Interpreting Pleistocene glacial features from SPOT HRV data using fuzzy techniques

The ability to correctly identify landform features from remotely sensed im agery is largely determined by pixel size. This spatial scale element is a particularly important consideration for glacial geomorphological feature i dentification when remote sensing data are used for mapping and palaeoenvir onmental reconstruction in mountain environments. It is important to be abl e to clearly delineate the boundaries of glacial landforms. However, in com mon with other phenomena, such features often possess indeterminate boundar ies and many geomorphometric changes occur over short distances. Thus, the use of conventional hard classification techniques may not always be approp riate in glacial terrain mapping where investigators are concerned with ind ividual feature identification. In such situations the ability to examine s ub-pixel scale information by using soft classifiers is potentially more us eful. This paper examines the value of sub-pixel data interpretation derive d from supervised and unsupervised fuzzy modelling techniques for the mappi ng and interpretation of glacial terrains for the wider purposes of glacial reconstruction in the Pindus Mountains of Northwest Greece. This work is p art of a larger study involving field-based investigation of the glacial se diments and landforms. Emphasis has been given to the effective delineation of features from 20 m resolution SPOT HRV imagery. (C) 2000 Elsevier Scien ce Ltd. All rights reserved.