Mangroves are among the most productive ecosystems in existence, with many ecological benefits. Therefore, generating accurate thematic maps from mangrove ecosystems is crucial for protecting, conserving, and reforestation planning for these valuable natural resources. In this paper, Sentinel-1 and Sentinel-2 satellite images were used in synergy to produce a detailed mangrove ecosystem map of the Hara protected area, Qeshm, Iran, at 10 m spatial resolution within the Google Earth Engine (GEE) cloud computing platform. In this regard, 86 Sentinel-1 and 41 Sentinel-2 data, acquired in 2019, were employed to generate seasonal optical and synthetic aperture radar (SAR) features. Afterward, seasonal features were inserted into a pixel-based random forest (RF) classifier, resulting in an accurate mangrove ecosystem map with average overall accuracy (OA) and Kappa coefficient (KC) of 93.23% and 0.92, respectively, wherein all classes (except aerial roots) achieved high producer and user accuracies of over 90%. Furthermore, comprehensive quantitative and qualitative assessments were performed to investigate the robustness of the proposed approach, and the accurate and stable results achieved through cross-validation and consistency checks confirmed its robustness and applicability. It was revealed that seasonal features and the integration of multi-source remote sensing data contributed towards obtaining a more reliable mangrove ecosystem map. The proposed approach relies on a straightforward yet effective workflow for mangrove ecosystem mapping, with a high rate of automation that can be easily implemented for frequent and precise mapping in other parts of the world. Overall, the proposed workflow can further improve the conservation and sustainable management of these valuable natural resources.

Despite the state-of-the-art performance of the deep learning methods for Synthetic Aperture Radar (SAR) data classification, the Real-Valued (RV) networks neglect the phase component of the Complex-Valued (CV) SAR data and lose a lot of useful information. CV deep architectures have been developed in the recent years to exploit the amplitude and phase components of the CV data, in different fields. However, the superiority of CV models over RV models are proved to be different for each application, and more investigation into the advantages and disadvantages of implementing CV models for SAR data classification is necessary. In this study, the performance of the CV Convolutional Neural Network (CV-CNN) for Polarimetric SAR (PolSAR) data classification is compared with its RV equivalent network, in different contexts.

Oceans cover over 70% of the Earth’s surface and provide numerous services to humans and the environment. Therefore, it is crucial to monitor these valuable assets using advanced technologies. In this regard, Remote Sensing (RS) provides a great opportunity to study different oceanographic parameters using archived consistent multitemporal datasets in a cost-efficient approach. So far, various types of RS techniques have been developed and utilized for different oceanographic applications. In this study, 15 applications of RS in the ocean using different RS techniques and systems are comprehensively reviewed and discussed. This study is divided into two parts to supply more detailed information about each application. The first part briefly discusses 12 different RS systems that are often employed for ocean studies. Then, six applications of these systems in the ocean, including Ocean Surface Wind (OSW), Ocean Surface Current (OSC), Ocean Wave Height (OWH), Sea Level (SL), Ocean Tide (OT), and Ship Detection (SD), are provided. For each application, the applicable RS systems, their advantages and disadvantages, various RS and Machine Learning (ML) techniques, and several case studies are discussed. The other nine applications, including Iceberg, Sea Ice (SI), Sea Surface temperature (SST), Ocean Surface Salinity (OSS), Ocean Color (OC), Ocean Chlorophyll (OCh), Ocean Oil Spill (OOS), Underwater Ocean, and Fishery, are provided in Part II of this study.

