An ensemble deep learning based shoreline segmentation approach (WaterNet) from Landsat 8 OLI images. Issue 3 (1st February 2021)

• Record Type: Journal Article
• Authors: Erdem, Firat; Bayram, Bulent; Bakirman, Tolga; Bayrak, Onur Can; Akpinar, Burak
• Is Part Of: Advances in space research. Volume 67:Issue 3(2021)
• Page Start: 964
• Page End: 974
• Publication Date: 2021-02-01
• Subjects: WaterNet -- Ensemble deep learning -- Shoreline segmentation -- Majority voting -- U-Net -- cGAN; Space sciences -- Periodicals; Astronautics -- Periodicals; Geophysics -- Periodicals; 500.505
• DOI: 10.1016/j.asr.2020.10.043
• Languages: English
• ISSNs: 0273-1177

Abstract

Highlights: An ensemble deep learning based shoreline segmentation model called WaterNet is proposed. cGAN based Pix2Pix model has been used for the first time in terms of shoreline segmentation. OSM has been used for the first time in the literature to create a water-body machine learning dataset. Publicly available water-body dataset called YTU-WaterNet is presented: http://www.remotesensinglab.yildiz.edu.tr/ Abstract: Shorelines constantly vary due to natural, urbanization and anthropogenic effects such as global warming, population growth, and environmental pollution. Sustainable monitoring of coastal changes is vital in terms of coastal resource management, environmental preservation and planning. Publicly available Landsat 8 OLI (Operational Land Manager) images provide accurate, reliable, temporal and up-to-date information about coastal areas. Recently, the use of machine learning and deep learning algorithms have become widespread. In this study, we used our public Landsat 8 OLI satellite image dataset to create a majority voting method which is an ensemble automatic shoreline segmentation system (WaterNet) to obtain shorelines automatically. For this purpose, different deep learning architectures have been utilized namely as Standard U-Net, Dilated U-Net, Fractal U-Net, FC-DenseNet, and Pix2Pix. Also, we have suggested a novel framework to create labeling data from OpenStreetMap service to create a unique dataset called YTU-WaterNet. According to the results, IoU and F1 scores have been calculated as 99.59% and 99.79% for the WaterNet. The results indicate that the WaterNet method outperforms other methods in terms of shoreline extraction from Landsat 8 OLI satellite images.