{"id":380,"date":"2018-05-03T14:35:49","date_gmt":"2018-05-03T12:35:49","guid":{"rendered":"https:\/\/blogs.fu-berlin.de\/reseda\/?page_id=380"},"modified":"2019-07-23T13:35:53","modified_gmt":"2019-07-23T11:35:53","slug":"regression-in-r","status":"publish","type":"page","link":"https:\/\/blogs.fu-berlin.de\/reseda\/regression-in-r\/","title":{"rendered":"Regression in R"},"content":{"rendered":"

Very high-resolution reference data are usually difficult to obtain or only available for small areas of the study area. However, low-resolution data, such as Landsat 8 (30 m), are available in a high spatio-temporal resolution. Using a regression method, we can create sub-pixel information by relating the high-resolution information to very low-resolution Landsat 8 pixels.<\/p>\n

We want to perform a Support Vector Regression in order to regress proportions of imperviousness for each Landsat 8 pixel in Berlin. For this we will use two data sets in this section:<\/p>\n

    \n
  1. a shapefile containing very high-resolution land cover information<\/strong><\/a> (including imperviousness), based on a digitized digital orthophoto of 2016 (Berlin Environmental Atlas<\/a>)<\/li>\n
  2. a Landsat 8 acquisition<\/strong> <\/a>(ID: LC08_L1TP_193023_20170602_20170615_01_T1), which you may already have acquired during the L8 Download Exercise<\/a><\/li>\n<\/ol>\n

    \"\"<\/a><\/p>\n

    Landsat 8 scene overlaid by the shapefile (colored by classes) in QGIS. The different detail levels become very clear in this visualization<\/span><\/div>\n
    \n

    Section in a Box<\/h1>\n

    Prepare the samples for training<\/strong><\/a>
    \n– learn how to preprocess your shapefile
    \n– extract raster features and percentages of your target class (e.g., imperviousness)
    \n– create your training data set for regression analysis
    \n    SVM Regression<\/strong><\/a>
    \n– learn how to perform a Support Vector Regression (SVR) in R using the e1071 package
    \n– predict the whole image data based on your regression model<\/p>\n<\/div>\n

     <\/p>\n

    \n
    NEXT<\/em><\/strong><\/span>
    \n    PREPARE SAMPLES FOR REGRESSION<\/em><\/strong><\/span><\/a><\/div>\n

     <\/p>\n","protected":false},"excerpt":{"rendered":"

    Very high-resolution reference data are usually difficult to obtain or only available for small areas of the study area. However, low-resolution data, such as Landsat 8 (30 m), are available in a high spatio-temporal resolution. Using a regression method, we can create sub-pixel information by relating the high-resolution information to very low-resolution Landsat 8 pixels. … Continue reading “Regression in R”<\/span><\/a><\/p>\n","protected":false},"author":3237,"featured_media":0,"parent":0,"menu_order":0,"comment_status":"closed","ping_status":"closed","template":"","meta":{"footnotes":""},"class_list":["post-380","page","type-page","status-publish","hentry"],"_links":{"self":[{"href":"https:\/\/blogs.fu-berlin.de\/reseda\/wp-json\/wp\/v2\/pages\/380","targetHints":{"allow":["GET"]}}],"collection":[{"href":"https:\/\/blogs.fu-berlin.de\/reseda\/wp-json\/wp\/v2\/pages"}],"about":[{"href":"https:\/\/blogs.fu-berlin.de\/reseda\/wp-json\/wp\/v2\/types\/page"}],"author":[{"embeddable":true,"href":"https:\/\/blogs.fu-berlin.de\/reseda\/wp-json\/wp\/v2\/users\/3237"}],"replies":[{"embeddable":true,"href":"https:\/\/blogs.fu-berlin.de\/reseda\/wp-json\/wp\/v2\/comments?post=380"}],"version-history":[{"count":13,"href":"https:\/\/blogs.fu-berlin.de\/reseda\/wp-json\/wp\/v2\/pages\/380\/revisions"}],"predecessor-version":[{"id":2954,"href":"https:\/\/blogs.fu-berlin.de\/reseda\/wp-json\/wp\/v2\/pages\/380\/revisions\/2954"}],"wp:attachment":[{"href":"https:\/\/blogs.fu-berlin.de\/reseda\/wp-json\/wp\/v2\/media?parent=380"}],"curies":[{"name":"wp","href":"https:\/\/api.w.org\/{rel}","templated":true}]}}