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

2428RE: [ai-geostats] Software for Automatic Semivariogram Estimation

Expand Messages
  • Pierre Goovaerts
    Feb 28, 2006
      Hello,

      I have been using a modified version of VARFIT that is available on the
      Computer and Geosciences website.

      Pardo-Iguzquiza E: VARFIT: a Fortran-77 program for fitting variogram models by weighted least squares. Computers and Geosciences 1999, 25:251-261.

      I agree that choosing a set of weighting factors for the fit can be frustrating
      and it's why in the program I provided with my latest IJHG paper, I allowed
      the user to choose among 5 options for the weights. For the weights N(h)/gamma(h),
      I used the experimental semivariogram values, which eliminates the problem of
      weights that change during the iterative fitting procedure and also attenuates
      the impact of unreliable semivariogram values computed for the first lags
      (i.e. impact of preferential sampling of high values as in my WRR paper on
      groundwater arsenic concentrations).

      I have increasingly used automatic fitting procedures, followed by a visual
      assessment of the fit (and yes the fitting of variogram clouds in Arcview is
      one of the many ESRI blunders). It has proven convenient in several situations:
      1. implementation of Poisson kriging to be used by epidemiologists, who
      have no idea what a semivariogram is, for removing noise from rate data,
      2. use of indicator kriging for automatic mapping procedures (SIC 2004 paper
      that is available on my webpage).
      3. testing of new algorithms using hundreds of simulations. The common use
      of only one jackknife or simulation to compare the prediction performances of
      various algorithms is very hazardous since the ranking can drastically change
      would another subset of data be used for validation.

      Cheers,

      Pierre



      Pierre Goovaerts
      Chief Scientist at BioMedware
      516 North State Street
      Ann Arbor, MI 48104
      Voice: (734) 913-1098 (ext. 8)
      Fax: (734) 913-2201
      http://home.comcast.net/~goovaerts/

      ________________________________

      From: Mach Nife [mailto:machnife@...]
      Sent: Tue 2/28/2006 10:16 AM
      To: ai-geostats
      Subject: [ai-geostats] Software for Automatic Semivariogram Estimation



      Hi,

      I'm hunting for a software (freeware/openSource if
      possible), that would help estimating the best
      possible semivariogram curve in a non-interactive way.
      As an example, ArcGis Geostatistical Analyst does a
      pretty good job at this when we accept the defaults.
      It does some automatic calculations for the parameters
      of the selected model. I've tried Gstat "Fit" method
      (in the command-line version), but the results aren't
      what I expected. What I need is a command line
      software or one that can be controlled by programming.

      Any ideas?
      machnife

      __________________________________________________
      Do You Yahoo!?
      Tired of spam? Yahoo! Mail has the best spam protection around
      http://mail.yahoo.com
    • Show all 3 messages in this topic