This study evaluates a flood extent mapping framework that combines multi-temporal Sentinel-2 imagery with deep learning in the Karkheh River Basin, Khuzestan Province, Iran. The 2019 flood scenes were processed into fixed-size temporal patches using four reported predictor channels: B3, B8, NDWI, and SMI. Five architectures were evaluated: CNN-LSTM, CNN-LSTM-U-Net, ConvLSTM, Conv-minLSTM, and ConvLSTM-U-Plus. Performance was assessed using intersection over union (IoU), Dice/F1, precision, recall, and binary accuracy. ConvLSTM achieved the highest F1-scores for the balanced 8 × 8 and 16 × 16 configurations and the unbalanced 32 × 32 configuration, whereas ConvLSTM-U-Plus obtained a marginally higher F1-score for the balanced 32 × 32 configuration and produced spatially coherent boundaries in the illustrated examples. The findings support convolutional recurrent architectures for event-based satellite flood mapping, while validation on independent events and regions is required before operational application.

This study addresses the critical task of automatically identifying oceanic eddies, essential features for marine energy and chemical distribution, using sea surface temperature data from the Atlantic Ocean. It introduces the Deep Eddy Network, a sophisticated deep-learning framework based on an encoder-decoder architecture. The network performs pixel-wise classification, generating an output map where each pixel is labeled as '0' (non-eddy), '1' (anticyclonic eddy), or '2' (cyclonic eddy). Key innovations include a dedicated morphological module that injects shapebased information into the input data. The architecture is designed for high efficiency, employing advanced techniques in its core components. The encoder block utilizes dilated convolutions combined with activation functions, batch normalization, and an attention mechanism. Similarly, the decoder block integrates activation functions with 2D transpose convolution, batch normalization, and attention. Developed using Python and Keras, the final model demonstrates a superior balance between computational performance and segmentation accuracy. This makes the proposed Deep Eddy Network a practical and powerful tool, particularly suitable for deployment in real-time oceanographic monitoring and analysis applications, advancing our ability to understand these dynamic oceanic phenomena.

Satellite imagery and remote sensing are suitable tools for monitoring and surveillance of the Earth. The use of this data to address various environmental challenges, from surveillance to risk management, is of great interest. In one of the applications of interest, satellite imagery is used for monitoring and assessing wildfires. However, its effectiveness is often limited by the spatial-spectral quality of the images, which also affects the performance of deep learning.This study proposes the LB-DL method, a hybrid framework that applies the Laplace-Beltrami (LB) operator to this application and integrates it with deep learning models to evaluate the improvement of image quality using LB. The LB operator exploits the inherent geometric structure of image manifolds for this improvement by suppressing noise while simultaneously enhancing critical spatial-spectral features, leading to more accurate mapping of burned areas.The method was evaluated using Sentinel-2 multispectral images of a wildfire in Uzbekistan and compared with conventional and state-of-the-art deep learning models. To test the robustness, realistic noise scenarios, additive, multiplicative, and dead pixels were simulated. Performance was measured using peak signal-to-noise ratio (PSNR), structural similarity index (SSIM), and classification accuracy.The results showed that LB-DL outperformed the baseline methods under the evaluated conditions, achieving PSNR improvements of up to 4.4 dB and SSIM increases of 0.13. Further validation on the hyperspectral datasets of Indian Pines and Salinas suggested promising generalizability, though additional validation on more diverse datasets and real-world conditions is needed.These findings highlight the potential of integrating geometry-based denoising with deep learning to enhance the reliability of remote sensing applications such as wildfire monitoring.

