Development of a Shoreline Detection Method Using an Artificial Neural Network Based on Satellite SAR Imagery

Abstract

Monitoring shoreline change is one of the essential tasks for sustainable coastal zone management. Due to its wide coverage and relatively high spatiotemporal monitoring resolutions, satellite imagery based on synthetic aperture radar (SAR) is considered a promising data source for shoreline monitoring. In this study, we developed a robust shoreline detection method based on satellite SAR imagery using an artificial neural network (NN). The method uses the feedforward NN to classify the pixels of SAR imagery into two categories, land and sea. The shoreline location is then determined as a boundary of these two groups of classified pixels. To enhance the performance of the present NN for land–sea classification, we introduced two different approaches in the settings of the input layer that account not only for the local characteristics of pixels but also for the spatial pixel patterns with a certain distance from the target pixel. Two different approaches were tested against SAR images, which were not used for model training, and the results showed classification accuracies higher than 95% in most SAR images. The extracted shorelines were compared with those obtained from eye detection. We found that the root mean square errors of the shoreline position were generally less than around 15 m. The developed method was further applied to two long coasts. The relatively high accuracy and low computational cost support the advantages of the present method for shoreline detection and monitoring. It should also be highlighted that the present method is calibration-free, and has robust applicability to the shoreline with arbitrary angles and profiles.

Synergistic Use of Earth Observation Driven Techniques to Support the Implementation of Water Framework Directive in Europe: A Review

“…Toure et al (2019) [120] studied the shoreline detection using optical remote sensing and state that the shoreline detection problem has still not been adequately solved since the algorithms are sensitive to the type of image, and every method is often adapted to a particular application. Tajima et al (2021) [121] studied the shoreline detection using an ANN and SAR images. The model first classifies the pixels into land and sea and then makes a classification in four layers: an input layer, two hidden layers, and an output layer, where the input layer is based on the pixel values of the SAR image.…”

A New Adaptive Remote Sensing Extraction Algorithm for Complex Muddy Coast Waterline

“…However, it is difficult to choose a suitable growth rule, which can be easily affected by noise and is not suitable for areas with various land cover types [35]. The principle of the neural network-based method simulates the structure and function of the human brain neuron network [36].The human-like thinking can be achieved by establishing a simple model to form different networks according to different linking methods [22]. The recent decades have seen the driving advance of neural networks in various visual recognition fields such as object detection [37,38], image classification [39], and semantic segmentation [40,41].…”

A Deep Learning Based Method to Delineate the Wet/Dry Shoreline and Compute Its Elevation Using High-Resolution UAS Imagery

“…These methods are capable of identifying the wet/dry shoreline, but they are not as accurate as newer machine learning, and deep learning approaches [11]. Many recent studies do combine the use of machine learning or deep learning with satellite imagery [19][20][21][22]. These approaches do obtain more accurate shoreline predictions, but their main limitation is in the use of satellite imagery.…”