Oil pollution of oceans from various sources is a devastating environmental problem and immediate detection of oil spills is crucial. Remote sensing techniques have provided an unprecedented opportunity for early oil spill detection and classification with an easy, quick, and cheap approach. Moreover, Fully Polarimetric Synthetic Aperture Radar (PolSAR) data with unique capabilities and informative features is an immense data source for oil spill detection on large scales. The objective of the present study is to utilize PolSAR data not only for oil spill detection, but also to classify the detected oil spill in the ocean into four classes: thick oil, thin oil, oil/water mixture, and clear water. In this study, numerous polarimetric decomposition parameters and texture features are extracted from the PolSAR image. A two-phase feature selection method, manually selection based on oil and water surface backscattering behavior and an optimization algorithm, has been employed on the extracted features to select the optimum feature set. The selected feature set has been used to classify the PolSAR image into oil and water classes. Moreover, the high sensitivity and discriminative power of the validation PolSAR dataset, UAVSAR L-band quad-pol data, is exploited by classifying the image into four classes. Remarkable acquired classification accuracies of 90.21% and 85.41% and Kappa coefficient of 0.8052 and 0.7905 for two-class and four-class classifications, respectively, demonstrate the robustness and high potential of the proposed methodology for oil spill detection and classification.

As discussed in the first part of this review paper, Remote Sensing (RS) systems are great tools to study various oceanographic parameters. Part I of this study described different passive and active RS systems and six applications of RS in ocean studies, including Ocean Surface Wind (OSW), Ocean Surface Current (OSC), Ocean Wave Height (OWH), Sea Level (SL), Ocean Tide (OT), and Ship Detection (SD). In Part II, the remaining nine important applications of RS systems for ocean environments, including Iceberg, Sea Ice (SI), Sea Surface temperature (SST), Ocean Surface Salinity (OSS), Ocean Color (OC), Ocean Chlorophyll (OCh), Ocean Oil Spill (OOS), Underwater Ocean, and Fishery are comprehensively reviewed and discussed. For each application, the applicable RS systems, their advantages and disadvantages, various RS and Machine Learning (ML) techniques, and several case studies are discussed.

In the first year of my PhD project, as the fifteenth Early Stage Researcher (ESR) of the MENELAOS-NT project, I have focused on two objectives of my thesis. In the first objective, I have exploited semantic data mining techniques for latent information discovery from various Earth Observation images. In the second goal and as the continuity of the first aspect, I have studied complex-valued deep architectures for Synthetic Aperture Radar (SAR) data processing in order to utilize both the amplitude and phase information in SAR images.

Land cover maps are among the most important products of Remote Sensing (RS) imagery. Despite remarkable advancements in land cover classification techniques, abundant detailed information in the very high-resolution RS images necessitates further improvements to harness the data and discover detailed semantic information. Moreover, scarcity of the labelled data and its quality is a major limitation in RS land cover mapping. In the present study, Latent Dirichlet Allocation is employed for semantic discovery in RS images and a novel kernel-based Bag of Visual Words model is proposed for land cover mapping.

Recent advances in remote sensing technology have provided (very) high spatial resolution Earth Observation (EO) data with abundant latent semantic information. Conventional data processing algorithms are not capable of extracting the latent semantic information form these data and harness their full potential. As a result, semantic information discovery methods, based on data mining techniques, such as Latent Dirichlet Allocation (LDA) and Bag of Visual Words (BOVW) models, can discover the latent information. Despite their crucial rule, there are only a few studies in the field of semantic data mining for remote sensing applications. This study is focused on this shortage. Three different scenarios are used to evaluate the semantic information discovery in various remote sensing applications, including both optical and Synthetic Aperture Radar (SAR) data with different spatial resolutions. In the first scenario, semantic discovery method correlated the semantic perception of the user and machine to correct and enhance the user defined Ground Truth (GT) map in very high-resolution RGB data. The potential of the semantic discovery is evaluated for wildfire affected area detection in Sentinel-2 data in the second scenario. Finally, in the third scenario, the semantic discovery method is utilized to detect the misclassifications as well as the patches with ambiguous or multiple semantic labels in a Sentinel-1 SAR patch-based benchmark dataset, to enhance the robustness and accuracy of the annotation in the dataset. Our results in these three scenarios demonstrated the capability of the data mining-based semantic information discovery methods for various remote sensing applications.