The spatial resolution of multispectral satellite imagery often limits its utility for precise environmental monitoring applications, such as detailed mapping of burned areas after wildfires. To address this, we propose a novel hybrid deep-learning architecture, the high-resolution super-resolution network (HR-SR Net), for 4x super-resolution of Sentinel-2 imagery. The HR-SR Net integrates a parallel encoder comprising a 3-D depthwise convolutional neural network and a Swin Transformer block to synergistically extract both local spatial features and global contextual dependencies. A key innovation is the weighted sum injection of burned-area indices, which guides the network to prioritize semantically relevant features during reconstruction. Furthermore, a residual cubic Gabor-wavelet filter module is incorporated to enhance input data quality by suppressing noise and emphasizing critical textural details. The model was trained and evaluated on a benchmark dataset of Sentinel-2 imagery from a fire-affected region in Uzbekistan. Comprehensive experiments demonstrate that HR-SR Net sets a new state-of-the-art, achieving a peak signal-to-noise ratio of 45.72 dB and a structural similarity index measure of 95.63%, significantly outperforming a wide range of classical and deep-learning-based super-resolution methods. The results confirm the model's robustness and its potential for generating high-fidelity, ultraresolution imagery to support the accurate postfire assessment and monitoring.

Mapping wildfire burned areas using satellite imagery is essential for immediate response measures as well as for long-term recovery planning. These maps provide critical information to response teams, allowing them to effectively allocate resources and prioritize affected areas. This study focuses on the aim of providing accurate maps of areas affected by wildfires in the Guzli region near Bukhara province in Uzbekistan. The benchmark dataset from the study area, named UZB-WF2022, which indicates the country name and year of occurrence, and includes Sentinel-2 and Plant-Scope multispectral multi-resolution images. This study uses a mixture of unsupervised deep learning with the k-means algorithm to accurately identify and map burned areas. The core of the proposed method is an autoencoder model designed with 3-dimensional convolutional layers. This autoencoder is mixed with the k-means algorithm in the latent space of the model and uses the k-means cost function to improve the training process. In addition, the proposed method has an attention mechanism based on morphological operations called Inject-Multiply. This mechanism integrates morphological features obtained from post-wildfire vegetation index data and moisture changes captured in Sentinel-2 images, focusing on enriching features related to the shape and boundaries of burned areas. This study evaluates the effectiveness of the proposed method in labeling, identifying, and mapping burned areas using benchmark datasets, using different evaluation criteria. The model achieves an accuracy of over 93 % on the UZB-WF2022 dataset. This approach increases the accuracy of burned area detection in similar datasets and facilitates more informed decision-making for post-wildfire recovery and land management.

Massive Multiple Input Multiple Output (mMIMO) is a promising solution for enabling green communication in next-generation wireless networks. Integrating mMIMO with Simultaneous Wireless Information and Power Transfer (SWIPT) technology can further enhance the system efficiencies in terms of Energy Efficiency (EE) and spectral efficiency. This article studies the feasibility and energy-efficient design of a uniform planar antenna (UPA)-assisted mMIMO-enabled SWIPT system. The downlink transmission of the SWIPT mMIMO system over the Rician fading channels is investigated with terminals harvesting energy based on a nonlinear energy harvesting model. We derive approximate expressions for signal-to-interference-plus-noise Ratio (SINR) and harvested power. Additionally, we formulate an EE optimization problem considering user-level quality of service and total transmit power constraints. To solve this nonconvex problem, we jointly optimize the allocated power and Power Splitting (PS) ratios by exploiting the fractional programming and convex-concave procedure approaches. Results demonstrate the superiority of our proposed design compared to the conventional scenarios with equal power allocation and fixed PS ratio algorithms with about 2 to 5 times EE improvements. The Results also indicate a considerably higher growth rate on EE by increasing the number of antennas and Rician factors compared to the two other methods.

Today, agriculture plays an important role due to population growth and increasing demand for food. Diseases caused by bacteria, fungi, and viruses are an effective factor in product quality. Accurate diagnosis and identification of plant diseases are necessary to developing intelligent and modern agricultural production. Plant diseases can affect leaves during cultivation, causing serious damage to crop quality, yield, and economic value. Therefore, in the farming industry, the identification of leaf diseases plays a vital role, and since there are many types of leaf diseases and pests, their pathology is very complex. Manual diagnosis of these diseases is time-consuming and requires expertise in this field. Deep learning techniques have introduced several smart solutions to detect and control plant pests and diseases effectively. Deep learning is a branch of artificial intelligence that has received a lot of attention in recent years, with the benefits of automatic feature learning and extraction. Convolutional neural network (CNN) is one of the most important networks in the field of deep learning. CNN-based deep learning methods have made significant progress in image classification. Several factors related to plant disease detection using deep learning techniques need to be considered to develop a robust system for accurate disease management. This article discussed and studied a deep learning-based method using CNN networks and a series of preprocessing with entropy filters to detect tomato leaf diseases. The proposed model achieved 98.42% accuracy for the classification of 11 classes with a loss function of 0.08. We recommend using the proposed network because it requires less time and memory than previous works to achieve the desired accuracy.

