Multispectral satellite imagery and machine learning for the extraction of shoreline indicators

McAllister, Emma; Payo, Andrés; Novellino, Alessandro; Dolphin, Tony; Medina-López, Encarni

doi:10.1016/j.coastaleng.2022.104102

Cited by 76 publications

(40 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…A variety of deep-learning-based image segmentation and classification methods have been applied to characterize coastal landforms and covers, sediments, hydrodynamics, shorelines, beach erosional and morphodynamic states (e.g., Luijendijk et al, 2018;Buscombe and Carini, 2019;Ellenson et al, 2020, Buscombe andDang et al, 2020;den Bieman et al, 2020;Gray et al, 2021;McAllister et al, 2022;Buscombe and Goldstein, in review). Image segmentation, whereby each pixel is classified into predetermined classes (e.g., 'sand,' 'water,' 'vegetation'; see Figure 3), facilitates spatially explicit mapping of coastal environments.…”

Section: Satellite Image Classification Segmentation and Regressionmentioning

confidence: 99%

The future of coastal monitoring through satellite remote sensing

Vitousek

Buscombe

Vos

et al. 2022

Camb. prisms Coast. futures

View full text Add to dashboard Cite

Satellite remote sensing is transforming coastal science from a 'data-poor' field into a 'data-rich' field. Sandy beaches are dynamic landscapes that change in response to long-term pressures, short-term pulses, and anthropogenic interventions. Until recently, the rate and breadth of beach change has outpaced our ability to monitor those changes, due to the spatiotemporal limitations of our observational capacity. Over the past several decades, only a handful of beaches worldwide have been regularly monitored with accurate yet expensive in-situ surveys. The longterm coastal-change data of these few well-monitored beaches have led to in-depth understanding of many site-specific coastal processes. However, because the best-monitored beaches are not representative of all beaches, much remains unknown about the processes and fate of the other >99% of unmonitored beaches worldwide. The fleet of Earth-observing satellites has enabled multiscale monitoring of beaches, for the very first time, by providing imagery with global coverage and up to daily frequency. The long-standing and ever-expanding archive of satellite imagery will enable coastal scientists to investigate coastal change at sites vulnerable to future sea-level rise, i.e., (almost) everywhere. In the past decade, our capability to observe coastal change from space has grown substantially with computing and algorithmic power. Yet, further advances are needed in automating monitoring using machine learning, deep learning, and computer-vision to fully leverage this massive treasure-trove of data. Extensive

show abstract

Section: Satellite Image Classification Segmentation and Regressionmentioning

confidence: 99%

The future of coastal monitoring through satellite remote sensing

Vitousek

Buscombe

Vos

et al. 2022

Camb. prisms Coast. futures

View full text Add to dashboard Cite

show abstract

Section: High Frequency Remote Sensing Data: S2 Gee and Ndwimentioning

confidence: 99%

“…According to McAllister et al, the use of S2 for shoreline extraction through water and non-water pixels between 2006 and 2021 revealed a better performance of water indices and thresholding [68]. Among indices, NDWI and MNDWI are the most commonly used due to their optimized performance [43,44,49,51,69], having been subjected to different modifications [70], while thresholding is widely considered to be the simplest method of image segmentation [68]. We used the first NDWI defined by McFeeters [45], as MNDWI enhances the performance for coastal shadows (e.g., cliffs) and it can reveal more detail in open water [68,70], our study being focused on flat beaches and sand spit morphologies along the coast.…”

Section: High Frequency Remote Sensing Data: S2 Gee and Ndwimentioning

confidence: 99%

“…Among indices, NDWI and MNDWI are the most commonly used due to their optimized performance [43,44,49,51,69], having been subjected to different modifications [70], while thresholding is widely considered to be the simplest method of image segmentation [68]. We used the first NDWI defined by McFeeters [45], as MNDWI enhances the performance for coastal shadows (e.g., cliffs) and it can reveal more detail in open water [68,70], our study being focused on flat beaches and sand spit morphologies along the coast. Regarding NDWI threshold, this study revealed an optimized 0.1 value for single images, while the threshold value of 0 revealed less data noise for long temporal statistics.…”

Section: High Frequency Remote Sensing Data: S2 Gee and Ndwimentioning

confidence: 99%

See 1 more Smart Citation

Monitoring Sand Spit Variability Using Sentinel-2 and Google Earth Engine in a Mediterranean Estuary

