30 m Land Cover Dataset of Sri Lanka (2018)
ZHONG Bo1HU Longfei1WU Junjun1YANG Aixia1
1 State Key Laboratory of Remote Sensing Science,Aerospace Information Research Institute,Chinese Academy of Sciences,Beijing 100101,China
DOI:10.3974/geodb.2020.09.06.V1
Published:Dec. 2020
Visitors:8608 Data Files Downloaded:225
Data Downloaded:1893.06 MB Citations:
Key Words:
land cover classification,Landsat,Sri Lanka,random forest,supervised classification
Abstract:
30 m land cover dataset of Sri Lanka (2018) was developed based on Landsat OLI data, combined with the vegetation index, water index, gray level co-occurrence matrix of similarity and the homogeneity characteristic. Sample points were selected based on pixels, and the supervised classification was conducted using random forest classifier, seven main land cover types in Sri Lanka were identified, including farmland, forest, grassland, wetland, water, artificial surface and bare land. The overall accuracy is about 0.85. The spatial resolution is 30 m. The dataset is archived in .tif data format, and consists of 3 data files with data size of 479 MB (compressed into one single file with 8.41 MB).
Foundation Item:
Ministry of Science and Technology of P. R. China (2018YFA0605500); Chinese Academy of Sciences (2020)
Data Citation:
ZHONG Bo, HU Longfei, WU Junjun, YANG Aixia. 30 m Land Cover Dataset of Sri Lanka (2018)[J/DB/OL]. Digital Journal of Global Change Data Repository, 2020. https://doi.org/10.3974/geodb.2020.09.06.V1.
References:
GADM data (version 3.6),https://gadm.org/download_country_v3.html.
     
Data Product:
ID |
Data Name |
Data Size |
Operation |
1 |
SriLanka_Landcover_2018.rar |
8615.53KB |
|