Hyperspectral anomaly detection (HAD) is an area of hyperspectral image processing that seeks to identify observations that deviate from their surroundings both spectrally and spatially. Recently, generative adversarial networks (GANs) and auto-encoders (AEs) have been used to detect hyperspectral anomalies; however, current AE and GAN based approaches do not account for the intercorrelation of channels when reconstructing the image background. In this paper, an attention-based generative adversarial network (attention-GANomaly) is proposed to detect hyperspectral anomalies. This network uses attention mechanism and skip connections on both spectral channels and convolutional channels to eliminate inter-channel correlation problem;; it uses the entire hyperspectral image (HSI) as input for background reconstruction rather than relying on certain assumptions for HSI; Given the importance of contextual information in hyperspectral imaging, this network also uses context loss. This model reconstructs hyperspectral image background effectively by focusing more attention on normal features. By removing the reconstructed background from the original image, anomalies are revealed. We employ a conditional generative adversarial network as a baseline model, which simultaneously learns how to generate a high-dimensional picture space and how to derive a latent space. In this network, the intercorrelation of typical characteristics was extensively taken into account by including efficient channel attention (ECA) blocks. Additionally, l1-l2 and l2 regularizes were introduced to the network to prevent overfitting. Experimental findings on four publicly available datasets show the effectiveness of the suggested attention-GANomaly strategy, with AUC values of 0.9992, 0.9991, 0.9967, and 0.9996.

Mobile edge computing (MEC) is emerging as a critical technology for supporting latency-sensitive and computation-intensive services-however, random wireless channel fading limits offloading rates, posing a significant challenge to MEC performance. In MEC systems, effective energy management and high-speed communication links between user devices and MEC servers are essential for supporting services that require low latency and high computation power. Reconfigurable intelligent surfaces (RIS) have been proposed as a promising solution to enhance the quality of communication links between users and MEC servers by dynamically reconfiguring the wireless propagation environment to overcome these challenges. We formulate a trade-off optimization problem to balance SE and EE in RIS-aided MEC systems, which is crucial due to limited system resources and the need for dynamic adaptation to varying network requirements-aimed at joint optimization of transmission power, phase-shift matrix, and MEC offloading and computation delays. Given the problem’s intractability, we develop an alternating optimization-based iterative algorithm incorporating quadratic transformation and successive convex approximation techniques to obtain sub-optimal solutions. Firstly, we address the minimum delay power allocation and task offloading by using quadratic transformations for fractional problems and closed-form solutions. Afterward, we optimize the phase shifts through semidefinite programming and a penalty-based approach. Simulation results validate the effectiveness of the proposed framework, demonstrating significant improvements in SE and EE compared to conventional systems without RIS or with static RIS configurations.

Hyperspectral imagery is widely used for analyzing substances and objects, specifically focusing on their classification. The advancement of processing capabilities and the emergence of cloud computing platforms have made deep learning (DL) models increasingly popular for accurately and efficiently hyperspectral images (HSI) classification. In addition, utilizing image-processing techniques that employ specific mathematical operations for feature extraction and noise reduction further improves the precision of HSI classification. This study introduces the ResMorCNN model, which utilizes 3-D convolutional layers and morphology mathematics to extract structural information, shapes, and interregional interactions from HSIs. These features are then incorporated into the model's layers using residual connections. This approach significantly enhances the classification accuracy of datasets with different characteristics. In fact, the proposed model achieves an average accuracy higher than the top-performing DL method in a competition. To evaluate the overall effectiveness of the proposed method, it was tested on four distinct and comprehensive datasets, Indian Pines, Pavia University, Houston University, and Salinas. These datasets were carefully selected, taking into account factors such as scale, dispersion, and sample size. The overall accuracy results obtained for each evaluated dataset were 97.81%, 99.33%, 98.67%, and 99.71%, respectively. This demonstrates an average improvement of 3.37% compared to the results of the best-performing method. The results demonstrate the effectiveness of the proposed ResMorCNN model for various applications that require accurate and efficient classification of HSI.

