Unsupervised Classification and Polygonization With QGis - Revision history

Smitch: /* Video Walkthrough */

2022-01-06T20:24:50Z

Video Walkthrough

NathanByerley: /* Map Production */

2021-12-23T21:58:07Z

Map Production

NathanByerley: /* Editing and Merging Polygons */

2021-12-23T21:55:47Z

Editing and Merging Polygons

NathanByerley: /* Field Calculator */

2021-12-23T21:53:28Z

Field Calculator

NathanByerley: /* Unsupervised Classification and Filtering */

2021-12-23T21:50:16Z

Unsupervised Classification and Filtering

NathanByerley: /* Trim to Mask Area */

2021-12-23T21:43:12Z

Trim to Mask Area

NathanByerley: /* Importing and Displaying Data */

2021-12-23T21:41:35Z

Importing and Displaying Data

NathanByerley: /* Acquiring Data */

2021-12-23T21:37:46Z

Acquiring Data

NathanByerley: /* Introduction */

2021-12-23T21:34:31Z

Introduction

NathanByerley: /* Introduction */

2021-12-23T21:33:48Z

Introduction

@@ Line 1: / Line 1: @@
 If you have any trouble with any part of this tutorial please view the video walkthrough.<br>
 == Video Walkthrough ==
-If you would like a video walkthrough please follow this link to YouTube! <br/>
+This document is a companion to the video walkthrough available on YouTube! <br/>
 https://youtu.be/H06wWFFNtgU
+In some places, extra details that were not covered in the video are added here.
 == Introduction ==
 There are lots of reasons for wanting to make a land cover classification. Whether that is to make beautiful maps, a temporal study of land cover or a more complicated statistical analysis. The goal of this tutorial is to be a jumping off point into the profound and complicated world of classifications.</br></br>

@@ Line 129: / Line 129: @@
 Before making a map now is a good time to change the display colours of the classification. To do this go to symbology and select a new colour for every category.<br>
 To make a map got to project-> new print layout-> name the layout-> hit ok. <br>
-Next step is to add the map to the layout. Add item-> add map-> click and drag to draw the map perimeter. You can turn layers on and off from the layer tab in the main QGis window because the map will auto update.<br>
+Next step is to add the map to the layout. Add item-> add map-> click and drag to draw the map perimeter. You can turn layers on and off from the layer tab in the main QGis window and the map will auto update.<br>
 There is a wide variety of tools to make the map more appealing. Some important items to add can be found in the add item tab. <br>
 Some good items to include:<br>
@@ Line 136: / Line 136: @@
 North Arrow<br>
 Title(label)<br>
-Please see the video walk though for more details about map creation.
+Please see the video walk though for more details about map creation. There are also lots of other good resources out there for map creation.<br><br>
+Congratulations! You have completed this unsupervised classification tutorial!
 == Resources ==

@@ Line 123: / Line 123: @@
 The land cover field also needs to be updated because it will not update automatically. Open up the field calculator again and update the land cover field. Simply copy and paste in the same formula you used the first time to assign the land cover names. field CASE WHEN  "DN" IS 1 THEN 'Land' WHEN "DN" IS 2 THEN 'Bound' WHEN  "DN" IS 4 THEN 'Water' ELSE 'Ice' END -> click ok.<br>
 Hit the save button at the top of the attribute table and hit toggle editing to turn off editing.<br><br>
-The classified region is still being displayed based on its DN values so to make it easily interpreted, go back into symbology, change the value to the land cover field, it classify and then ok. This is the same process you did earlier. If you had two different types of ice like me this will now cause them to be displayed as the same colour. With the the two different types of ice being the same colour, the region looks very crowded. This can be helped by merging the polygons into a bigger polygon.<br>
+The classified region is still being displayed based on its DN values so to make it easily interpreted, go back into symbology, change the value to the land cover field, hit classify and then ok. This is the same process you did earlier. If you had two different types of ice like me this will now cause them to be displayed as the same colour. With the the two different types of ice being the same colour, the region looks very crowded. This can be helped by merging the polygons into a bigger polygon.<br>
 Select the polygons you want to merge (either from the map or attribute table)-> toggle on editing-> Right click on any tool bar and make sure to activate your digitizing tool bar as well as your advanced digitizing tool bar-> merge selected features (on the advanced digitizing tool bar)-> click ok. This will merge the features.

