Loading ...
Sorry, an error occurred while loading the content.

GEOSTATS: sampling

Expand Messages
  • Yetta Jager
    We are dealing with a similar problem of sampling GIS complete data for spatial analysis. In our case, it is necessary to sample for the simulation or
    Message 1 of 1 , Oct 29, 1998
    • 0 Attachment
      We are dealing with a similar problem of sampling GIS "complete"
      data for spatial analysis. In our case, it is necessary to sample
      for the simulation or prediction component (perhaps not semivariogram
      estimation) because we are interested in introducing spatial uncertainty
      which is possible only by pretending that its necessary to interpolate.

      We adopted the following scheme for drawing two samples: one for variogram
      estimation and another for indicator simulation. We welcome opinions on this
      approach.

      For the sample used to predict, we sample regularly from the full grid
      to get good spatial coverage and representative numbers in each
      category (Z value). In addition, we supplement this sample with a
      minimum specified number in each category, but exclude extremely
      rare categories (too few data for semivariogram estimation).

      For the sample used for semivariogram analysis, we subsampled the grid
      in the prediction sample with a specified probability and include both
      the point from the regular sample and one of its neighbors (drawn at
      random) to provide enough closely-spaced information. In addition, we
      stored a minimum number of points in each category when reading the
      original grid and we supplement the semivariogram sample with these and
      all nearest neighbors in the same (rare) category.

      Parts of this approach derive from Warrick and Meyers 1987. Optimization
      of sampling locations for variogram calculations. Water Res. Research
      23(3): 496-500.

      Yetta


      ------------------------------------------------------
      Yetta Jager
      Environmental Sciences Division
      Oak Ridge National Laboratory
      P.O. Box 2008, MS 6036
      Oak Ridge, TN 37831-6036
      OFFICE: 423/574-8143
      FAX: 423/576-8543
      Work email: jagerhi@...
      Home email: hjager@...
      WEBpage: http://www.esd.ornl.gov/~zij/
      -----------------------------------------------------

      "One man's mean is another man's Poisson" J.W. Haeffner
      --
      *To post a message to the list, send it to ai-geostats@....
      *As a general service to list users, please remember to post a summary
      of any useful responses to your questions.
      *To unsubscribe, send email to majordomo@... with no subject and
      "unsubscribe ai-geostats" in the message body.
      DO NOT SEND Subscribe/Unsubscribe requests to the list!
    Your message has been successfully submitted and would be delivered to recipients shortly.