Oceanic eddies are a widespread and important occurrence that plays a vital role in the movement of chemicals and energy within the marine ecosystem. Hence, the astute and precise recognition of these swirling currents may greatly contribute to the progress of our comprehension of oceanography. Due to the continuous breakthroughs in state-of-the-art deep learning technology, the population is witnessing a progressive improvement in the methods used to identify and understand these aquatic characteristics. This study employs sea surface temperature data acquired from the Copernicus Marine and Environment Monitoring Service (CMEMS) in the Atlantic Ocean. The objective is to present EddyNet, a cutting-edge deep-learning framework specifically developed for the automatic identification and categorization of ocean eddies. EddyNet incorporates a pixel-wise classification layer into its neural encoder-decoder architecture. The resulting output is a map that maintains the same dimensions as the input, but each individual pixel is assigned a label indicating its classification as either "0" for noneddy regions, "1" for anticyclonic eddies, or "2" for cyclonic eddies. We propose a new image segmentation method based on the U-net architecture with different convolutional neural network backbones such as VGG16, VGG19, DenseNet121, and MobileNetV2. Our models are built and trained using Python and the Keras library with the Adam optimizer for improved convergence. Our approach uses sparse categorical cross-entropy as the loss function, simplifying the label encoding process for multiclass classification with sparse labels. Initial results show that this method achieves a good balance between computational efficiency and segmentation accuracy, making it suitable for real-time applications.

Precise prediction of agricultural production output is crucial for farmers, policymakers, and the Farming-related industry. This article introduces a novel methodology to crop yield forecasting using a capsular neural network equipped with Conv-LSTM and attention mechanism. Our model combines the strengths of 3DCNN, and ConvLSTM, which can capture the temporal dependencies and 3D features of crop yield data, and attention mechanism, which Can prioritize the most significant characteristics for making predictions. We evaluated CACN on a sizable collection of data of soybean crop yield in the United States from 2003 to 2019 and evaluated against various cutting-edge deep learning models. The outcomes indicate that our suggested approach surpasses other models in performance in terms of RMSE, correlation coefficient, and prediction error map. Specifically, our model achieved approximately 14 % improvement in terms of RMSE, compared to the state-of-the-art model Deep-Yield. Our model also demonstrated the ability to extract more meaningful features and capture the complex relationships between crop yield data and meteorological variables. Overall, our proposed method shows great potential for accurate and efficient crop yield forecasting and can be applied to other crops and regions.

These days, extracting information from remote sensing data has a great impact on various aspects of our lives, such as infrastructure and urban planning, transportation and traffic management, forecasting and tracking natural disasters, searching for mineral resources, monitoring environmental changes, and numerous other fields. One crucial application is extracting accurate road information from aerial images, which has many practical applications ranging from our daily lives to long-term planning for transportation systems to autonomous vehicles. Deep learning models have shown great promise in image-processing tasks, specifically in accurately detecting and extracting roads from aerial images. In this study, various techniques were employed to achieve the desired performance. The model is a UNet assisted with attention blocks in the decoder part and trained with a patched, rotated, and augmented dataset that has been extracted from the DeepGlobe dataset. The preprocessing of the dataset included image and mask patching, rotation, exclusion of background-only images, and excluding images with very little road surface. Both patching and background exclusion in preprocessing as hard attention and attention blocks in the model as soft attention were deployed in order to tackle the inherently biased nature of the dataset. This combination of different techniques empowers the proposed model for superior remote sensing image segmentation performance with an accuracy level of 98.33%. In addition to achieve better performance by the model, another objective is to find the issues that cause the model's performance degradation on some image samples. Therefore, a comprehensive analysis of metrics, with a focus on precision and recall as proper metrics for biased dataset analysis, was conducted to identify potential shortcomings in the model or the dataset, and based on the result, several proposals for future work and further investigations were formulated.

