Hyperspectral Imagery (HSI) has great importance in industrial remote sensing applications, such as geological exploration and soil mapping. HSI has high spectral resolution, which gives each object a unique spectral response, making them easily identifiable. Nonetheless, their spatial resolution is compromised due to sensor limitation, which hinders utilizing HSI to their full potential. This paper deals with the spatial enhancement of HSI using Single Image Super Resolution (SISR) approaches. One of the main challenges in this area of research is preserving the spectral signature of HSI while improving the spatial resolution simultaneously. To tackle this challenge, we propose a 3D Wide Residual Convolutional Neural Network (3D-WRCNN) model that effectively utilizes the principle of wide activation to enhance feature propagation throughout the network. Residual connections are also deployed to boost image reconstruction and information sharing between the layers to reduce overfitting. Furthermore, this study incorporates and demonstrates the usage of Bayesian-optimized hybrid loss function to further improve the performance of the 3D-WRCNN. The quantitative and qualitative evaluation indicate that the proposed approach prevails over other state-of-the-art approaches. The implementation of the proposed model is provided in this repository: https://github.com/NourO93/SISR_Library

Hyperspectral Single Image Super Resolution is an important field of research due to the low spatial resolution of Hyperspectral Images (HSI) that limits their usability. Deep Convolutional Neural Networks (DCNNs) have been commonly used for SISR tasks, however, a large dataset is typically needed for training. Because of HSI data scarcity, training DCNNs for HSI-SISR becomes a challenging task. In this study, HSI data scarcity problem is tackled from an SISR perspective via Data Augmentation (DA). Several DA techniques are reviewed in this context, and a new DA technique called CutMixBlur is introduced. The best techniques are decided based on maximizing Peak Signal-to-Noise Ratio (PSNR) and Structure Similarity Index Measurement (SSIM) while minimizing Spectral Angle Mapper (SAM). The aim is to enhance HSI spatially without distorting their unique spectral signature. Experiments on Pavia University and Indian Pines datasets show that CutMixBlur boosts all quality metrics. Additionally, applying DA techniques by randomly stacking their effect significantly enhances the performance of SISR DCNNs, particularly the 3D-SRCNN.

Accurate flood mapping plays a critical role in disaster management, allowing for effective response and mitigation efforts. Thus, researchers seek to boost the accuracy of flood mapping algorithms, especially in terms of generalization capability and minimizing False Positive and False Negative detection. This paper presents a robust flood mapping algorithm from SAR images via Deep Convolutional Neural Network (DCNN) that follows encoder-decoder scheme. By introducing Bidirectional Convolutional LSTM (ConvLSTM) layers into its architecture, the proposed Temporal-Spatial Encoder-Decoder Network (TSEDN) network is able to extract temporal information and produce more accurate change maps. The training and testing are carried using OMBRIA dataset, which is known to be challenging to train. The proposed network is evaluated and compared to other state-of-the-art approaches in terms of Overall Accuracy (OA), Precision, Recall, and mean Intersection over Union (mIoU).

This paper proposes a novel multi-branch feature fusion network for PolSAR image classification and interpretation. It is built using Complex-valued Convolutional Neural Networks (CV-CNNs). The proposed approach utilizes extraction of polarimetric features at each branch to achieve high classification accuracy. Moreover, Squeeze and Excitation (SE) is also introduced within the model’s architecture. SE block improves channel interdependencies with almost no additional computational cost. The proposed approach is tested and evaluated using Flevoland benchmark dataset. Experiments demonstrate the effectiveness of the proposed attention based shallow to deep CV-CNN model for PolSAR image classification in terms of Kappa Coefficient (k), Overall Accuracy (OA), and Average Accuracy (AA) metrics.

