Comparison between a Machine-Learning-Based Method and a Water-Index-Based Method for Shoreline Mapping Using a High-Resolution Satellite Image Acquired in Hwado Island, South Korea

Abstract

Shoreline-mapping tasks using remotely sensed image sources were carried out using the machine learning techniques or using water indices derived from image sources. This research compared two different methods for mapping accurate shorelines using the high-resolution satellite image acquired in Hwado Island, South Korea. The first shoreline was generated using a water-index-based method proposed in previous research, and the second shoreline was generated using a machine-learning-based method proposed in this research. The statistical results showed that both shorelines had high accuracies in the well-identified coastal zones while the second shoreline had better accuracy than the first shoreline in the coastal zones with irregular shapes and the shaded areas not identified by the water-index-based method. Both shorelines, however, had low accuracies in the coastal zones with the shaded areas not identified by both methods.

Coastal Wetland Shoreline Change Monitoring: A Comparison of Shorelines from High-Resolution WorldView Satellite Imagery, Aerial Imagery, and Field Surveys

“…Techniques to reduce this effect are to increase transect frequency or creating curvilinear baselines that closely match the bends of the shoreline, however both options would require a greater time investment for data analyses. Other methodologies for evaluating shoreline changes over time, such as point-based techniques that evaluate distances between shoreline points [59,64], "fuzzy boundaries" techniques [65], Bayesian methods [15], or machine learning [66,67] may be appropriate for the gradual, indistinct boundaries common to wetland and estuarine shorelines. Calkoen et al [68] evaluated machine learning techniques against ordinary least squares regression techniques (the transect-based approach explored here) to predict future shoreline change, but research that evaluates different shoreline extraction methods and their impact on statistical calculation of shoreline change rates for estuarine shorelines is a topic that warrants greater attention.…”

Cuba Surface Estimation From Shoreline Mapping, Generated by Sentinel-2 Image Processing

“…Choung, 2015) and (Y.-J. Choung & Jo, 2017) and the National Oceanic and Atmospheric Administration (NOAA) based the extraction of the coast on the normalized differential water index: NDWI, since they can extract the information more conveniently than any other classification methods. This index maximizing the properties of reflectance of water using green lengths of wave and minimize the low reflectance in the infrared one as well as maximizing the high reflectance of the infrared due to the terrestrial vegetation and the characteristics of the ground, which makes it suitable for delimitation landwater (Emran, Rob, Kabir, & Islam, 2016), and it can calculated by the equation number 1:…”

Study of the Relationship between Urban Expansion and PM10 Concentration Using Multi-Temporal Spatial Datasets and the Machine Learning Technique: Case Study for Daegu, South Korea

“…Machine learning is defined as ""the ability of a machine to improve its performance based on previous results" [16]. The machine learning technique has been widely used of late in remote sensing applications for classifying land uses and detecting the significant features from the remote sensing datasets, due to its advantages for high-value classification [17,18]. SVM, a widely used machine learning technique for finding the linear hyperplane that maximizes the margins between the two clusters in n-dimensional spaces, has been widely used in remote sensing applications due to its superior advantages over the other machine learning techniques for classifying land uses, detecting significant features, and avoiding classification errors [19].…”