The advent of cloud computing and advanced processing technologies has elevated deep learning (DL) as a leading method for hyperspectral imaging (HSI) classification. Classifying crops accurately is vital for generating precise agricultural data to support informed decision-making. This study introduces a DL framework, called HypsLiDNet, tailored for remote sensing activities. This model processes HSI in conjunction with innovative, comprehensive light detection and ranging (LiDAR) data from Hungary to conduct thorough examinations of the Earth's surface. Integrating LiDAR attributes with HSI is anticipated to enhance classification accuracy beyond HSI-only techniques. LiDAR integration provides a significant advantage by adding structural details to spectral data, aiding in the correct identification of objects with similar spectral characteristics but different shapes.The HypsLiDNet method utilizes morphological operations on LiDAR data to extract features indicative of the land's shape and texture. These features are then combined with HSI data through an attention mechanism that selectively highlights key features from both data types, improving the model's accuracy in predictions. This is particularly beneficial for complex environmental assessments, such as distinguishing between plant species. The attention mechanism also refines the feature selection process, prioritizing relevant information, which boosts computational efficiency and reduces the use of resources. Moreover, this method requires a smaller number of training samples. HypsLiDNet showcases its ability to classify with precision by harnessing the combined power of HSI and LiDAR data. Experimental results show a significant improvement in classification outcomes, outperforming traditional machine learning approaches by more than 14% and recent DL techniques by approximately 1%-3%.

The advent of cloud computing and advanced processing technologies has elevated deep learning (DL) as a leading method for hyperspectral imaging (HSI) classification. Classifying crops accurately is vital for generating precise agricultural data to support informed decision-making. This study introduces a DL framework, called HypsLiDNet, tailored for remote sensing activities. This model processes HSI in conjunction with innovative, comprehensive light detection and ranging (LiDAR) data from Hungary to conduct thorough examinations of the Earth's surface. Integrating LiDAR attributes with HSI is anticipated to enhance classification accuracy beyond HSI-only techniques. LiDAR integration provides a significant advantage by adding structural details to spectral data, aiding in the correct identification of objects with similar spectral characteristics but different shapes.The HypsLiDNet method utilizes morphological operations on LiDAR data to extract features indicative of the land's shape and texture. These features are then combined with HSI data through an attention mechanism that selectively highlights key features from both data types, improving the model's accuracy in predictions. This is particularly beneficial for complex environmental assessments, such as distinguishing between plant species. The attention mechanism also refines the feature selection process, prioritizing relevant information, which boosts computational efficiency and reduces the use of resources. Moreover, this method requires a smaller number of training samples. HypsLiDNet showcases its ability to classify with precision by harnessing the combined power of HSI and LiDAR data. Experimental results show a significant improvement in classification outcomes, outperforming traditional machine learning approaches by more than 14% and recent DL techniques by approximately 1%–3%.

This article introduces an approach for soybean yield prediction by integrating convolutional long short-term memory (ConvLSTM), three-dimensional convolutional neural network (3D-CNN), and vision transformer (ViT). By utilizing multispectral remote sensing data, our model leverages the spatial hierarchy of 3D-CNNs, the temporal sequencing capabilities of ConvLSTM, and the global context analysis of ViTs to capture complex patterns in agricultural datasets. The integration of these advanced methodologies allows for a comprehensive analysis of both spatial and temporal aspects of crop growth, enabling more accurate and robust predictions. Our experimental results demonstrate that the proposed model significantly outperforms existing methods, as evidenced by lower root mean square error and higher correlation coefficients. The 3D-CNN component effectively extracts spatial features from the multispectral images, while the ConvLSTM captures the temporal dynamics of crop development. The ViT further refines these features by focusing on the most relevant parts of the input data through self-attention mechanisms. The findings highlight the potential of this model in enhancing decision-making processes in crop management, particularly in precision agriculture. By providing more accurate yield predictions, the model can assist farmers in optimizing resource allocation, scheduling irrigation, and applying fertilizers more efficiently, thereby promoting sustainable farming practices. Furthermore, the model's robustness across various conditions underscores its applicability to different crops and geographic regions. This article contributes to the field of agricultural remote sensing by offering a robust solution to the complexities of analyzing large-scale, multispectral data. The proposed approach not only improves prediction accuracy but also provides timely and actionable insights for agricultural stakeholders.

