<?xml version="1.0" encoding="UTF-8"?>
<rss xmlns:content="http://purl.org/rss/1.0/modules/content/" xmlns:dc="http://purl.org/dc/elements/1.1/" xmlns:rdf="http://www.w3.org/1999/02/22-rdf-syntax-ns#" xmlns:taxo="http://purl.org/rss/1.0/modules/taxonomy/" version="2.0">
  <channel>
    <title>topic Re: MaxEnt and Jackknifing in Geoprocessing Questions</title>
    <link>https://community.esri.com/t5/geoprocessing-questions/maxent-and-jackknifing/m-p/1699967#M27725</link>
    <description>&lt;P&gt;I had the same question as GISJess.&amp;nbsp; It seems as there is no 'variable importance' plots, like the Java version of the model produces.&amp;nbsp; I don't understand why this would be take out of the model outputs.&amp;nbsp; Is there a way to output something that would be equivalent to the variable importance plots in ArcGIS Pro?&amp;nbsp; The coefficients are useful in determining the relationships, but doesn't rank them against each other, unless I'm missing something?&amp;nbsp;&amp;nbsp;&lt;/P&gt;</description>
    <pubDate>Mon, 04 May 2026 21:36:36 GMT</pubDate>
    <dc:creator>G__AndrewFricker</dc:creator>
    <dc:date>2026-05-04T21:36:36Z</dc:date>
    <item>
      <title>MaxEnt and Jackknifing</title>
      <link>https://community.esri.com/t5/geoprocessing-questions/maxent-and-jackknifing/m-p/1688229#M27697</link>
      <description>&lt;P&gt;Hi Everyone,&amp;nbsp;&lt;/P&gt;&lt;P&gt;I'm new to using Presence-only Prediction in ArcGIS Pro. I've been reading up on MaxEnt, and it seems that the standalone tool had a 'Do jackknife to measure variable importance' option built into the tool. This would help&amp;nbsp; determine the highest performing variables. Is there a version of this in the ArcGIS Pro GP MaxEnt? Is there a script for this to be added?&lt;/P&gt;&lt;P&gt;I've done a correlation matrix via the Band Collection Statistics tool and chosen which variables to omit at .95 and .8 correlation. I also have MaxEnt output the&amp;nbsp;Partial Response of Continuous Variables chart, but I'm still trying to make it all make sense.&amp;nbsp;&lt;/P&gt;&lt;P&gt;Is this the way to do it? I would love if jackknife was an obvious option built into the tool.&amp;nbsp;&lt;/P&gt;&lt;P&gt;Thanks!&lt;/P&gt;</description>
      <pubDate>Wed, 04 Mar 2026 02:27:07 GMT</pubDate>
      <guid>https://community.esri.com/t5/geoprocessing-questions/maxent-and-jackknifing/m-p/1688229#M27697</guid>
      <dc:creator>GISJess</dc:creator>
      <dc:date>2026-03-04T02:27:07Z</dc:date>
    </item>
    <item>
      <title>Re: MaxEnt and Jackknifing</title>
      <link>https://community.esri.com/t5/geoprocessing-questions/maxent-and-jackknifing/m-p/1699967#M27725</link>
      <description>&lt;P&gt;I had the same question as GISJess.&amp;nbsp; It seems as there is no 'variable importance' plots, like the Java version of the model produces.&amp;nbsp; I don't understand why this would be take out of the model outputs.&amp;nbsp; Is there a way to output something that would be equivalent to the variable importance plots in ArcGIS Pro?&amp;nbsp; The coefficients are useful in determining the relationships, but doesn't rank them against each other, unless I'm missing something?&amp;nbsp;&amp;nbsp;&lt;/P&gt;</description>
      <pubDate>Mon, 04 May 2026 21:36:36 GMT</pubDate>
      <guid>https://community.esri.com/t5/geoprocessing-questions/maxent-and-jackknifing/m-p/1699967#M27725</guid>
      <dc:creator>G__AndrewFricker</dc:creator>
      <dc:date>2026-05-04T21:36:36Z</dc:date>
    </item>
  </channel>
</rss>

