European Spatial Data for Coastal and Marine Remote Sensing: Proceedings of International Conference EUCOMARE 2022-Saint Malo, France

Description

This volume presents full paper contributions from the International Conference of European Spatial Data for Coastal and Marine Remote Sensing (EUCOMARE) 2022, with the support of the ERASMUS+ Programme of the European Union, held in Saint Malo, France. EUCOMARE aims to promote academic and technical exchange on coastal related studies including coastal environmental and socio-economic issues, with the use of European remotely sensed data. The book is an excellent resource for scientists, engineers, and programme managers eager to learn about the recent developments and achievements in the field of remote sensing applications on marine and coastal areas. Readers will learn about recent advances in sensors' radiometric, spatial, temporal and spectral resolution, as well as new data processing approaches in remote sensing for monitoring and mapping the various characteristics of marine, coastal and aquatic systems. Editorial for Special Issue: European Spatial Data for Coastal and Marine Remote Sensing In the Category of Short Articles, There Are Six Articles References Contents Contributors Detection of Coccolithophore Bloom Episodes in Algiers Bay Using Satellite and In Situ Analysis 1 Introduction 2 Study Area 3 Materials and Methods 3.1 In Situ Data 3.2 Satellite Data Acquisition 3.3 Coccolithophore Bloom Index (Cocco-Index) 4 Results 4.1 Coccolithophore Bloom Episodes in the Algiers Bay from In Situ Observations 4.2 Monitoring and Spectral Response of E1, E2, and E3 4.3 Cocco-Index of E1, E2, and E3 4.4 Coccolithophore Bloom Episodes in the Algiers Bay (from 2003 to 2018) 5 Discussion 6 Conclusion References Multiscale Spatiotemporal NDVI Mapping of Salt Marshes Using Sentinel-2, Dove, and UAV Imagery in the Bay of Mont-Saint-Michel, France 1 Introduction 2 Methodology 2.1 Study Area 2.2 Imagery Source and Processing 2.2.1 Satellite Sentinel-2 2.2.2 Nanosatellite Dove 2.2.3 Unmanned Aerial Vehicle 2.3 Predicting the NIR at the UAV Scale 2.3.1 Two-Scaled Spectral Datasets 2.3.2 Neural Network Regression 3 Results 3.1 Changes in the Normalized Difference Vegetation Index Values 3.1.1 Satellite Sentinel-2 3.1.2 Nanosatellite Dove 3.2 Prediction of the Normalized Difference Vegetation Index Values 3.2.1 Unmanned Aerial Vehicle Near-Infrared 4 Discussion 4.1 Salt Marsh Spatiotemporal Patterns 4.1.1 Satellite-Based Salt Marsh Spatial Analysis 4.1.2 Satellite-Based Salt Marsh Temporal Change 4.2 Modelling the Extent of Salt Marsh at an Ultra-High Resolution 4.2.1 Spectral Predictive Modelling at Ultra-High Resolution 4.2.2 Predictive Modelling of Vegetation Height at Ultra-High Resolution 5 Conclusion References Contribution of Near- and Mid-Infrared Wavebands to Mapping Fine-Scale Coastal Ecogeomorphological Features 1 Introduction 2 Methodology 2.1 Study Site 2.2 Imagery Data 2.3 Class Identification 2.4 Pixel-Based Supervised Classification 3 Results and Discussion 3.1 Identification of the Best Model Based on Overall Accuracy 3.2 Class-Level Accuracy 3.2.1 Best Model for Classification of the Plant Features 3.2.2 Sedimentary Feature Classifications 4 Conclusion References Monitoring Land Cover Change in the Southeastern Baltic Sea Since the 1980s by Remote Sensing 1 Introduction 2 Context 2.1 The Soviet Period: Military Control and Economic Specialization 2.2 Liberalization and Gradual Coastalization of the Southeastern Baltic Countries 3 Methodology 3.1 Definition of the Coastal Zone Study Area 3.2 Data Acquisition 3.3 Method of Analysis of Land-Use Change 3.3.1 Pre-processing 3.3.2 Image Segmentation 3.3.3 Object-Oriented Land-Use Classification 3.3.4 Post-processing 4 Results 4.1 Significant and Distinctive Trends Toward Coastal Urbanization 4.2 Evolution of Land Use, Territorial Development, and Planning Policies 5 Discussion 5.1 Limitations of Coastal Zone Management Policies 5.2 Limits of Supervised Classification by GEOBIA Approach 6 Conclusion References Assessment of Land Cover Changes in the Allala Watershed Based on Object Based Image Analysis Using Landsat and Sentinel-2 Images 1 Introduction 2 Study Area 3 Material and Methods 3.1 Object-Based Image Analysis (OBIA) 3.1.1 Data Acquisition and Preprocessing 3.1.2 Multi-resolution Segmentation 3.1.3 OBIA Classification–Based Machine Learning Classifiers 3.2 LULC Map Validation 3.3 LULC Change Detection 4 Results 4.1 Accuracy Assessment of LULC Classification 4.2 Analysis of LULC Changes 4.3 Analysis of LULC Transition Matrix 5 Discussion 6 Conclusion References Deep Learning–Based Bathymetry Mapping from Multispectral Satellite Data Around Europa Island 1 Introduction 2 Aim and Objectives 3 Study Area and Data Sources 4 Methodology 4.1 Image Pre-processing 4.2 Network Architecture 