Roca

Navarro

Sanabria³

et al. 2022

Remote Sensing

View full text Add to dashboard Cite

Estuarine degradation is a major concern worldwide, and is rapidly increasing due to anthropogenic pressures. The Mediterranean Guadiaro estuary, located in San Roque (Cadiz, Spain), is an example of a highly modified estuary, showing severe negative effects of eutrophication episodes and beach erosion. The migration of its river mouth sand spit causes the closure of the estuary, resulting in serious water quality issues and flora and fauna mortality due to the lack of water renewal. With the aim of studying the Guadiaro estuary throughout a 4-year period (2017–2020), the Sentinel-2 A/B twin satellites of the Copernicus programme were used thanks to their 5-day and 10 m temporal and spatial resolution, respectively. Sea–land mapping was performed using the Normalized Difference Water Index (NDWI) in the Google Earth Engine (GEE) platform, selecting cloud-free Sentinel-2 Level 2A images and computing statistics. Results show a closure trend of the Guadiaro river mouth and no clear sand spit seasonal patterns. The study also reveals the potential of both Sentinel-2 and GEE for estuarine monitoring by means of an optimized processing workflow. This improvement will be useful for coastal management to ensure a continuous and detailed monitoring in the area, contributing to the development of early-warning tools, which can be helpful for supporting an ecosystem-based approach to coastal areas.

show abstract

“…Due to nearshore hydrodynamic processes (e.g., ocean waves, tides, and currents, among others), it is difficult to obtain the precise location of shorelines on a large scale. Therefore, the shoreline indicator is widely used as a proxy to represent the "true" shoreline location (Boak and Turner, 2005;McAllister et al, 2022). There are many physical features that can be used as shoreline indicators, which include vegetable line, debris line, wet/dry boundaries, high water line (HWL), mean high water line (MHWL), instantaneous high water line (IHWL), and low water line (LWL) (Zhang and Hou, 2020).…”

Section: Introductionmentioning

confidence: 99%

Characteristics of shoreline changes around the South China Sea from 1980 to 2020

Cui

Yan²,

He³

et al. 2022

Front. Mar. Sci.

View full text Add to dashboard Cite

As one of the most sensitive factors in the sea–land interaction zone, the shoreline is significantly influenced by natural processes and anthropogenic activities. Monitoring long-term shoreline changes offers a basis for the integrated management and protection of coastal zones. The spatiotemporal distribution and the utilization types of shorelines had changed a lot, along with the advancement of the socioeconomics of the countries around the South China Sea (SCS) since 1980. However, the changes in shoreline characteristics for a long time around the whole SCS under anthropogenic influence remain uncertain. Using Landsat and high-resolution satellite images, this study monitored the changes in the spatial location and type of shorelines around the SCS from 1980 to 2020. Additionally, the possible reasons for the shoreline changes around the SCS were analyzed. The results showed the following: 1) the length of shorelines around the SCS maintained growth, especially in the 1990s, which increased by 734.8 km, from 28,243.8 km (1990) to 28,978.6 km (2000). 2) The proportion of natural shorelines around the SCS decreased from 92.4% to 73.3% during the past 40 years. Bedrock and mangrove shorelines disappeared most sharply by 34.2% and 21.6%, respectively. The increase of artificial shorelines was mostly driven by the expansion of constructed and aquaculture dikes. 3) The spatial location changes of most artificial shorelines can be attributed to seaward advancement, with an average advancing speed of 7.98 m/year. Of the natural shorelines, 58.4% changed in terms of their location (30.4% advancement and 28.0% retreat). Most natural shorelines around the SCS were threatened by erosion, but the extent of which was largely determined by the shorelines’ own stability, with less influence from the surrounding environment. Artificialization was the most prominent feature of shorelines around the SCS over the past 40 years, which was closely related to the original types of shorelines and the socioeconomic conditions of the area where they are located, and often accompanied by dramatic changes in shoreline morphology and spatial location. In addition, human interventions were not only the dominant factor in shoreline artificialization but also a major driver of natural shoreline protection.

show abstract

Multispectral satellite imagery and machine learning for the extraction of shoreline indicators

Cited by 76 publications

References 66 publications

The future of coastal monitoring through satellite remote sensing

The future of coastal monitoring through satellite remote sensing

Monitoring Sand Spit Variability Using Sentinel-2 and Google Earth Engine in a Mediterranean Estuary

Characteristics of shoreline changes around the South China Sea from 1980 to 2020

Contact Info

Product

Resources

About