4

I have point data from deer surveys and would like to predict values for areas not surveyed based on vegetation type (Grass, Disturbed, Oak, Pine, Mixed etc.)

So far I have dissolved my vegetation layer to combine adjacent polygons and used Spatial Join to combine this layer with my point data. I'm now trying to predict values for polygons with Null values for the pop field (deer seen) and pop_avg field (pop/3 survey nights) based on vegetation type (text field). I'm not really sure what my next step should be if anyone has any suggestions.

Would I need to do the prediction analysis in a program such as R or python to later bring back to map in ArcGIS?

5
  • Are you trying to predict solely based on the vegetation type or do you have a more complex model in mind (e.g. distance to closest polygon with deer seen, proximity to urban areas, etc.)?
    – Kersten
    Jan 9, 2016 at 18:09
  • Right now I was only looking to base my predictions on vegetation type. Though I was thinking about incorporating the acreage of each vegetation type as another parameter if/when I was able to get the first part to work.
    – Southard
    Jan 9, 2016 at 18:20
  • 1
    Consider using R to predict your variables of interst. Random forest regression is highly suited for this type of analysis: cran.r-project.org/web/packages/randomForest/randomForest.pdf
    – Aaron
    Jan 9, 2016 at 19:48
  • Thanks for the suggestion. I will look into it and see what I can do with it.
    – Southard
    Jan 10, 2016 at 20:21
  • @Aaron I tried using randomForest in R. But I'm still having trouble getting the estimated or predicted values for my Pop_avg column and have posted an update to my question here: link
    – Southard
    Jan 18, 2016 at 21:17

1 Answer 1

0

I was able to use the randomForest package to answer my question which I explain in more detail here: https://stackoverflow.com/questions/34864182/predict-estimate-values-using-randomforest-in-r

Your Answer

By clicking “Post Your Answer”, you agree to our terms of service and acknowledge that you have read and understand our privacy policy and code of conduct.

Not the answer you're looking for? Browse other questions tagged or ask your own question.