<?xml version='1.0' encoding='utf-8'?>
<oai_dc:dc xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:oai_dc="http://www.openarchives.org/OAI/2.0/oai_dc/" xmlns:xsi="http://www.w3.org/2001/XMLSchema-instance" xsi:schemaLocation="http://www.openarchives.org/OAI/2.0/oai_dc/ http://www.openarchives.org/OAI/2.0/oai_dc.xsd">
  <dc:contributor>Corina Cerovski-Darriau</dc:contributor>
  <dc:contributor>Vadim Zaliva</dc:contributor>
  <dc:contributor>Jonathan D. Stock</dc:contributor>
  <dc:creator>Helen Petlyak</dc:creator>
  <dc:date>2019</dc:date>
  <dc:description>&lt;p&gt;&lt;span&gt;While machine learning techniques have been increasingly applied to land cover classification problems, these techniques have not focused on separating exposed bare rock from soil covered areas. Therefore, we built a convolutional neural network (CNN) to differentiate exposed bare rock (&lt;/span&gt;&lt;span class="html-italic"&gt;rock&lt;/span&gt;&lt;span&gt;) from soil cover (&lt;/span&gt;&lt;span class="html-italic"&gt;other&lt;/span&gt;&lt;span&gt;). We made a training dataset by mapping exposed rock at eight test sites across the Sierra Nevada Mountains (California, USA) using USDA’s 0.6 m National Aerial Inventory Program (NAIP) orthoimagery. These areas were then used to train and test the CNN. The resulting machine learning approach classifies bare rock in NAIP orthoimagery with a 0.95&amp;nbsp;&lt;/span&gt;&lt;span id="MathJax-Element-1-Frame" class="MathJax" data-mathml="&lt;math xmlns=&amp;quot;http://www.w3.org/1998/Math/MathML&amp;quot; display=&amp;quot;inline&amp;quot;&gt;&lt;semantics&gt;&lt;msub&gt;&lt;mi&gt;F&lt;/mi&gt;&lt;mn&gt;1&lt;/mn&gt;&lt;/msub&gt;&lt;/semantics&gt;&lt;/math&gt;"&gt;&lt;span id="MathJax-Span-1" class="math"&gt;&lt;span&gt;&lt;span id="MathJax-Span-2" class="mrow"&gt;&lt;span id="MathJax-Span-3" class="semantics"&gt;&lt;span id="MathJax-Span-4" class="msub"&gt;&lt;i&gt;&lt;span id="MathJax-Span-5" class="mi"&gt;F&lt;/span&gt;&lt;/i&gt;&lt;sub&gt;&lt;span id="MathJax-Span-6" class="mn"&gt;1&lt;/span&gt;&lt;/sub&gt;&lt;/span&gt;&lt;/span&gt;&lt;/span&gt;&lt;/span&gt;&lt;/span&gt;&lt;/span&gt;&lt;span&gt;&amp;nbsp;&lt;/span&gt;&lt;span&gt;score. Comparatively, the classical OBIA approach gives only a 0.84&amp;nbsp;&lt;/span&gt;&lt;span id="MathJax-Element-2-Frame" class="MathJax" data-mathml="&lt;math xmlns=&amp;quot;http://www.w3.org/1998/Math/MathML&amp;quot; display=&amp;quot;inline&amp;quot;&gt;&lt;semantics&gt;&lt;msub&gt;&lt;mi&gt;F&lt;/mi&gt;&lt;mn&gt;1&lt;/mn&gt;&lt;/msub&gt;&lt;/semantics&gt;&lt;/math&gt;"&gt;&lt;span id="MathJax-Span-7" class="math"&gt;&lt;span&gt;&lt;span id="MathJax-Span-8" class="mrow"&gt;&lt;span id="MathJax-Span-9" class="semantics"&gt;&lt;span id="MathJax-Span-10" class="msub"&gt;&lt;i&gt;&lt;span id="MathJax-Span-11" class="mi"&gt;F&lt;/span&gt;&lt;/i&gt;&lt;sub&gt;&lt;span id="MathJax-Span-12" class="mn"&gt;1&lt;/span&gt;&lt;/sub&gt;&lt;/span&gt;&lt;/span&gt;&lt;/span&gt;&lt;/span&gt;&lt;/span&gt;&lt;/span&gt;&lt;span&gt;&amp;nbsp;&lt;/span&gt;&lt;span&gt;score. This is an improvement over existing land cover maps, which underestimate rock by almost 90%. The resulting CNN approach is likely scalable but dependent on high-quality imagery and high-performance algorithms using representative training sets informed by expert mapping. As image quality and quantity continue to increase globally, machine learning models that incorporate high-quality training data informed by geologic, topographic, or other topical maps may be applied to more effectively identify exposed rock in large image collections.&lt;/span&gt;&lt;/p&gt;</dc:description>
  <dc:format>application/pdf</dc:format>
  <dc:identifier>10.3390/rs11192211</dc:identifier>
  <dc:language>en</dc:language>
  <dc:publisher>MDPI</dc:publisher>
  <dc:title>Where’s the rock: Using convolutional neural networks to improve land cover classification</dc:title>
  <dc:type>article</dc:type>
</oai_dc:dc>