Abstract
Our study explores the use of a range of image processing methods combined with Landsat TM imagery for mapping the morphodynamics of the delta of the Axios River, one of the largest rivers of Greece, between 1984 and 2009. The techniques evaluated ranged from the traditional spectral bands arithmetic operations to unsupervised and supervised classification method. Changes in
coastline morphology and erosion and deposition magnitudes were also estimated from direct photo-interpretation of the TM images, forming our reference dataset. Our analysis, conducted in a GIS environment, showed noticeable changes in the coastline of the study area, with erosion occurring
mostly in the early periods followed by deposition later on. In addition, relatively similar patterns of coastline change were obtained from the different approaches, albeit of different magnitude. The differences observed were largely attributed to the varying ability of the different approaches to utilise the spectral information content of the TM data, strongly linked to the relative strengths and weaknesses underlying the implementation of the different techniques. Notably, supervised classifiers based on machine learning showed the closest results to the photo interpretation of TM, evidencing a promising potential for monitoring shoreline changes over long timescales in a cost-effective and rapid manner
coastline morphology and erosion and deposition magnitudes were also estimated from direct photo-interpretation of the TM images, forming our reference dataset. Our analysis, conducted in a GIS environment, showed noticeable changes in the coastline of the study area, with erosion occurring
mostly in the early periods followed by deposition later on. In addition, relatively similar patterns of coastline change were obtained from the different approaches, albeit of different magnitude. The differences observed were largely attributed to the varying ability of the different approaches to utilise the spectral information content of the TM data, strongly linked to the relative strengths and weaknesses underlying the implementation of the different techniques. Notably, supervised classifiers based on machine learning showed the closest results to the photo interpretation of TM, evidencing a promising potential for monitoring shoreline changes over long timescales in a cost-effective and rapid manner
Original language | English |
---|---|
Journal | Bulletin of the Geological Society of Greece |
Volume | 47 |
Publication status | Published - 2013 |