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

GEOSTATS: Simple request

Expand Messages
  • John Sadler
    Greetings, I have a specialized interpolation need wherein a surface must be developed from elevation data on an arbitrary and limited number of close
    Message 1 of 2 , Jun 10, 1998
    • 0 Attachment
      Greetings,

      I have a specialized interpolation need wherein a surface must be developed
      from elevation data on an arbitrary and limited number of close neighbors. I
      am working in FORTRAN and need to imbed a subroutine that will accept a
      series of (x,y,z), create an approximation to the z surface, and return
      estimated z for an (x,y) pair. The x,y locations in the series are not
      necessarily regular. The number of close neighbors is variable, but usually
      4 or more. I will have to build in protection from cases in which fewer
      than the necessary number occur. I would be willing to use a plane surface,
      but a more-flexible surface would be nice (maybe quadratic in x and y if
      enough neighbors exist).

      I have scrounged several sources of routines available on the web, but most
      of those are far more sophisticated than my needs.

      If anyone has an idea, I'd like to hear of potential sources.

      Thanks,
      John Sadler

      ==============================================================
      E. John Sadler, Ph.D.
      USDA-ARS sadler@...
      Coastal Plains Soil, Water, http://www.florence.ars.usda.gov
      and Plant Research Center 843-669-5203x112 (voice)
      2611 West Lucas St. 843-669-6970 (fax)
      Florence, SC 29501-1241
      U.S.A.
      ==============================================================

      --
      *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!
    • Syed Abdul Rahman
      From: John Sadler ... Sophistication is relative, consider that: (a) a pure nugget model decomposes into a local mean
      Message 2 of 2 , Jun 12, 1998
      • 0 Attachment
        From: John Sadler <sadler@...>

        >I have scrounged several sources of routines available on the web, but most
        >of those are far more sophisticated than my needs.

        Sophistication is relative, consider that:

        (a) a pure nugget model decomposes into a local
        mean interpolation technique
        (b) some specific power law variogram parameters
        can decompose into a linear interpolation between
        points.
        (c) there are cases where splines can be equivalent
        to some specific generalized covariance models
        (d) likewise radial basis function networks, which
        can be equivalent to simple kriging for some specific
        RBFs.
        (e) universal kriging with nugget can decompose into a
        trend fitting technique

        et cetera et cetera. Starting with kriging is probably a good
        idea, considering the universal nature of two basic components
        in spatial interpolation: (a) the spatial correlation model; and
        (b) weighting by statistical and/or spatial distance (although I
        admit the math can be a bit confusing).

        Regards,

        Syed


        --
        *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.