How the Combination of Satellite Remote Sensing with Artificial Intelligence Can Solve Coastal Issues

Accurate bathymetric data is crucial for marine and coastal ecosystems. A lot of studies have been carried out for nearshore bathymetry using satellite data. The approach adopted extensively in shallow water depths estimation has recently been one of empirical models. However, the linear empirical model is simple and only takes limited band information at each bathymetric point into consideration. It may be not suitable for complex environments. In this paper, a deep learning framework was proposed for nearshore bathymetry (DL-NB) from ICESat-2 LiDAR and Sentinel-2 Imagery datasets. The bathymetric points from the spaceborne ICESat-2 LiDAR were extracted instead of in situ measurements. By virtue of the two-dimensional convolutional neural network (2D CNN), DL-NB can make full use of the initial multi-spectral information of Sentinel-2 at each bathymetric point and its adjacent areas during the training. Based on the trained model, the bathymetric maps of several study areas were produced including the Appalachian Bay (AB), Virgin Islands (VI), and Cat Island (CI) of the United States. The performance of DL-NB was evaluated by empirical method, machine learning method and multilayer perceptron (MLP). The results indicate that the accuracy of the DL-NB is better than comparative methods can in nearshore bathymetry. After quantitative analysis, the RMSE of DL-NB could achieve 1.01 m, 1.80 m and 0.28 m in AB, VI and CI respectively. Given the same data conditions, the proposed method can be applied for high precise global scale and multitemporal nearshore bathymetric maps generation, which are beneficial to marine environmental change assessment and conservation. Full article

At the interface between land and sea, the shoreface of sandy coasts extends from the dune (up to tens of meters above the sea level) to below the depth of the closure (often tens of meters below sea level). This is a crucial zone to monitor in order to reduce the uncertainty associated with forecasting the impact of storms and climate change on the coastal zone. At the same time, monitoring the dynamic interface between land and sea presents a traditional challenge for both in situ and remote sensing techniques. Here, we show the potential of using a video from a metric optical satellite sensor to estimate the emerged topography and submerged bathymetry over a single-pass. A short sequence (21 s, 10 Hz) of satellite-images was acquired with the Jilin-1/07 satellite covering the area in the vicinity of the Field Research Facility (FRF) at Duck (North Carolina, USA). The FRF site is regularly monitored with traditional surveys. From a few satellite images, the topography is reconstructed using stereo-photogrammetry techniques, while the bathymetry is inversed using incident waves through time-series spatio-temporal correlation techniques. Finally, the topography and bathymetry are merged into a seamless coastal digital elevation model (DEM). The satellite estimate shows a good agreement with the in situ survey with 0.8 m error for the topography and 0.5 m for the bathymetry. Overall, the largest discrepancy (more than 2 m) is obtained at the foreshore land–water interface due to the inherent problems of both satellite methods. A sensitivity analysis shows that using a temporal approach becomes beneficial over a spatial approach when the duration goes beyond a wave period. A satellite-based video with a duration of typically tens of seconds is beneficial for the bathymetry estimation and is also a prerequisite for stereo-based topography with large base-over-height ratio (characterizes the view angle of the satellite). Recommendations are given for future missions to improve coastal zone optical monitoring with the following settings: matricial sensors (potentially in push-frame setting) of ∼100 km² scenes worldwide; up to a monthly revisit to capture seasonal to inter-annual evolution; (sub)meter resolution (i.e., much less than a wavelength) and burst of images with frame rate >1 Hz over tens of seconds (more than a wave period). Full article

The ability to monitor the evolution of the coastal zone over time is an important factor in coastal knowledge, development, planning, risk mitigation, and overall coastal zone management. While traditional bathymetry surveys using echo-sounding techniques are expensive and time consuming, remote sensing tools have recently emerged as reliable and inexpensive data sources that can be used to estimate bathymetry using depth inversion models. Deep learning is a growing field of artificial intelligence that allows for the automatic construction of models from data and has been successfully used for various Earth observation and model inversion applications. In this work, we make use of publicly available Sentinel-2 satellite imagery and multiple bathymetry surveys to train a deep learning-based bathymetry estimation model. We explore for the first time two complementary approaches, based on color information but also wave kinematics, as inputs to the deep learning model. This offers the possibility to derive bathymetry not only in clear waters as previously done with deep learning models but also at common turbid coastal zones. We show competitive results with a state-of-the-art physical inversion method for satellite-derived bathymetry, Satellite to Shores (S2Shores), demonstrating a promising direction for worldwide applicability of deep learning models to inverse bathymetry from satellite imagery and a novel use of deep learning models in Earth observation. Full article

