24 Ağustos 2021 Kitap bölümü Açık Erişim

Kaya, Fuat; Başayiğit, Levent

DataCite XML

<?xml version='1.0' encoding='utf-8'?>
<resource xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xmlns="http://datacite.org/schema/kernel-4" xsi:schemaLocation="http://datacite.org/schema/kernel-4 http://schema.datacite.org/meta/kernel-4.1/metadata.xsd">
  <identifier identifierType="URL">https://aperta.ulakbim.gov.tr/record/262961</identifier>
  <creators>
    <creator>
      <creatorName>Kaya, Fuat</creatorName>
      <givenName>Fuat</givenName>
      <familyName>Kaya</familyName>
      <affiliation>Isparta Uygulamalı Bilimler Üniversitesi</affiliation>
    </creator>
    <creator>
      <creatorName>Başayiğit, Levent</creatorName>
      <givenName>Levent</givenName>
      <familyName>Başayiğit</familyName>
      <affiliation>Isparta Uygulamalı Bilimler Üniversitesi</affiliation>
    </creator>
  </creators>
  <titles>
    <title>Spatial Prediction And Digital Mapping Of Soil Texture Classes In A Floodplain Using Multinomial Logistic Regression</title>
  </titles>
  <publisher>Aperta</publisher>
  <publicationYear>2021</publicationYear>
  <subjects>
    <subject>Digital soil mapping</subject>
    <subject>Machine learning algorithms</subject>
    <subject>Soil texture class</subject>
    <subject>Spatial predictive modelling</subject>
  </subjects>
  <dates>
    <date dateType="Issued">2021-08-24</date>
  </dates>
  <language>en</language>
  <resourceType resourceTypeGeneral="Text">Book section</resourceType>
  <alternateIdentifiers>
    <alternateIdentifier alternateIdentifierType="url">https://aperta.ulakbim.gov.tr/record/262961</alternateIdentifier>
  </alternateIdentifiers>
  <relatedIdentifiers>
    <relatedIdentifier relatedIdentifierType="DOI" relationType="IsIdenticalTo">10.1007/978-3-030-85577-2_55</relatedIdentifier>
  </relatedIdentifiers>
  <rightsList>
    <rights rightsURI="http://www.opendefinition.org/licenses/cc-by-sa">Creative Commons Attribution Share-Alike</rights>
    <rights rightsURI="info:eu-repo/semantics/openAccess">Open Access</rights>
  </rightsList>
  <descriptions>
    <description descriptionType="Abstract">&lt;p&gt;The spatial distribution of physical soil properties is an important requirement in practice as basic input data. Most effective of these properties is soil texture that governs water holding capacity, nutrient availability, and root development. Detailed information on soil texture variability in lateral dimension is crucial for proper crop and land management and environmental studies. Soil texture classes are determined in the soil survey. It may be consist of two or more texture classes for each polygon according to soil mapping units. There is a spatial discrepancy due to variability in soil texture within the mapping polygon. Digital soil mapping (DSM) offers major innovations in removing some of the inconsistencies in traditional soil mapping. DSM methodology can integrate the various raster-based spatial environmental data that field-based soil morphology, soil analyses, and effects of soil formation factors. In this study, the potential of environmental variables generated from digital data to predict soil texture classes were investigated. Curvature parameters indicating the shape of the slope were determined as the most important predictive variables in a flood plain. Overall accuracy was calculated as 63.9% and 47.60% for the training set and the test set, respectively. Digital soil map can be used effectively by farmers in the management of crops in this plain.&lt;/p&gt;</description>
  </descriptions>
</resource>