Urban Sprawl Mapping and Land Use Change Detection Analysis

Abstract

Hasty changes occurred in the land use and land cover of Coimbatore city corporation, Tamil Nadu within 32 years span (1984 -2016). Agricultural and forest lands are mainly converted into urban areas generally in an unplanned way which is making a change in dynamics of urban sprawl characteristics. The principal aim of this study is to use remote sensing data, geospatial tools to detect, quantify, analyze the urban land use changes of Coimbatore city, located in the western part of the Tamil Nadu. This study emphases on urban growth analyses and urban sprawl of Coimbatore city. In 2016, the jurisdiction of the Coimbatore Corporation was increased from 72 to 100 wards and five zones which consist area of 365.74Sq.Km. The corporation limit was extended from 29.25Sq.Km. in 1984 to 365.74 Sq. Km. in 2016 which has a growth of 1150 percent area of 1984. Various GIS layers such as Ward, Zone, Corporation boundaries, Road and railway network, Waterbody, Stream, Major locations and Land use / land cover including built-up area; agricultural land; water bodies; industrial area; educational area, and Public & Semi-public area were generated from Coimbatore Corporation map and Remote sensing imagery. This study revealed that Land use/Land cover areas such as agricultural, commercial, educational, industrial , public and semi-public, residential areas and water bodies occupied 9.38, 2.20, 5.0, 3.1, 1.02, 77.37 and 1.93 percentage areas of the city respectively in the year 2016. Land use pattern change was confirmed by field verification study in some places like near Gandhipuram, Brooke Fields, Avinashi Road, etc.

Unsupervised ISODATA algorithm classification used in the landsat image for predicting the expansion of Salem urban, Tamil Nadu

“…Then the land cover class is identified by comparing the classified spectral classes with the corresponding reference data. But in supervised classification, an analyst uses previously acquired knowledge of an area, or a priori knowledge, to locate specific areas, or training sites, which represent homogeneous samples of known land use and/or land cover types (12,13) . Based on statistics of these training sites, each pixel in an image is then assigned to a user-defined land use type (residential, industrial, agriculture, etc.)…”