The seafloor—or bathymetry—of the world’s coastal waters remains largely unknown despite its primary importance to human activities and ecosystems. Here we present S2Shores (Satellite to Shores), the first sub-kilometer global atlas of coastal bathymetry based on depth inversion from wave kinematics captured by the Sentinel-2 constellation. The methodology reveals coastal seafloors up to a hundred meters in depth which allows covering most continental shelves and represents 4.9 million km${}^2$ along the world coastline. Although the vertical accuracy (RMSE 6–9 m) is currently coarser than that of traditional surveying techniques, S2Shores is of particular interest to countries that do not have the means to carry out in situ surveys and to unexplored regions such as polar areas. S2Shores is a major step forward in mitigating the effects of global changes on coastal communities and ecosystems by providing scientists, engineers, and policy makers with new science-based decision tools. Full article

Carolina Bays are oriented and sandy-rimmed depressions that are ubiquitous throughout the Atlantic Coastal Plain (ACP). Their origin has been a highly debated topic since the 1800s and remains unsolved. Past population estimates of Carolina Bays have varied vastly, ranging between as few as 10,000 to as many as 500,000. With such a large uncertainty around the actual population size, mapping these enigmatic features is a problem that requires an automated detection scheme. Using publicly available LiDAR-derived digital elevation models (DEMs) of the ACP as training images, various types of convolutional neural networks (CNNs) were trained to detect Carolina bays. The detection results were assessed for accuracy and scalability, as well as analyzed for various morphologic, land-use and land cover, and hydrologic characteristics. Overall, the detector found over 23,000 Carolina Bays from southern New Jersey to northern Florida, with highest densities along interfluves. Carolina Bays in Delmarva were found to be smaller and shallower than Bays in the southeastern ACP. At least a third of Carolina Bays have been converted to agricultural lands and almost half of all Carolina Bays are forested. Few Carolina Bays are classified as open water basins, yet almost all of the detected Bays were within 2 km of a water body. In addition, field investigations based upon detection results were performed to describe the sedimentology of Carolina Bays. Sedimentological investigations showed that Bays typically have 1.5 m to 2.5 m thick sand rims that show a gradient in texture, with coarser sand at the bottom and finer sand and silt towards the top. Their basins were found to be 0.5 m to 2 m thick and showed a mix of clayey, silty, and sandy deposits. Last, the results compiled during this study were compared to similar depressional features (i.e., playa-lunette systems) to pinpoint any similarities in origin processes. Altogether, this study shows that CNNs are valuable tools for automated geomorphic feature detection and can lead to new insights when coupled with various forms of remotely sensed and field-based datasets. Full article

Coastal erosion at Saint Louis in Senegal is affecting the local population that consists of primarily fishermen communities in their housing and their access to the sea. This paper aims at quantifying urban beach erosion at Saint Louis, Senegal, West Africa which is located on the northern end of the 13 km long Langue de Barbarie sand spit. The coastal evolution is examined quantitatively over a yearly period using Pleiades sub-metric satellite imagery that allows for stereogrammetry to derive Digital Elevation Models (DEMs). The comparison with ground truth data shows sub-metric differences to the satellite DEMs. Despite its interest in remote areas and developing countries that cannot count on regular surveys, the accuracy of the satellite-derived topography is in the same order as the coastal change itself, which emphasizes its current limitations. These 3D data are combined with decades-long regular Landsat and Sentinel-2 imagery derived shorelines. These observations reveal that the sand spit is stretching, narrowing at its Northern part while it is lengthening downdrift Southward, independently from climatological changes in the wave regime. A parametric model based on a stochastic cyclic sand spit behaviour allows for predicting the next northern opening of a breach and the urban erosion at Saint Louis. Full article

Forecasting shoreline evolution for sandy coasts is important for sustainable coastal management, given the present-day increasing anthropogenic pressures and a changing future climate. Here, we evaluate eight different time-series forecasting methods for predicting future shorelines derived from historic satellite-derived shorelines. Analyzing more than 37,000 transects around the globe, we find that traditional forecast methods altogether with some of the evaluated probabilistic Machine Learning (ML) time-series forecast algorithms, outperform Ordinary Least Squares (OLS) predictions for the majority of the sites. When forecasting seven years ahead, we find that these algorithms generate better predictions than OLS for 54% of the transect sites, producing forecasts with, on average, 29% smaller Mean Squared Error (MSE). Importantly, this advantage is shown to exist over all considered forecast horizons, i.e., from 1 up to 11 years. Although the ML algorithms do not produce significantly better predictions than traditional time-series forecast methods, some proved to be significantly more efficient in terms of computation time. We further provide insight in how these ML algorithms can be improved so that they can be expected to outperform not only OLS regression, but also the traditional time-series forecast methods. These forecasting algorithms can be used by coastal engineers, managers, and scientists to generate future shoreline prediction at a global level and derive conclusions thereof. Full article