@@ Line 107: / Line 107: @@
 == Field Calculator ==
-To get some more useful information from this new poligonized classification right click on the layer and open up the attribute table. The DN field is corresponds to the number of the land cover from the raster version of the classification but that is difficult to understand at a glance so we are going to add a new field that displays the name of the land cover type.<br>
+To get some more useful information from this new poligonized classification right click on the layer and open up the attribute table. The DN field corresponds to the number of the land cover from the raster version of the classification but that is difficult to understand at a glance so we are going to add a new field that displays the name of the land cover type.<br>
-Open field calculator (from the attribute table screen)->Create new field-> name it land cover-> Output field type, text (string). In the expression box type in: CASE WHEN  "DN" IS 1 THEN 'Land' WHEN "DN" IS 2 THEN 'Bound' WHEN  "DN" IS 4 THEN 'Water' ELSE 'Ice' END <br>
+Open field calculator (from the attribute table screen)->Create new field-> name it landcover-> Output field type, text (string). In the expression box type in: CASE WHEN  "DN" IS 1 THEN 'Land' WHEN "DN" IS 2 THEN 'Bound' WHEN  "DN" IS 4 THEN 'Water' ELSE 'Ice' END <br>
 This expression will correspond all the DN values to a name that the field calculator will put in a new field. Change the numbers as necessary for you classification as it may not end up being identical to mine. Click ok.<br>
 this will add a new field with a land cover name for every polygon.<br><br>
 The SCP tool classifies a box round the entire region and now is a good time to get rid of that:<br>
 Click on the title for the field we just made, this will sort by name-> click on toggle editing in the attribute table-> select all the rows you want to delete (in my case everything named bound)-> hit the delete features button.<br><br>
-Now we will calculate another field, this field will calculate the area for each polygon. Once again open up the field calculator.:<br>
+Now we will calculate another field, this field will calculate the area for each polygon. Once again open up the field calculator:<br>
 Create a new field-> name it area-> Output field type (decimal number)-> Open geometry tab, select $area (alternatively type $area into the expression box)-> click ok.<br>
 A new column with the area for each polygon will be calculated. The attribute table can be exported as a CSV for further analysis. To do this:<br>

@@ Line 86: / Line 86: @@
 == Unsupervised Classification and Filtering==
 Time to classify the image. You need the SCP tool. To download it go to:<br>
-Plugins-> manage nd install plugins-> search up scp-> select the semi-automatic classification plugin-> install-> close.<br>
+Plugins-> manage and install plugins-> search up scp-> select the semi-automatic classification plugin-> install-> close.<br>
 to use the SCP tool:
-SCP->Band set. This will open the tool. Under the Multiband image lost option right at the top go to the drop down menu and select the Clipped (mask) band created. Hit the refresh button on the right (second from the top), select all the bands and hit the Add bands to bandset button. Those steps will bring all the bands into the tool.<br>
+SCP->Band set. This will open the tool. Under the Multiband image list option right at the top, go to the drop down menu and select the Clipped (mask) band created. Hit the refresh button on the right (second from the top), select all the bands and hit the Add bands to bandset button. Those steps will bring all the bands into the tool.<br>
-Next step is to go to the clustering tab in to tool.<br>
+Next step is to go to the clustering tab in the tool.<br>
 The inputs will be:<br>
 method: K-means<br>
@@ Line 97: / Line 97: @@
 SCP will classify a box around the buffer, don't worry we will take care of that later<br>
 I ended up with 5 classes: water, land, box around the buffer and two types of ice.<br>
-There might be some noise speckling in the classification and classes where there shouldn't be, this is likely due to noise in the imagery. To remove the noise open up the SCP tool again:<br>
+There might be some speckling in the classification; tiny regions of different classifications, this is likely due to noise in the imagery. To remove the noise open up the SCP tool again:<br>
 post processing tab-> Classification sieve. Set the threshold to 25 (makes the smallest area classified 25 pixels) and set the pixel connection to 8 (this means pixels touching on the diagonal are considered connected and in one cluster). Hit Run. You will be prompted to save the output, name it and hit save. The effect this will have is a more smoothed out classification.

@@ Line 83: / Line 83: @@
 Raster-> Extraction-> Clip raster by mask layer<br>
 Input layer will be the virtual raster, mask layer will be the buffer. Click run.<br>
-There we go the raster has been clipped.
 == Unsupervised Classification and Filtering==

