<!DOCTYPE HTML PUBLIC "-//W3C//DTD HTML 4.01 Transitional//EN">
<html>
  <head>
    <meta content="text/html; charset=ISO-8859-1"
      http-equiv="Content-Type">
  </head>
  <body bgcolor="#ffffff" text="#000000">
    Hi,<br>
    <br>
    You could also opt for kriging, which supports anisotropy. The
    intamap package has a function to detect anisotropy, in case you
    would like to automate the interpolation. <br>
    <br>
    cheers,<br>
    Paul<br>
    <br>
    On 03/18/2011 01:41 AM, <a class="moz-txt-link-abbreviated" href="mailto:smurray@worldbank.org">smurray@worldbank.org</a> wrote:
    <blockquote
cite="mid:OF9E467B2C.66CBB9BB-ON85257857.00039E87-05257857.0003DDC8@worldbank.org"
      type="cite">
      <p><font size="2">Thanks for the reply. I was planning to generate
          a surface for each time slice independently, so just x ,y.</font><br>
        <font size="2">Siobhan</font><br>
        <img src="cid:part1.08030106.09020604@knmi.nl" alt="Inactive
          hide details for Re: [R-sig-Geo] using IDW with anisotropy"
          border="0" height="16" width="16"><font size="2">Re:
          [R-sig-Geo] using IDW with anisotropy</font><br>
        <br>
        <br>
        <table border="0" cellpadding="0" cellspacing="0" width="100%">
          <tbody>
            <tr valign="top">
              <td style="background-image:
                url("cid:1__=0ABBF2C4DF9018178f9e8a93df@worldbank.org");
                background-repeat: no-repeat;" valign="middle"
                width="1%"><img
                  src="cid:part2.02030000.05060209@knmi.nl" alt=""
                  border="0" height="1" width="80"><br>
                <img src="cid:part3.05000704.00010008@knmi.nl"
                  height="1" width="80"></td>
              <td valign="middle" width="100%"><img
                  src="cid:part2.02030000.05060209@knmi.nl" alt=""
                  border="0" height="1" width="1"><br>
                <table border="0" cellpadding="0" cellspacing="0"
                  width="100%">
                  <tbody>
                    <tr valign="top">
                      <td width="1%"><img
                          src="cid:part2.02030000.05060209@knmi.nl"
                          alt="" border="0" height="1" width="12"><br>
                      </td>
                      <td width="100%"><img
                          src="cid:part2.02030000.05060209@knmi.nl"
                          alt="" border="0" height="1" width="1"><br>
                      </td>
                    </tr>
                  </tbody>
                </table>
                <table border="0" cellpadding="0" cellspacing="0"
                  width="100%">
                  <tbody>
                    <tr valign="top">
                      <td width="100%"><b>Re: [R-sig-Geo] using IDW with
                          anisotropy</b></td>
                    </tr>
                  </tbody>
                </table>
                <table id="tmpdisplaysendto" border="0" cellpadding="0"
                  cellspacing="0" width="100%">
                  <tbody>
                    <tr valign="top">
                      <td valign="middle" width="1%"><img
                          src="cid:part2.02030000.05060209@knmi.nl"
                          alt="" border="0" height="1" width="110"><br>
                        <b><font size="2" color="#e26200">Edzer Pebesma</font></b></td>
                      <td width="1%"><img
                          src="cid:part2.02030000.05060209@knmi.nl"
                          alt="" border="0" height="1" width="18"><br>
                        <font size="2" color="#929292">to:</font></td>
                      <td width="100%"><img
                          src="cid:part2.02030000.05060209@knmi.nl"
                          alt="" border="0" height="1" width="1"><br>
                        <font size="2">r-sig-geo</font></td>
                      <td width="1%"><img
                          src="cid:part2.02030000.05060209@knmi.nl"
                          alt="" border="0" height="1" width="141"><br>
                        <div align="right"><font size="2">03/17/2011
                            02:03 PM</font></div>
                      </td>
                    </tr>
                  </tbody>
                </table>
                <table border="0" cellpadding="0" cellspacing="0"
                  width="100%">
                  <tbody>
                    <tr valign="top">
                      <td valign="middle" width="100%"><img
                          src="cid:part2.02030000.05060209@knmi.nl"
                          alt="" border="0" height="1" width="1"><br>
                        <table border="0" cellpadding="0"
                          cellspacing="0" width="100%">
                          <tbody>
                            <tr valign="top">