Recent advancements in remote sensing technology have significantly expanded the exploration of natural resources and enabled the detection of materials in inaccessible areas. Hyperspectral images (HSIs) are a valuable data source due to their distinctive properties in various applications. However, several problems, including noise, band correlation, ineffectively extracted features, and most notably, a lack of sufficient labeled samples, reduce the accuracy of HSI classification. To improve the performance of such a system, we propose an effective method with the capability of paying attention to spectral and spatial features. The raw HSI data are first preprocessed using a principal component analysis (PCA) operation because of the redundancy and correlation between HSI bands. Then, the entropy base informative module is designed to add entropy information to the selected spectral features by PCA. We also use spectral and spatial attention modules in the proposed model. Moreover, a hybrid neural network that uses both 3-D convolutional neural networks (CNNs) and 2-D CNNs with skip connections is exploited to reduce the complexity of the network compared to 3-D CNNs. The spatial attention module called depthwise spatial attention block can inherently highlight spatial information. The spectral attention module named reshape softmax attention can capture useful spectral regions of feature maps. Meticulous HSI classification tests are conducted over the University of Pavia, Indian Pines, Salinas, and Houston 2013 to evaluate the effectiveness of our approach. Our experiments show higher accuracy compared to other deep learning methods.

In recent years, national economies are highly affected by crop yield predictions. By early prediction, the market price can be predicted, importing, and exporting plan can be provided, social, and economic effects of waste products can be minimized, and a program can be presented for humanitarian food aid. In addition, agricultural fields are constantly growing to generate products required. The use of machine learning (ML) methods in this sector can lead to the efficient production and high-quality agricultural products. Traditional predictive machine models were unable to find nonlinear relationships between data. Recently, there has been a revolution in prediction systems via the advancement of ML, which can be used to achieve highly accurate decision-making networks. Thus far, many strategies have been used to evaluate agricultural products, such as DeepYield, CNN-LSTM, and ConvLSTM. However, preferable prediction accuracy is required. In this study, two architectures have been proposed. The first model includes 2D-CNN, skip connections, and LSTM-Attentions. The second model comprises 3D-CNN, skip connections, and ConvLSTM Attention. The Input data given from MODIS products such as Land-Cover, Surface-Temperature, and MODIS-Land-surface from 2003 to 2018 on the county level over 1800 counties, where soybean is mainly cultivated in the USA. The proposed methods have been compared with the most recent models. Then, the results showed that the second proposed method notably outperformed the other techniques. In case of MAE, the second proposed method, DeepYield, ConvLSTM, 3DCNN, and CNN-LSTM obtained 4.3, 6.003, 6.05, 6.3, and 7.002, respectively.

This study delves into the examination of the Physical Layer Security (PLS) of in-home Broadband Power Line Communication (BB-PLC) systems and highlights the use of secrecy capacity as a metric for evaluating the PLS of the communication system. The impact of Impulsive Noise (IN) on the secrecy capacity of a single-input single-output (SISO) Orthogonal Frequency Division Multiplexing (OFDM) wiretap channel for in-home power line communication systems is analyzed in detail. The results demonstrate that the secrecy capacity of the system can be significantly improved by up to 38% through the utilization of an improved MH iterative algorithm and 55% through the application of pure elimination techniques. The paper also highlights the potential of the impulsive noise of in-home PLC channels to act as artificial noise, thus improving the randomness for the eavesdropper, provided the legitimate receiver effectively mitigates the effects of IN. The findings of this study provide valuable insights into the PLS of in-home BB-PLC systems and offer practical solutions for enhancing their security.