{"id":327,"date":"2018-02-14T15:13:19","date_gmt":"2018-02-14T15:13:19","guid":{"rendered":"https:\/\/career0to1.wordpress.com\/?p=327"},"modified":"2018-02-15T05:54:25","modified_gmt":"2018-02-15T05:54:25","slug":"empirical-baysian-kriging","status":"publish","type":"post","link":"https:\/\/career0to1.com\/?p=327","title":{"rendered":"Empirical Baysian Kriging"},"content":{"rendered":"<div id=\"dslc-theme-content\"><div id=\"dslc-theme-content-inner\"><p style=\"margin:0;font-family:Calibri;font-size:11pt;color:black;\">Empirical Bayesian kriging also differs from other kriging methods by accounting for the error introduced by estimating the underlying semivariogram. Other kriging methods calculate the semivariogram from known data locations and use this single semivariogram to make predictions at unknown locations; this process implicitly assumes that the estimated semivariogram is the true semivariogram for the interpolation region. By not taking the uncertainty of semivariogram estimation into account, other kriging methods underestimate the standard errors of prediction.<\/p>\n<p style=\"margin:0;font-family:arial;font-size:10.5pt;color:black;\">\n<p style=\"margin:0;font-family:Calibri;font-size:10.5pt;color:black;\"><span style=\"font-weight:bold;\">Advantages<\/span><\/p>\n<ul style=\"margin-left:.375in;direction:ltr;unicode-bidi:embed;margin-top:0;margin-bottom:0;\" type=\"disc\">\n<li style=\"margin-top:0;margin-bottom:3pt;vertical-align:middle;color:#4d4d4d;\"><span style=\"font-family:Calibri;font-size:11pt;\">Requires minimal interactive modeling<\/span><\/li>\n<li style=\"margin-top:0;margin-bottom:3pt;vertical-align:middle;color:#4d4d4d;\"><span style=\"font-family:Calibri;font-size:11pt;\">Standard errors of prediction are more accurate than other kriging methods<\/span><\/li>\n<li style=\"margin-top:0;margin-bottom:3pt;vertical-align:middle;color:#4d4d4d;\"><span style=\"font-family:Calibri;font-size:11pt;\">Allows accurate predictions of moderately nonstationary data<\/span><\/li>\n<li style=\"margin-top:0;margin-bottom:3pt;vertical-align:middle;color:#4d4d4d;\"><span style=\"font-family:Calibri;font-size:11pt;\">More accurate than other kriging methods for small datasets<\/span><\/li>\n<\/ul>\n<p style=\"margin:0;font-family:Calibri;font-size:11pt;color:black;\"><span style=\"font-weight:bold;\">Disadvantages<\/span><\/p>\n<ul style=\"margin-left:.375in;direction:ltr;unicode-bidi:embed;margin-top:0;margin-bottom:0;\" type=\"disc\">\n<li style=\"margin-top:0;margin-bottom:3pt;vertical-align:middle;color:#4d4d4d;\"><span style=\"font-family:Calibri;font-size:11pt;\">Processing time rapidly increases as the number of input points, the subset size, or the overlap factor increase. Applying a transformation will also increase processing time. These parameters are described below.<\/span><\/li>\n<li style=\"margin-top:0;margin-bottom:3pt;vertical-align:middle;color:#4d4d4d;\"><span style=\"font-family:Calibri;font-size:11pt;\">Processing is slower than other kriging methods, especially when outputting to raster.<\/span><\/li>\n<li style=\"margin-top:0;margin-bottom:3pt;vertical-align:middle;color:#4d4d4d;\"><span style=\"font-family:Calibri;font-size:11pt;\">Cokriging and anisotropy are unavailable.<\/span><\/li>\n<li style=\"margin-top:0;margin-bottom:3pt;vertical-align:middle;color:#4d4d4d;\"><span style=\"font-family:Calibri;font-size:11pt;\">A small number of parameters in the semivariogram model limits the ability to customize. Other kriging methods provide many choices for the semivariogram model.<\/span><\/li>\n<li style=\"margin-top:0;margin-bottom:3pt;vertical-align:middle;color:#4d4d4d;\"><span style=\"font-family:Calibri;font-size:11pt;\">The Log Empirical transformation is particularly sensitive to outliers. If you use this transformation with data that contains outliers, you might receive predictions that are orders of magnitude larger or smaller than the values of your input points. This parameter is described in the &#8220;Transformations&#8221; section below.<\/span><\/li>\n<\/ul>\n<p style=\"margin:0;font-family:Calibri;font-size:11pt;color:red;\">Local fit, especially good for non-stationary data<\/p>\n<ul style=\"margin-left:.375in;direction:ltr;unicode-bidi:embed;margin-top:0;margin-bottom:0;\" type=\"disc\">\n<li style=\"margin-top:0;margin-bottom:0;vertical-align:middle;color:#4d4d4d;\"><span style=\"font-family:Calibri;font-size:11pt;\">Max likelihood simulation to get the semivarigram<\/span><\/li>\n<\/ul>\n<p style=\"margin:0;font-family:Calibri;font-size:11pt;color:#4d4d4d;\">Normal score transformation:<\/p>\n<ul style=\"margin-left:.375in;direction:ltr;unicode-bidi:embed;margin-top:0;margin-bottom:0;\" type=\"disc\">\n<li style=\"margin-top:0;margin-bottom:0;vertical-align:middle;color:#4d4d4d;\"><span style=\"font-family:Calibri;font-size:11pt;\">Log<\/span><\/li>\n<li