Determining the extent and spectral separability of industrially despoiled land in South Wales from satellite sensor data

Abstract

Satellite remote sensing offers the potential to accurately identify and monitor spectrally separable land-cover classes at a range of spatial and temporal scales. This paper investigates the separability of despoiled land in imagery acquired by sensors carried by the Landsat satellites. These systems offer the opportunity to map areas at large to medium scales at a relatively high temporal frequency and so provide information on environmental quality necessary for many monitoring and planning activities. From an investigation using imagery of South Wales it was found that despoiled land was separable from other classes in the Landsat TM imagery, with an accuracy of over 90 per cent. Furthermore, with Landsat TM data three spectral wavebands were found to provide a level of separability similar to that based on all wavebands available, illustrating potential savings to the analyst. Despoiled land cover was classified from Landsat TM and MSS data and these classifications were evaluated against a manually produced map of despoiled land cover derived from the interpretation of aerial photographs. Estimates of the extent of despoiled land cover in administrative units derived from the Landsat TM data were significantly correlated ( r = 0-81) with the map based estimates, although a weaker correlation was observed with Landsat MSS data.