2.3. Image Preprocessing and Classification Methods
This protocol is extracted from research article:
Land Use/Land Cover Change and Its Driving Forces in Shenkolla Watershed, South Central Ethiopia
ScientificWorldJournal, Feb 18, 2021; DOI: 10.1155/2021/9470918

All satellite images were geometrically corrected to the Universal Transfer Mercator coordinate system and georeferenced to the data in which Ethiopia has selected by the WGS (World Geodetic System) (zone 84). Moreover, preprocessing activity such as radiometric correction and a false color grid composite image are developed before classifying the images [29, 30].

Image classification was carried out by sorting pixels into a finite number of individual categories of data based on their data file values [3133]. All pixels in an image were placed into LU/LC classes to draw out useful thematic information [34]. First, unsupervised classification was used to get the major land parcels, which then used for supervised classification. A total of 150 training sites were selected based on image interpretation keys during the field survey and from interviews with the local inhabitants. Reference points in different land use/land cover types were randomly recorded during the field survey using a hand-held Global Position System (GPS) for the 2017 images, the same as the procedure followed by [35, 36]. Supervised classification with maximum likelihood algorithm was used to classify the individual images independently using the ground control points collected from each LU/LC category [37, 38]. ArcGIS 10.3 and QGIS v 3.0 software were used for overall image processing. The way of classification of this study was adopted in such a way that it suits the purpose of the study. Finally, two land use/land cover classes were identified using independent classification of individual images from different dates for the same geographic location. These include agricultural land and forestland. The dispersed rural settlement and small scattered plots of grazing land were categorized as agricultural land use class. Land use/land cover classes of Shenkolla watershed and the corresponding description are displayed in Table 2.

Descriptions of land use/land cover types for the period 1973–2017.

Note: The content above has been extracted from a research article, so it may not display correctly.

Please log in to submit your questions online.
Your question will be posted on the Bio-101 website. We will send your questions to the authors of this protocol and Bio-protocol community members who are experienced with this method. you will be informed using the email address associated with your Bio-protocol account.

We use cookies on this site to enhance your user experience. By using our website, you are agreeing to allow the storage of cookies on your computer.