style=\"margin-top:0;margin-bottom:0;vertical-align:middle;color:#4d4d4d;\"><span style=\"font-family:Calibri;font-size:11pt;\">Log Empirical<\/span><\/li>\n<\/ul>\n<p style=\"margin:0;margin-left:.375in;font-family:Calibri;font-size:11pt;color:black;\">The Log Empirical transformation requires all data values to be positive, and it will guarantee that all predictions will be positive<\/p>\n<ul style=\"margin-left:.375in;direction:ltr;unicode-bidi:embed;margin-top:0;margin-bottom:0;\" type=\"disc\">\n<li style=\"margin-top:0;margin-bottom:0;vertical-align:middle;color:#4d4d4d;\"><span style=\"font-family:Calibri;font-size:11pt;\">None<\/span><\/li>\n<\/ul>\n<p style=\"margin:0;font-family:Calibri;font-size:11pt;color:#4d4d4d;\">Recommended Work Flow for Kriging<\/p>\n<ul style=\"margin-left:.375in;direction:ltr;unicode-bidi:embed;margin-top:0;margin-bottom:0;\" type=\"disc\">\n<li style=\"margin-top:0;margin-bottom:0;vertical-align:middle;color:#4d4d4d;\"><span style=\"font-family:Calibri;font-size:11pt;\">EBK: all default values (baseline)<\/span><\/li>\n<li style=\"margin-top:0;margin-bottom:0;vertical-align:middle;color:#4d4d4d;\"><span style=\"font-family:Calibri;font-size:11pt;\">Kernel smoothing (baseline)<\/span><\/li>\n<li style=\"margin-top:0;margin-bottom:0;vertical-align:middle;color:#4d4d4d;\"><span style=\"font-family:Calibri;font-size:11pt;\">Traditional Kriging (baseline)<\/span><\/li>\n<li style=\"margin-top:0;margin-bottom:0;vertical-align:middle;color:#4d4d4d;\"><span style=\"font-family:Calibri;font-size:11pt;\">EBK: transformation (&amp; change different parameters)<\/span><\/li>\n<\/ul>\n<p style=\"margin:0;font-family:Calibri;font-size:11pt;color:#4d4d4d;\">\u00a0Sometimes there are more than one model that works well, pick the one<\/p>\n<p style=\"margin:0;font-family:Calibri;font-size:11pt;color:black;\">\n<p style=\"margin:0;font-family:Calibri;font-size:11pt;color:black;\">\n<p style=\"margin:0;font-family:Calibri;font-size:11pt;color:black;\">Resources:<\/p>\n<p style=\"margin:0;font-family:Calibri;font-size:11pt;color:black;\">\n<ol style=\"margin-left:.375in;direction:ltr;unicode-bidi:embed;margin-top:0;margin-bottom:0;font-family:Calibri;font-size:11pt;font-weight:normal;font-style:normal;\" type=\"1\">\n<li style=\"margin-top:0;margin-bottom:0;vertical-align:middle;\" value=\"1\"><a href=\"http:\/\/webhelp.esri.com\/arcgisdesktop\/9.2\/pdf\/Geostatistical_Analyst_Tutorial.pdf\"><span style=\"font-family:Calibri;font-size:11pt;\">http:\/\/webhelp.esri.com\/arcgisdesktop\/9.2\/pdf\/Geostatistical_Analyst_Tutorial.pdf<\/span><\/a><\/li>\n<\/ol>\n<p style=\"margin:0;margin-left:.375in;font-family:Calibri;font-size:11pt;color:black;\">Appedix<\/p>\n<p style=\"margin:0;font-family:Calibri;font-size:11pt;color:black;\">\u00a0\u00a02.\u00a0\u00a0\u00a0\u00a0A Practical Guide to Geostatistical Mapping<\/p>\n<\/div><\/div>","protected":false},"excerpt":{"rendered":"<p>Empirical Bayesian kriging also differs from other kriging methods by accounting for the error introduced by estimating the underlying semivariogram. Other kriging methods calculate the semivariogram from known data locations and use this single semivariogram to make predictions at unknown locations; this process implicitly assumes that the estimated semivariogram is &hellip;<\/p>\n","protected":false},"author":2,"featured_media":0,"comment_status":"open","ping_status":"open","sticky":false,"template":"","format":"standard","meta":{"_monsterinsights_skip_tracking":false,"_monsterinsights_sitenote_active":false,"_monsterinsights_sitenote_note":"","_monsterinsights_sitenote_category":0},"categories":[2],"tags":[9],"_links":{"self":[{"href":"https:\/\/career0to1.com\/index.php?rest_route=\/wp\/v2\/posts\/327"}],"collection":[{"href":"https:\/\/career0to1.com\/index.php?rest_route=\/wp\/v2\/posts"}],"about":[{"href":"https:\/\/career0to1.com\/index.php?rest_route=\/wp\/v2\/types\/post"}],"author":[{"embeddable":true,"href":"https:\/\/career0to1.com\/index.php?rest_route=\/wp\/v2\/users\/2"}],"replies":[{"embeddable":true,"href":"https:\/\/career0to1.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcomments&post=327"}],"version-history":[{"count":1,"href":"https:\/\/career0to1.com\/index.php?rest_route=\/wp\/v2\/posts\/327\/revisions"}],"predecessor-version":[{"id":434,"href":"https:\/\/career0to1.com\/index.php?rest_route=\/wp\/v2\/posts\/327\/revisions\/434"}],"wp:attachment":[{"href":"https:\/\/career0to1.com\/index.php?rest_route=%2Fwp%2Fv2%2Fmedia&parent=327"}],"wp:term":[{"taxonomy":"category","embeddable":true,"href":"https:\/\/career0to1.com\/index.php?rest_route=%2Fwp%2Fv2%2Fcategories&post=327"},{"taxonomy":"post_tag","embeddable":true,"href":"https:\/\/career0to1.com\/index.php?rest_route=%2Fwp%2Fv2%2Ftags&post=327"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}