COMPARISON OF LANDSAT 8 AND SENTINEL 2 DATA FOR ACCURATE MAPPING OF BUILT-UP AREA AND BARE SOIL

Hits: 39
Research areas:
Year:
2017
Type of Publication:
Article
Keywords:
Sentinel 2, Normalized Built-up Area Index, Band Ratio for Built-up Area, Bare Soil Index, support vector machines
Authors:
Mahesh Pal, Kapil
Abstract:
Accurate mapping of built-up area and bare soil, having similar spectral chracterstics, using remote sensing data is important for urban mapping because of their relationship with environmental quality and urban growth. Landsat 8 and Sentinel 2 data for February 2016 were used to derive three indices: Normalized Built-up Area Index (NBAI), Band Ratio for Built-up Area (BRBA) and Bare Soil Index (BSI) and used in combination of actual images for accurate discrimination between bare soil and built-up area over Kurukshetra (Haryana). Bands 11 and 12 of Sentinel 2 data were resampled to 10 m resolution so as use them with Bands 2, 3, 4 and 8 for indices calculation and further classification. Three different dataset consisting of (1) three indices only (2) six actual bands and (3) combination of 3 indices and 6 bands for both Landsat 8 and Sentinel 2 data were used for classification using four classes i.e. bare soil, built-up area, water and vegetation. Support vector machine classifier was used to classify different combination of images used in this study. A post classification field visit was also carried using different classified image and a GPS set. Comparison of results in terms of area for both built-up area and bare soil using classified images and field visit suggest that Sentinel 2 data consisting of 6 wavebands and three indices was able to better discriminate both classes (12.99 and 27.72 Km2) in comparison to 6 bands and three indices (3.5 and 38.98 Km2) and other combinations using Landsat 8 Data.
Full text: 108.pdf [Bibtex]
You are here: Home ACRS ACRS Overview Proceedings comparison-of-landsat-8-and-sentinel-2-data-for-accurate-mapping-of-built-up-area-and-bare-soil