Evaluating land cover types from Landsat TM using SAGA GIS for vegetation mapping based on ISODATA and K-means clustering
The paper presents the cartographic processing of the Landsat TM image by the two unsupervised classification methods of SAGA GIS: ISODATA and K-means clustering. The approaches were tested and compared for land cover type mapping. Vegetation areas were detected and separated from other land cover t...
| Main Author: | |
|---|---|
| Format: | Article |
| Language: | English |
| Published: |
University of Kragujevac, Faculty of Agronomy, Cacak
2021-01-01
|
| Series: | Acta Agriculturae Serbica |
| Subjects: | |
| Online Access: | https://scindeks-clanci.ceon.rs/data/pdf/0354-9542/2021/0354-95422152159L.pdf |
| _version_ | 1818772957719166976 |
|---|---|
| author | Lemenkova Polina |
| author_facet | Lemenkova Polina |
| author_sort | Lemenkova Polina |
| collection | DOAJ |
| description | The paper presents the cartographic processing of the Landsat TM image by the two unsupervised classification methods of SAGA GIS: ISODATA and K-means clustering. The approaches were tested and compared for land cover type mapping. Vegetation areas were detected and separated from other land cover types in the study area of southwestern Iceland. The number of clusters was set to ten classes. The processing of the satellite image by SAGA GIS was achieved using Imagery Classification tools in the Geoprocessing menu of SAGA GIS. Unsupervised classification performed effectively in the unlabeled pixels for the land cover types using machine learning in GIS. Following an iterative approach of clustering, the pixels were grouped in each step of the algorithm and the clusters were reassigned as centroids. The paper contributes to the technical development of the application of machine learning in cartography by demonstrating the effectiveness of SAGA GIS in remote sensing data processing applied for vegetation and environmental mapping. |
| first_indexed | 2024-12-18T10:17:37Z |
| format | Article |
| id | doaj.art-05274d76c1504b94b16e3bd6154b6624 |
| institution | Directory Open Access Journal |
| issn | 0354-9542 2560-3140 |
| language | English |
| last_indexed | 2024-12-18T10:17:37Z |
| publishDate | 2021-01-01 |
| publisher | University of Kragujevac, Faculty of Agronomy, Cacak |
| record_format | Article |
| series | Acta Agriculturae Serbica |
| spelling | doaj.art-05274d76c1504b94b16e3bd6154b66242022-12-21T21:11:13ZengUniversity of Kragujevac, Faculty of Agronomy, CacakActa Agriculturae Serbica0354-95422560-31402021-01-01265215916510.5937/AASer2152159L0354-95422152159LEvaluating land cover types from Landsat TM using SAGA GIS for vegetation mapping based on ISODATA and K-means clusteringLemenkova Polina0https://orcid.org/0000-0002-5759-1089Université Libre de Bruxelles, École polytechnique de Bruxelles (Brussels Faculty of Engineering), Laboratory of Image Synthesis and Analysis (LISA), Brussels, BelgiumThe paper presents the cartographic processing of the Landsat TM image by the two unsupervised classification methods of SAGA GIS: ISODATA and K-means clustering. The approaches were tested and compared for land cover type mapping. Vegetation areas were detected and separated from other land cover types in the study area of southwestern Iceland. The number of clusters was set to ten classes. The processing of the satellite image by SAGA GIS was achieved using Imagery Classification tools in the Geoprocessing menu of SAGA GIS. Unsupervised classification performed effectively in the unlabeled pixels for the land cover types using machine learning in GIS. Following an iterative approach of clustering, the pixels were grouped in each step of the algorithm and the clusters were reassigned as centroids. The paper contributes to the technical development of the application of machine learning in cartography by demonstrating the effectiveness of SAGA GIS in remote sensing data processing applied for vegetation and environmental mapping.https://scindeks-clanci.ceon.rs/data/pdf/0354-9542/2021/0354-95422152159L.pdfsaga gismappingvegetationk-meansisodataclusteringcartographymachine learning |
| spellingShingle | Lemenkova Polina Evaluating land cover types from Landsat TM using SAGA GIS for vegetation mapping based on ISODATA and K-means clustering Acta Agriculturae Serbica saga gis mapping vegetation k-means isodata clustering cartography machine learning |
| title | Evaluating land cover types from Landsat TM using SAGA GIS for vegetation mapping based on ISODATA and K-means clustering |
| title_full | Evaluating land cover types from Landsat TM using SAGA GIS for vegetation mapping based on ISODATA and K-means clustering |
| title_fullStr | Evaluating land cover types from Landsat TM using SAGA GIS for vegetation mapping based on ISODATA and K-means clustering |
| title_full_unstemmed | Evaluating land cover types from Landsat TM using SAGA GIS for vegetation mapping based on ISODATA and K-means clustering |
| title_short | Evaluating land cover types from Landsat TM using SAGA GIS for vegetation mapping based on ISODATA and K-means clustering |
| title_sort | evaluating land cover types from landsat tm using saga gis for vegetation mapping based on isodata and k means clustering |
| topic | saga gis mapping vegetation k-means isodata clustering cartography machine learning |
| url | https://scindeks-clanci.ceon.rs/data/pdf/0354-9542/2021/0354-95422152159L.pdf |
| work_keys_str_mv | AT lemenkovapolina evaluatinglandcovertypesfromlandsattmusingsagagisforvegetationmappingbasedonisodataandkmeansclustering |