Search

Remote sensing is a powerful technique for classifying and quantifying objects. However, the elaborate classification of objects in coastal waters with complex structures is still challenging due to the high possibility of class mixing. The classification through the hyperspectral images can be a reasonable alternative to problems related to such precise classification work because it has high spectral resolution over a wide bandwidth. This study introduced the results of the case study using a novel method to classify green algae on an artificial structure based on hyperspectral data and deep-learning models. The spectral characteristics of the attached green algae on the artificial structure were observed using a ground-based hyperspectral camera. The observed image had a total of three classes (concrete, dense green algae, and sparse green algae). A certain area of the image was used as learning data to create classification models for three classes. The classification models were created from one machine-learning (support vector machine, SVM) and two deep-learning models (convolutional neural network, CNN; and dense convolutional network, DenseNet). As a result, the performance for the classification results of green algae predicted from two deep-learning models was higher than that of the machine-learning model. Additionally, the deep-learning model successfully classified the interface area between concrete and green algae. This study suggests that the combination of hyperspectral data and deep learning could enable more precise classification of objects in coastal areas. [ABSTRACT FROM AUTHOR]

Remote sensing is a powerful technique for classifying and quantifying objects. However, the elaborate classification of objects in coastal waters with complex structures is still challenging due to the high possibility of class mixing. The classification through the hyperspectral images can be a reasonable alternative to problems related to such precise classification work because it has high spectral resolution over a wide bandwidth. This study introduced the results of the case study using a novel method to classify green algae on an artificial structure based on hyperspectral data and deep-learning models. The spectral characteristics of the attached green algae on the artificial structure were observed using a ground-based hyperspectral camera. The observed image had a total of three classes (concrete, dense green algae, and sparse green algae). A certain area of the image was used as learning data to create classification models for three classes. The classification models were created from one machine-learning (support vector machine, SVM) and two deep-learning models (convolutional neural network, CNN; and dense convolutional network, DenseNet). As a result, the performance for the classification results of green algae predicted from two deep-learning models was higher than that of the machine-learning model. Additionally, the deep-learning model successfully classified the interface area between concrete and green algae. This study suggests that the combination of hyperspectral data and deep learning could enable more precise classification of objects in coastal areas.

In recent decades, the growth of urbanization has caused great transformations in the social, economic and morphological aspects in the coastal areas. The urban beaches of Boa Viagem and Pina (Recife-PE) and the beach of Piedade (Jaboatão dos Guararapes-PE), have presented these aspects, where coastal vulnerability to erosion is observed. The objective of this work is to analyze the spatial and temporal displacement of the shoreline. For this, the several data obtained from the kinematic relative geodetic survey method was modeled, which allows the monitoring of the shoreline for the years 2007, 2009, 2010 and 2012. The method of transects was used, which is necessary to adopt a shoreline as base, year 2007. The study area was divided into 6 sectors to analyze the average displacement of the shoreline. Sectors 1 and 5 presented accretion in all periods analyzed (2007-2009, 2007-2010, and 2007-2012). Sector 2 presented erosion in all periods analyzed. The sectors 3 and 6 in the periods 2007-2009 and 2007-2010, presented erosion, while from 2007-2012 they presented the tended to accretion. Stand out that in sector 4 the calculation was not made due to the fact that it is the area that presents rockfill. This study tends to contribute to the analysis of temporal behavior in decision-making projects in coastal environments. [ABSTRACT FROM AUTHOR]