4.3 Model Evaluation 5 Results and Discussion 5.1 International Hydrographic Organization (IHO) Standards 5.2 Reconstruction of Bathymetry Prediction Map 6 Conclusion References Assessment of Coastal Vulnerability to Erosion Risk Using Geospatial and Remote Sensing Methods (Case of Jerba Island, Tunisia) 1 Introduction 2 Study Area 3 Methodology 3.1 Treatment 3.1.1 Shoreline Change 3.1.2 Geomorphology 3.1.3 Slope 3.1.4 Significant Wave Height 3.1.5 Mean Tidal Range 3.1.6 Land Cover 3.2 Coastal Vulnerability Index (CVI) Calculation 4 Results 4.1 The Shoreline Variable 4.2 The Geomorphology Variable 4.3 The Slope Variable 4.4 The Wave Height Variable 4.5 Mean Tidal Range 4.6 The Land Use Variable 4.7 Coastal Vulnerability Index (CVI) 5 Discussion 6 Conclusion References A Random Forest Approach for Evaluating Forest Cover Changes Outside Dikes with Sentinel Images 1 Introduction 2 Sentinel Imagery 2.1 Sentinel-1 2.1.1 Calibration 2.1.2 Speckle Filtering 2.1.3 Range Doppler Terrain Correction 2.1.4 Conversion to dB 2.2 Sentinel-2 2.2.1 Sentinel-2 Bands 2.2.2 Sentinel Band Combinations Natural Color (B4, B3, B2) Color Infrared (B8, B4, B3) 3 From Sentinel Data to Matrix 4 Sentinel as a Random Forest 4.1 Decision Tree 4.2 Bootstrap 4.3 Bagging 4.4 Random Forest 5 Experiment 5.1 Dataset 5.2 Tools 6 Results 6.1 Accuracy of the Random Forest Model by Year 6.2 Forest Area by Year from 2019 to 2022 6.3 Forest Restoration from 2020 to 2022 6.4 Deforestations from 2020 to 2022 7 Conclusion and Discussion References Spatial Monitoring of Coastal Protection DikesCase Study of the Touristic Beach “Palm Beach, West Algiers, Algeria” 1 Introduction 2 Study Area 3 Methodology 3.1 Data Set and Pre-processing 3.2 SAM: Spectral Angle Matching 3.3 Median Filter 3.4 Spectral Unmixing 3.5 Principal Component Analysis (PCA) 3.6 Independent Component Analysis (ICA) 3.7 Normalized Difference Water Index (NDWI) 4 Results 4.1 Shorelines’ Variants 4.2 Beach Dynamic Analysis 5 Conclusion References Monitoring Shoreline Changes in the Vietnamese Mekong Delta Coastal Zone Using Satellite Images and Wave Reduction Structures 1 Introduction 2 Material and Methods 2.1 Study Area 2.2 Data Collection 2.2.1 Landsat Image Analysis of Shoreline Position 2.2.2 GoogleTM Earth Images 2.3 Data Pre-processing 2.3.1 Landsat Image Analysis of Shoreline Position 2.3.2 GoogleTM Earth Image Analysis 2.3.3 Wave Measurements 2.4 Data Analysis 2.4.1 Change in Beach Volume 2.4.2 Wave Height Calculations 3 Results and Discussion 3.1 Results from Remote Sensing Images 3.1.1 Shoreline Changes from Landsat Images 3.1.2 Shoreline Changed from Google Images 3.2 Changes in Beach Volume 3.3 Results on Wave Height and Wave Reduction 3.3.1 Wave Characteristics 3.3.2 Wave Height Reduction 4 Conclusion 5 Recommendations References Automatic Detection of Hydrodynamical and Biological Indicators of the Shoreline Using a Convolutional Neural Network 1 Introduction 2 Methodological Approach 2.1 Shoreline Indicator 2.1.1 Hydrodynamical Indicator 2.1.2 Biological Indicator 2.2 Data Set 2.3 Convolutional Neural Network Architecture 2.4 Accuracy Assessment 2.4.1 Hydrodynamic Characterization 3 Results 4 Discussion 5 Conclusion References Very High-Resolution Monitoring and Evaluation of Tidal and Ecological Restoration in Beaussais’ Bay 1 Introduction 2 Methodology 3 Results and Discussion References Assessment of Shoreline Change of Jerba Island Based on Remote Sensing Data and GIS Using DSAS Tools 1 Introduction 2 Methodology 3 Results and Discussion References New Insights into the Shallow Morpho-Sedimentary Patterns Using High-Resolution Topo-Bathymetric Lidar: The Case Study of the Bay of Saint-Malo 1 Introduction 2 Study Site 3 Topo-Bathymetric Lidar Acquisition 4 Sonar and Sediment Samples 5 Preliminary Results References Spatial Modeling of the Benthic Biodiversity Using Topo-Bathymetric Lidar and Neural Networks 1 Introduction 2 Methodology 3 Results and Discussion References Local Circalittoral Rocky Seascape Structuring Fish Community: Insights from a Photogrammetric Approach 1 Introduction 2 Methodology 3 Preliminary Results References Increasing the Nature-Based Coastal Protection Using Bathymetric Lidar, Terrain Classification, Network Modelling: Reefs of Saint-Malo’s Lagoon? 1 Introduction 2 Methodology 2.1 Study Area 2.2 Bathymetric LiDAR 2.3 Morpho-Bathymetry Classification 2.4 Graph-Based Network Modelling 3 Results and Discussion 3.1 Network of the Ridges 3.2 Transferability and Biodiversity References Abstracts of Keyspeakers Imaging Spectroscopy and Coastal Oil Spills: Examples from the Deepwater Horizon Modeling Approach for Meso-Habitat Detection on Coastal Ecosystems by Very High-Resolution UAV Imagery and Field Survey Coastal Vulnerability and Climate Change Adaptation in South Africa: Remote Sensing Challenges and Opportunities Index