Sea state estimation from wide-swath and frequent-revisit scatterometers, which are providing ocean winds in the routine, is an attractive challenge. In this study, state-of-the-art deep learning technology is successfully adopted to develop an algorithm for deriving significant wave height from Advanced Scatterometer (ASCAT) aboard MetOp-A. By collocating three years (2016–2018) of ASCAT measurements and WaveWatch III sea state hindcasts at a global scale, huge amount data points (>8 million) were employed to train the multi-hidden-layer deep learning model, which has been established to map the inputs of thirteen sea state related ASCAT observables into the wave heights. The ASCAT significant wave height estimates were validated against hindcast dataset independent on training, showing good consistency in terms of root mean square error of 0.5 m under moderate sea condition (1.0–5.0 m). Additionally, reasonable agreement is also found between ASCAT derived wave heights and buoy observations from National Data Buoy Center for the proposed algorithm. Results are further discussed with respect to sea state maturity, radar incidence angle along with the limitations of the model. Our work demonstrates the capability of scatterometers for monitoring sea state, thus would advance the use of scatterometers, which were originally designed for winds, in studies of ocean waves. Full article

This paper introduces a discussion about the need for atmospheric corrections by comparing data-driven sea surface salinity (SSS) derived from Top- and Bottom-of-Atmosphere imagery. Atmospheric corrections are used to remove the effect of the atmosphere in reflectances acquired by satellite sensors. The Sentinel-2 Level-2A product provides atmospherically corrected Bottom-of-Atmosphere (BOA) imagery, derived from Level-1C Top-of-Atmosphere (TOA) tiles using the Sen2Cor processor. SSS at high resolution in coastal areas ($100$m) is derived from multispectral signatures using artificial neural networks. These obtain relationships between satellite band information and in situ SSS data. Four scenarios with different input variables are tested for both TOA and BOA imagery, for interpolation (previous information on all platforms is available in the training dataset) and extrapolation (certain platforms are isolated and the network does not have any previous information on these) problems. Results show that TOA always outperforms BOA in terms of higher coefficient of determination ($R^2$), lower mean absolute error ($MAE$) and lower most common error (${\mu }_e$). The best TOA results are $R^2=0.99$, $MAE=0.4$PSU and ${\mu }_e=0.2$PSU. Moreover, the evaluation of the neural network in all the pixels of Sentinel-2 tiles shows that BOA results are accurate only far away from the coast, while TOA data provides useful information on nearshore mixing patterns, estuarine processes and is able to estimate freshwater salinity values. This suggests that land adjacency corrections could be a relevant source of error. Sun glint corrections appear to be another source of error. TOA imagery is more accurate than BOA imagery when using machine learning algorithms and big data, as there is a clear loss of information in the atmospheric correction process that affects the multispectral–in situ relationships. Finally, the time and computational resources gained by avoiding atmospheric corrections can make the use of TOA imagery interesting in future studies, such as the estimation of chlorophyll or coloured dissolved organic matter. Full article

In recent years, satellite imagery has shown its potential to support the sustainable management of land, water, and natural resources. In particular, it can provide key information about the properties and behavior of sandy beaches and the surrounding vegetation, improving the ecomorphological understanding and modeling of coastal dynamics. Although satellite image processing usually demands high memory and computational resources, free online platforms such as Google Earth Engine (GEE) have recently enabled their users to leverage cloud-based tools and handle big satellite data. In this technical note, we describe an algorithm to classify the coastal land cover and retrieve relevant information from Sentinel-2 and Landsat image collections at specific times or in a multitemporal way: the extent of the beach and vegetation strips, the statistics of the grass cover, and the position of the shoreline and the vegetation–sand interface. Furthermore, we validate the algorithm through both quantitative and qualitative methods, demonstrating the goodness of the derived classification (accuracy of approximately 90%) and showing some examples about the use of the algorithm’s output to study coastal physical and ecological dynamics. Finally, we discuss the algorithm’s limitations and potentialities in light of its scaling for global analyses. Full article