Mangroves are coastal ecosystems with enormous ecological benefits. These coastal protectors provide a living environment to many marine organisms, and it is considered a unique contributor against climate change in their carbon storage and sequestration process. Mangroves experience severe losses due to natural factors and intensive anthropogenic activities. Therefore, mapping, monitoring, and obtaining consistent recent information about these valuable resources is essential for conservation and protection. The United Arab Emirates (UAE) is the home of sixty million mangroves covering an area of more than 180 km2and storing 43,000 tons of carbon dioxide yearly [1]. The mangrove area located in the coastal region of UAE provides various benefits to the region and is considered a protective shield against the risk of erosion and sea intrusion. Therefore, UAE promised in the Conference of the Parties 2026 (COP26) to plant 100 million mangroves by the year 2030 [1]. Remote sensing and digital image processing techniques had proven to understand the mangrove ecosystem dynamics. Therefore, this study aims to investigate the changes in the Mangrove area and the effect of these changes on coastal erosion hazards over the last 20 years. The first step is to use a pixel-based machine learning (ML) classifiers along with multi-temporal, medium-resolution Landsat satellite images within Google Earth Engine (GEE) cloud computing platform, to create multi-temporal mangrove distribution maps of the UAE coastal area during the last 20 years. Second, qualitative and quantitative evaluations are conducted using ground truth data to validate the robustness of the proposed methodology and the accuracy of the results. Finally, coastline analysis is carried out using open-source tools, such as Digital Shoreline Analysis System (DSAS) [2] to estimate coastline changes and analyze coastal erosion risk. This method allows the identification of the mangrove gains and losses, as well as measurement of the change of coastline (accretion and erosion) over the past 20 years. The generated maps can lead to improvements in the ecosystems’ management and protection procedures. This study presents an effective workflow for mangrove detection and temporal mapping, using open-source medium-resolution satellite images, big data processing platforms, such as GEE, and open-source tools, such as DSAS.

Hyperspectral Imagery (HSI) classification is an important research area in remote sensing community due to its high efficiency in accurately analyzing ground features by assigning a class label to each pixel. This paper explores the use of Band Subset selection (BSS) methods as Dimensionality Reduction (DR) pre-processing stage for HSI classification, and compares them to Principal Component Analysis (PCA) approach. BSS is the problem of selecting the most independent bands in HSI cube. Classification is then performed using a proposed multi-branch HydraNet model that combines 1D, 2D, and 3D convolution. HydraNet is trained and tested using the benchmark Pavia University dataset, and the results are evaluated using Kappa and Overall Accuracy. Experimental results show positive indications of the network’s performance, especially when compared to other state-of-the-art CNN networks.

Single Image Super Resolution (SISR) refers to the spatial enhancement of an image from a single Low Resolution (LR) observation. This topic is of particular interest to remote sensing community, especially in the area of Hyperspectral Imagery (HSI) due to their high spectral resolution but limited spatial resolution. Enhancing the spatial resolution of HSI is a pre-requisite that boosts the accuracy of other image processing tasks, such as object detection and classification. This paper deals with SISR of HSI through the 3D expansion of Robust UNet (RUNet). The network is developed, trained, and tested over two datasets, and compared against the original 2D-RUNet and other state-of-the-art approaches. Quantitative and qualitative evaluation show the superiority of 3D-RUNet and its ability to preserve the spectral fidelity of the enhanced HSI.

Autonomous detection and counting of palm trees is a research field of interest to various countries around the world, including the UAE. Automating this task saves effort and resources by minimizing human intervention and reducing potential errors in counting. This paper introduces a new High Resolution (HR) remote sensing dataset for autonomous detection of palm trees in the UAE. The dataset is collected using Unmanned Aerial Vehicles (UAV), and it is labeled properly in PASCAL VOC and YOLO formats after preprocessing and visually inspecting its quality. A comparative evaluation between Faster-RCNN and YOLOv4 networks is then conducted to observe the usability of the dataset in addition to the strengths and weaknesses of each network. The dataset is publicly available at https://github.com/Nour093/Palm-Tree-Dataset.

Accurate and precise spatial hydrologic information is essential for effective management of natural resources, planning, and disaster response. Very high-resolution images and precise digital elevation models (DEMs) are crucial to accurately predict overflow in urban and mountainous regions; however, available course resolution DEMs with insufficient details cannot provide reliable overflow models. In this context, unmanned aerial vehicles (UAVs) offer a competitive alternative over satellites or airplanes and provide high spatial details essential for significant improvement of hydrological modeling. In this study, photogrammetric processing that includes stereo images captured via a fixed-wing drone were processed to generate a high-resolution DEM for the area surrounding the Hatta Dam in the United Arab Emirates. Three levels of details were introduced: data collection, photogrammetric processing, and hydrologic modeling. This study determined that flow modeling based on the UAV DEMs resulted in accurate hydrological modeling.

In this paper, several indoor positioning systems are reviewed and a deep neural network (DNN) algorithm based on Scaled Conjugate Gradient (SCG) algorithm is proposed. In the proposed indoor positioning system, Received Signal Strength (RSS) is used as a fingerprint to identify the indoor location in terms of Building and Floor. The performance of the system is evaluated and compared against other machine learning based positioning systems. The accuracy of the proposed DNN is 99% when tested using a standard dataset.