@@ Line 37: / Line 37: @@
 == Importing and Displaying Data ==
-To import data, launch QGis and create a new project. once the project it loaded go to the rater tab at the top: <br>
+To import data, launch QGis and create a new project. Once the project is loaded go to the rater tab at the top: <br>
 Raster-> miscellaneous -> Build Virtual Raster. This will open up the build virtual raster tool. Click the thee dots beside the input layers tab. <br>
 The input layers are going to be everything that was extracted from the .tar file. To do this use the: <br/>
@@ Line 56: / Line 56: @@
 B10.TIF<br>
 B11.TIF<br>
-Each file represents a different wavelength that the sensor collected. Landsat 8 uses a multispectral sensor so it collects the light spectrum across 11 wave lengths from blue to infrared. For instance B2 is blue, B3 is green, B4 is red NIR is B5 and thermal infrared is B11.You can use the various bands to your advantage, for instance if you use just band 6 which is a type of infrared, water absorbs so much of that band that it appears black. This could be really helpful for identifying how much water is in an area. Check out the USGS website for more information:https://www.usgs.gov/faqs/what-are-band-designations-landsat-satellites?qt-news_science_products=0#qt-news_science_products<br>
+Each file represents a different wavelength that the sensor collected. Landsat 8 uses a multispectral sensor so it collects the light spectrum across 11 wave lengths from blue to infrared. For instance, B2 is blue, B3 is green, B4 is red, B4 is NIR and B11 is thermal infrared. You can use the various bands to your advantage, for instance with band 6 which is a type of infrared, water absorbs so much of that band that it appears black. This could be really helpful for identifying how much water is in an area. Check out the USGS website for more information:https://www.usgs.gov/faqs/what-are-band-designations-landsat-satellites?qt-news_science_products=0#qt-news_science_products<br>
 With all the correct bands selected hit the ok button.<br>
 Change the resolution to highest<br>
 Check the box for place each band in separate band file.<br>
 Click run<br>
-The image should be displayed in the QGis project. The colouring might look weird and that is because it is currently a false colour composite. To change it to a natural colour composite<br>
+The image should be displayed in the QGis project. The colouring might look weird and that is because it is currently a false colour composite. To change it to a natural colour composite:<br>
 Right click on the Virtual layer-> select properties-> select symbology<br>
 Select Band 04 for red<br>

@@ Line 14: / Line 14: @@
 == Acquiring Data ==
-For this tutorial pretty much any remote sensing data can be used. Depending on what data it it it may require pre-processing in order to produce a usable product, and that is outside the scope of this tutorial. <br/> <br/>
+For this tutorial pretty much any remote sensing data can be used. Depending on what data it is, it may require pre-processing in order to produce a usable product, and that is outside the scope of this tutorial. <br/> <br/>
-A good resource for free remote sensing data us the USGS Earth explorer. It involves making an account but it is such a good resource for remote sensing data that it is completely worth the extra step. <br/> <br/>
+A good resource for free remote sensing data is the USGS Earth explorer. It involves making an account but it is such a good resource for remote sensing data that it is completely worth the extra step. <br/> <br/>
 Sign up here https://ers.cr.usgs.gov/login <br/> <br/>
 Now that you have made an account or signed into your existing account it is time to find the data to use.<br/>
-You can use pretty much whatever data you see fit but Landsat8 is a very common choice and so that is what's being used in this tutorial. That being said the first step is to select which data set you want to use. To get to Landsat 8 image used in this tutorial select Landsat ->Landsat Collection 2 Level-1 ->Landsat 8 OLI/TIRS C2 L1 </br></br>
+You can use pretty much whatever data you see fit but Landsat8 is a very common choice and so that is what's being used in this tutorial. That being said, the first step is to select which data set you want to use. To get to the Landsat 8 image used in this tutorial select Landsat ->Landsat Collection 2 Level-1 ->Landsat 8 OLI/TIRS C2 L1 </br></br>
-The next step is to pick the additional criteria. In this tutorial the image used was LC08_L1TP_046007_20200722_20200911_02_T1 this code can be copy and pasted into the "Landsat Product Identifier L1" text box. <br/><br/>
+The next step is to pick the additional criteria. In this tutorial the image used was LC08_L1TP_046007_20200722_20200911_02_T1 this name can be copy and pasted into the "Landsat Product Identifier L1" text box. <br/><br/>
 Next step is to click results.<br/><br/>
@@ Line 27: / Line 27: @@
 The results should bring up one image. Click on the footprint icon to show where it is on the world map (should be in northern Canada).<br/><br/>
-To download the image click on the download icon, the one with the little green arrow four icons left of the footprint.<br/><br/>
+To download the image click on the download icon, which the one with the little green arrow four icons left of the footprint.<br/><br/>
-Select the product options and right at the top click on the download button for the entire Landsat 8 Collection 2 Level-1 Product Bundle. It should be a big file (1.13 Gigabytes)
+Select the product options right at the top, click on the download button for the entire Landsat 8 Collection 2 Level-1 Product Bundle. It should be a big file (1.13 Gigabytes)
 == Unzipping Data ==

@@ Line 5: / Line 5: @@
 https://youtu.be/H06wWFFNtgU
 == Introduction ==
-There are lots of reasons for wanting to make a land cover classification. Whether that is to make beautiful maps, a temporal study of land cover or a more complicated statistical analysis. The goal of this tutorial is to be a jumping off point so to speak into the profound and complicated world of classifications.</br></br>
+There are lots of reasons for wanting to make a land cover classification. Whether that is to make beautiful maps, a temporal study of land cover or a more complicated statistical analysis. The goal of this tutorial is to be a jumping off point into the profound and complicated world of classifications.</br></br>
-In this tutorial we will be looking at how to perform an unsupervised classification; that is, a classification where the computer program chooses the classes without a training data set
+In this tutorial we will be looking at how to perform an unsupervised classification; that is, a classification where the computer program chooses the classes without a training data set.
 == Programs and Plugins Required ==