<?xml version="1.0" encoding="UTF-8" standalone="no"?><metadata xml:lang="en">
    <Esri>
        <CreaDate>20220128</CreaDate>
        <CreaTime>12113700</CreaTime>
        <ArcGISFormat>1.0</ArcGISFormat>
        <SyncOnce>TRUE</SyncOnce>
    </Esri>
    <dataIdInfo>
        <idCitation>
            <resTitle>New Group Layer</resTitle>
        </idCitation>
        <idAbs>Talbert Marsh is a wet land in Huntington Beach, California. It has open water, wet meadow, reeds, shrubs, and trees. This data is produced using 6 bands of MicaSense Dual Camera image by SVM classification and majority filtering. There are 12 classes here defined as &lt;div&gt;0: Water&lt;/div&gt;&lt;div&gt;1: Pebbles&lt;/div&gt;&lt;div&gt;2: Tall vegetations&lt;/div&gt;&lt;div&gt;3: Medium vegetations&lt;/div&gt;&lt;div&gt;4: Short vegetations&lt;/div&gt;&lt;div&gt;5: Dry reeds&lt;/div&gt;&lt;div&gt;6: Soil&lt;/div&gt;&lt;div&gt;7: Unpaved road&lt;/div&gt;&lt;div&gt;8: Shadow&lt;/div&gt;&lt;div&gt;9: Paved road&lt;/div&gt;&lt;div&gt;10: Reeds&lt;/div&gt;&lt;div&gt;11: Fens&lt;/div&gt;&lt;div&gt;&lt;br /&gt;&lt;/div&gt;</idAbs>
        <searchKeys>
            <keyword>Wet land</keyword>
            <keyword>Vegetation</keyword>
            <keyword>Classification</keyword>
            <keyword>Multiple spectrum</keyword>
            <keyword>Remote Sensing</keyword>
        </searchKeys>
        <idPurp>A wet land land cover classes. 
This region is at Talbert Marsh, Huntington Beach, CA. The feature layer is produced using 6 bands of MicaSense Dual Camera image by SVM classification and majority filtering. </idPurp>
        <idCredit/>
        <resConst>
            <Consts>
                <useLimit/>
            </Consts>
        </resConst>
    </dataIdInfo>
    <Binary>
        <Thumbnail>
            <Data EsriPropertyType="PictureX">/9j/4AAQSkZJRgABAQEAAQABAAD/2wBDAAgGBgcGBQgHBwcJCQgKDBQNDAsLDBkSEw8UHRofHh0a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</Data>
        </Thumbnail>
    </Binary>
</metadata>