                              <td valign="middle" width="1%"><img
                                  src="cid:part2.02030000.05060209@knmi.nl"
                                  alt="" border="0" height="1"
                                  width="48"><br>
                                <font size="2" color="#929292">Sent by:</font></td>
                              <td valign="middle" width="100%"><img
                                  src="cid:part2.02030000.05060209@knmi.nl"
                                  alt="" border="0" height="1" width="1"><br>
                                <b><font size="2" color="#e26200"><a class="moz-txt-link-abbreviated" href="mailto:r-sig-geo-bounces@r-project.org">r-sig-geo-bounces@r-project.org</a></font></b></td>
                            </tr>
                          </tbody>
                        </table>
                      </td>
                      <td valign="middle" width="0%"><img
                          src="cid:part2.02030000.05060209@knmi.nl"
                          alt="" border="0" height="1" width="1"><br>
                      </td>
                    </tr>
                  </tbody>
                </table>
              </td>
            </tr>
          </tbody>
        </table>
        <br>
      </p>
      <hr style="color: rgb(180, 191, 203);" size="2" align="left"
        width="2112"><br>
      <br>
      <tt><font size="2">Are you interpolating in 3D (x,y,t)?<br>
          <br>
          On 03/17/2011 04:21 PM, <a class="moz-txt-link-abbreviated" href="mailto:smurray@worldbank.org">smurray@worldbank.org</a> wrote:<br>
          > hello,<br>
          > <br>
          > I have a timseries dataset of monthly precip data from
          rain guages. The coverage <br>
          > is relatively sparse (approx 30 stations covering the
          country) and there is <br>
          > strong anisotropy in the data - at the monthly timestep
          data is strongly <br>
          > correlated in the E-W direction. Is there any way to use
          modify the IDW <br>
          > interpolation in gstat, to incorporate a directional bias
          in the distance weight?<br>
          > <br>
          > many thanks for any suggestions<br>
          > <br>
          > <br>
          > <br>
          > <br>
          > _______________________________________________<br>
          > R-sig-Geo mailing list<br>
          > <a class="moz-txt-link-abbreviated" href="mailto:R-sig-Geo@r-project.org">R-sig-Geo@r-project.org</a><br>
          > </font></tt><tt><font size="2"><a moz-do-not-send="true"
            href="https://stat.ethz.ch/mailman/listinfo/r-sig-geo">https://stat.ethz.ch/mailman/listinfo/r-sig-geo</a></font></tt><tt><font
          size="2"><br>
          <br>
          -- <br>
          Edzer Pebesma<br>
          Institute for Geoinformatics (ifgi), University of Münster<br>
          Weseler Straße 253, 48151 Münster, Germany. Phone: +49 251<br>
          8333081, Fax: +49 251 8339763  </font></tt><tt><font size="2"><a
            moz-do-not-send="true" href="http://ifgi.uni-muenster.de">http://ifgi.uni-muenster.de</a></font></tt><tt><font
          size="2"><br>
        </font></tt><tt><font size="2"><a moz-do-not-send="true"
            href="http://www.52north.org/geostatistics">http://www.52north.org/geostatistics</a></font></tt><tt><font
          size="2">      <a class="moz-txt-link-abbreviated" href="mailto:e.pebesma@wwu.de">e.pebesma@wwu.de</a><br>
          <br>
          _______________________________________________<br>
          R-sig-Geo mailing list<br>
          <a class="moz-txt-link-abbreviated" href="mailto:R-sig-Geo@r-project.org">R-sig-Geo@r-project.org</a><br>
        </font></tt><tt><font size="2"><a moz-do-not-send="true"
            href="https://stat.ethz.ch/mailman/listinfo/r-sig-geo">https://stat.ethz.ch/mailman/listinfo/r-sig-geo</a></font></tt><tt><font
          size="2"><br>
        </font></tt><br>
      <br>
      <br>
      <pre wrap="">
<fieldset class="mimeAttachmentHeader"></fieldset>
_______________________________________________
R-sig-Geo mailing list
<a class="moz-txt-link-abbreviated" href="mailto:R-sig-Geo@r-project.org">R-sig-Geo@r-project.org</a>
<a class="moz-txt-link-freetext" href="https://stat.ethz.ch/mailman/listinfo/r-sig-geo">https://stat.ethz.ch/mailman/listinfo/r-sig-geo</a>
</pre>
    </blockquote>
    <br>
    <br>
    <pre class="moz-signature" cols="72">-- 
Paul Hiemstra, MSc
Global Climate Division
Royal Netherlands Meteorological Institute (KNMI)
Wilhelminalaan 10 | 3732 GK | De Bilt | Kamer B 3.39
P.O. Box 201 | 3730 AE | De Bilt
tel: +31 30 2206 494

<a class="moz-txt-link-freetext" href="http://intamap.geo.uu.nl/~paul">http://intamap.geo.uu.nl/~paul</a>
<a class="moz-txt-link-freetext" href="http://nl.linkedin.com/pub/paul-hiemstra/20/30b/770">http://nl.linkedin.com/pub/paul-hiemstra/20/30b/770</a></pre>
  </body>
</html>