level. The study area was the Chiarino forest within the Gran Sasso&#xD;
and Monti della Laga National Park (central Italy). Aboveground biomass and&#xD;
current annual increment of tree volume were selected as the attributes of interest&#xD;
for the test. Field data were acquired within 28 sample plots selected&#xD;
by stratified random sampling. Satellite data were acquired by a Landsat 5 TM&#xD;
multispectral image. Attributes from field surveys and Landsat image processing&#xD;
were coupled by k-NN to predict the attributes of interest for each&#xD;
pixel of the Landsat image. Achieved results demonstrate the effectiveness of&#xD;
the k-NN approach for statistical estimation, that is compatible with the produced&#xD;
forest attribute raster maps and also proves to be characterized, in the&#xD;
considered study case, by a precision double than that obtained by conventional&#xD;
inventory based on field sample plots only.
Description: L'articolo è disponibile sul sito dell'editore www.sisef.it</description>
    <dc:date>2011-12-31T23:00:00Z</dc:date>
  </item>
</rdf:RDF>

