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

GEOSTATS: Problems with Kriging in Splus

Expand Messages
  • Fay Hughes
    Hello I am presently working with S+Spatial Stats (Splus 2000), trying to repeat results I obtained previously with Geoeas, but am encountering difficulties,
    Message 1 of 4 , Dec 6, 1999
    • 0 Attachment
      Hello

      I am presently working with S+Spatial Stats (Splus 2000), trying to
      repeat results I obtained previously with Geoeas, but am encountering
      difficulties, when trying to get Splus to give predictions on a small
      (eg 2x2) grid which is a subsection of the whole area, the .Fortran
      fault "Covariance matrix is not positive definite" results, even though
      Geoeas can perform the same kriging.

      I was also wondering if the code for the krige and predict.krige
      functions are available and also if there is anyway in Splus to specify
      search radii (like in geoeas) or to get more detailed information about
      the actual procedure (like caps, scroll and num lock in Geoeas).

      Thank you, in anticipation of your help.

      Fay Hughes (Miss)
      email: HughesFA@...

      --
      *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!
    • Melanie Wall
      The krige function in S+Spatial uses the covariogram instead of the variogram. So in general it can only do ordinary kriging on 2nd order stationary processes
      Message 2 of 4 , Dec 7, 1999
      • 0 Attachment
        The krige function in S+Spatial uses the covariogram instead of the
        variogram. So in general it can only do ordinary kriging on 2nd order
        stationary processes (i.e. where the covariogram exists). The theoretical
        covariograms it supports are expondential, spherical and gaussian models.
        Apparently this function can also be tricked to work with a linear
        variogram model (see p. 98 of S+Spatial Stat manual).

        -----------------------
        Melanie Wall
        Division of Biostatistics
        A460 Mayo Building Box 303
        420 Delaware Street S.E.
        Minneapolis, MN 55455
        (612)625-2138
        melanie@...

        On Tue, 7 Dec 1999, Fay Hughes wrote:

        > Hello
        >
        > I am presently working with S+Spatial Stats (Splus 2000), trying to
        > repeat results I obtained previously with Geoeas, but am encountering
        > difficulties, when trying to get Splus to give predictions on a small
        > (eg 2x2) grid which is a subsection of the whole area, the .Fortran
        > fault "Covariance matrix is not positive definite" results, even though
        > Geoeas can perform the same kriging.
        >
        > I was also wondering if the code for the krige and predict.krige
        > functions are available and also if there is anyway in Splus to specify
        > search radii (like in geoeas) or to get more detailed information about
        > the actual procedure (like caps, scroll and num lock in Geoeas).
        >
        > Thank you, in anticipation of your help.
        >
        > Fay Hughes (Miss)
        > email: HughesFA@...
        >
        > --
        > *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!
        >

        --
        *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!
      • Inge Frette
        Hello folks, not being an expert in geostatistics I wonder why the power model of the variogram model in Gslib is not allowed for when doing cokriging ? Anyone
        Message 3 of 4 , Dec 13, 1999
        • 0 Attachment
          Hello folks,
          not being an expert in geostatistics I wonder why the power model of the
          variogram model
          in Gslib is not allowed for when doing cokriging ?

          Anyone that knows why ?

          Regards from Inge Frette


          ************************************************************************
          Inge Frette Phone : +47 51 87 54 50
          GEOLOGICA AS Phone : +47 51 87 58 15 (from 1.1.2000)
          P.O.Box 8034 Fax : +47 51 87 52 87
          N-4003 STAVANGER E-mail: inge.frette@...
          NORWAY Web : http://www.geologica.no
          ************************************************************************

          --
          *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!
        • Pierre Goovaerts
          Hello, Power models are not allowed for SIMPLE cokriging in the current version of cokb3d although they are allowed for simple kriging. Note that simple
          Message 4 of 4 , Dec 13, 1999
          • 0 Attachment
            Hello,

            Power models are not allowed for SIMPLE cokriging
            in the current version of cokb3d although they
            are allowed for simple kriging.
            Note that simple (co)kriging systems need to be expressed in
            terms of covariances but pseudo-variances can be used
            to convert unbounded semivariograms into covariances.

            My advice is: Do not use simple cokriging since the
            assumptions of stationarity of the means are rarely met.
            Use the option ordinary cokriging and compare the
            two options: traditional and standardized cokriging since
            the unbiasedness constraints can influence the quality
            of the predictions, e.g. see
            Goovaerts, P. 1998. Ordinary cokriging revisited.
            Mathematical Geology, 30(1):21--42.

            Cheers,

            Pierre
            <><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>

            ________ ________
            | \ / | Pierre Goovaerts
            |_ \ / _| Assistant professor
            __|________\/________|__ Dept of Civil & Environmental Engineering
            | | The University of Michigan
            | M I C H I G A N | EWRE Building, Room 117
            |________________________| Ann Arbor, Michigan, 48109-2125, U.S.A
            _| |_\ /_| |_
            | |\ /| | E-mail: goovaert@...
            |________| \/ |________| Phone: (734) 936-0141
            Fax: (734) 763-2275
            http://www-personal.engin.umich.edu/~goovaert/

            <><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><><>


            On Mon, 13 Dec 1999, Inge Frette wrote:

            > Hello folks,
            > not being an expert in geostatistics I wonder why the power model of the
            > variogram model
            > in Gslib is not allowed for when doing cokriging ?
            >
            > Anyone that knows why ?
            >
            > Regards from Inge Frette
            >
            >
            > ************************************************************************
            > Inge Frette Phone : +47 51 87 54 50
            > GEOLOGICA AS Phone : +47 51 87 58 15 (from 1.1.2000)
            > P.O.Box 8034 Fax : +47 51 87 52 87
            > N-4003 STAVANGER E-mail: inge.frette@...
            > NORWAY Web : http://www.geologica.no
            > ************************************************************************
            >
            > --
            > *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!
            >

            --
            *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.