Beach hydromorphological classification through image classification techniques applied to remotely sensed data

Abstract

Evaluation of beach hydromorphological behavior and its classification is extremely complex. Several aerial photographs, using visual interpretation on a GIS environment, were previously used on the identification of coastal hydroforms and hydromorphologies, and to classify beach morphological stage in a selected area of the NW Portuguese coast. The goal of this study is to improve and develop new methodologies to identify coastal features and coastal patterns. In order to achieve that, pixel-based classification and object-oriented classification algorithms were employed, with the aim to identify and analyze morphological features and hydrodynamic patterns and to compare these results with the visual interpretation already performed. The dataset is composed by two aerial photographs (1996 and 2001) and one IKONOS-2 image (2004). The supervised classification algorithms presented good results both for aerial photographs and for IKONOS-2 image, demonstrated by its overall accuracy and Kappa coefficient values. For the two aerial photographs the best results were found for the maximum likelihood classifier and for the IKONOS-2 image the best result was archived with the parallelepiped classifier. The object-oriented classification performance for the aerial photographs was very good, identifying the classes of interest. The results obtained with the IKONOS-2 image were worst.

Remote Sensing Technologies for the Assessment of Marine and Coastal Ecosystems

“…These spectral characteristics can be used to access the major factors affecting water quality in coastal water bodies (e.g. Total Suspended Matter (TSM) and dissolved organic matter (DOM)) (Vanhellemont and Ruddick 2014;Tang et al 2013;Zhu et al 2013Zhu et al , 2014Liew et al 2011;Vantrepotte et al 2011;Nechad et al 2010;Rodríguez-Guzmán and Gilbes-Santaella 2009;Wang 2009;Teodoro et al 2007a, b;Zhou et al 2006;Bustamante et al 2006;Ruddick et al 2003); to identify, characterize and analyze river plumes (Mendes et al 2014;Guneroglu et al 2013;Gonçalves et al 2012;Rudorff et al 2011;Teodoro et al 2009a;Otero et al 2008); to extract estuarine/coastal sandy bodies (Teodoro and Gonçalves 2012;Chowdhury et al 2011;Teodoro et al 2011a, b;Silveira and Heleno 2009;Baptista et al 2008); to identify beach features/patterns (Teodoro 2015;Teodoro et al 2009bTeodoro et al , 2010Teodoro et al , 2011bTeodoro et al , c, 2013Mujabar and Chandrasekar 2012;Harris et al 2011;Pais-Barbosa et al 2009); and to evaluate the changes and integrity (health) of the coastal lagoon habitats (Gutierres 2014;McCarthy and Halls 2014;Bustamante et al 2013;Vahtmäe and Kutser 2013;…”

“…15 Results of: (a) parallelepiped (with MLC as tie breaker); (b) K-Means; and c object-based classification, for the aerial photograph of 1996 (Adapted fromTeodoro et al 2009b) 3 Remote Sensing Technologies for the Assessment of Marine and Coastal Ecosystems…”