Search

Understanding land use and damage in open-pit coal mining areas is crucial for effective scientific oversight and management. Current recognition methods exhibit limitations: traditional approaches depend on manually designed features, which offer limited expressiveness, whereas deep learning techniques are heavily reliant on sample data. In order to overcome the aforementioned limitations, a three-branch feature extraction framework was proposed in the present study. The proposed framework effectively fuses deep features (DF) and shallow features (SF), and can accomplish scene recognition tasks with high accuracy and fewer samples. Deep features are enhanced through a neighbouring feature attention module and a Graph Convolutional Network (GCN) module, which capture both neighbouring features and the correlation between local scene information. Shallow features are extracted using the Gray-Level Co-occurrence Matrix (GLCM) and Gabor filters, which respectively capture local and overall texture variations. Evaluation results on the AID and RSSCN7 datasets demonstrate that the proposed deep feature extraction model achieved classification accuracies of 97.53% and 96.73%, respectively, indicating superior performance in deep feature extraction tasks. Finally, the two kinds of features were fused and input into the particle swarm algorithm optimised support vector machine (PSO-SVM) to classify the scenes of remote sensing images, and the classification accuracy reached 92.78%, outperforming four other classification methods. [ABSTRACT FROM AUTHOR]

Understanding the spatial and temporal patterns of sediment loading in water bodies is crucial for effective water quality management. Remote sensing (RS) has emerged as a valuable and reliable tool for monitoring turbidity, which can provide insights into sediment dynamics in water bodies. In this study, we investigate the potential of turbidity data derived from RS to explain simulated spatial and temporal sediment loading patterns in the Lake Tana basin, Ethiopia. Utilizing existing RS lake turbidity data from Copernicus Global Land Service (CGLS) and simulated seasonal and multiyear trends of river sediment loadings into Lake Tana from the Soil and Water Assessment Tool (SWAT + model), we estimate correlations at different river inlets into Lake Tana. The results reveal a strong positive correlation (R2 > 0.66) between the multiyear monthly average sediment load from inflow rivers and RS lake turbidity at most river inlets. This indicates that the simulated river sediment loads and lake turbidity at river inlets exhibit similar seasonal patterns. Notably, higher turbidity levels are observed at the river inlet with the highest sediment load export. These findings highlight the potential of RS turbidity products in characterizing temporal and spatial patterns of sediment loadings, particularly in data-scarce regions, contributing to a better understanding of water quality dynamics in such areas. [ABSTRACT FROM AUTHOR]

The timely updating of the spatial distribution of buildings is essential to understanding a city's development. Deep learning methods have remarkable benefits in quickly and accurately recognizing these changes. Current semi-supervised change detection (SSCD) methods have effectively reduced the reliance on labeled data. However, these methods primarily focus on utilizing unlabeled data through various training strategies, neglecting the impact of pseudo-changes and learning bias in models. When dealing with limited labeled data, abundant low-quality pseudo-labels generated by poorly performing models can hinder effective performance improvement, leading to the incomplete recognition results of changes to buildings. To address this issue, we propose a feature multi-scale information interaction and complementation semi-supervised method based on consistency regularization (MSFG-SemiCD), which includes a multi-scale feature fusion-guided change detection network (MSFGNet) and a semi-supervised update method. Among them, the network facilitates the generation of multi-scale change features, integrates features, and captures multi-scale change targets through the temporal difference guidance module, the full-scale feature fusion module, and the depth feature guidance fusion module. Moreover, this enables the fusion and complementation of information between features, resulting in more complete change features. The semi-supervised update method employs a weak-to-strong consistency framework to achieve model parameter updates while maintaining perturbation invariance of unlabeled data at both input and encoder output features. Experimental results on the WHU-CD and LEVIR-CD datasets confirm the efficacy of the proposed method. There is a notable improvement in performance at both the 1% and 5% levels. The IOU in the WHU-CD dataset increased by 5.72% and 6.84%, respectively, while in the LEVIR-CD dataset, it improved by 18.44% and 5.52%, respectively. [ABSTRACT FROM AUTHOR]

The exponential growth in population and physical infrastructure since 1980 has imposed immense pressure on Dhaka Metropolitan City (DMC), triggering extensive urbanization and a surge in built-up areas. This urban expansion has intensified the urban heat island (UHI) effect (the phenomenon where urban areas experience significantly higher temperatures compared to surrounding areas), resulting in adverse global urban climate changes such as temperature spikes, erratic rainfall, and compromised air quality. This study aims to discern the heat wave trends in DMC from 1972 to 2020 and elucidate their impact on public health and livelihoods. Employing a blend of quantitative and qualitative methodologies, the research analysis of land surface temperatures (LST) and land cover indices reveals a significant increase in built-up areas, particularly in western and central parts of the city, correlating with higher LST. Satellite imagery (Landsat 5 and 8) with 30-m resolution and meteorological data indicate a rise in surface temperatures. Analysis reveals April, May, and June as the peak months for heat wave occurrences, with DMC enduring a total of 328 heat wave days according to heat index (a measurement of perceived temperature in human body indicating how hot it feels when relative temperature is added to the actual air temperature) classifications. Notably, the density of built-up areas, particularly in central and western regions, exacerbates the UHI effect, evident in rising surface temperatures reaching 40.1 °C in 2014. The study underscores the dire health hazards posed by heat waves, with vulnerable populations, such as slum dwellers and outdoor laborers, facing heightened risks. Despite widespread impacts, public awareness about heat waves remains deficient, as evidenced by respondents' limited understanding of the term. These outcomes and prepared maps of the current research will be supportive for the local inhabitant, urban planner, and environmental resources management manager, national and international policy advisor, government and non-movement stakeholder, and researcher to observe the urban climate, trend of heat wave, and its impact on exposed people. [ABSTRACT FROM AUTHOR]

Abstract Understanding land use and damage in open-pit coal mining areas is crucial for effective scientific oversight and management. Current recognition methods exhibit limitations: traditional approaches depend on manually designed features, which offer limited expressiveness, whereas deep learning techniques are heavily reliant on sample data. In order to overcome the aforementioned limitations, a three-branch feature extraction framework was proposed in the present study. The proposed framework effectively fuses deep features (DF) and shallow features (SF), and can accomplish scene recognition tasks with high accuracy and fewer samples. Deep features are enhanced through a neighbouring feature attention module and a Graph Convolutional Network (GCN) module, which capture both neighbouring features and the correlation between local scene information. Shallow features are extracted using the Gray-Level Co-occurrence Matrix (GLCM) and Gabor filters, which respectively capture local and overall texture variations. Evaluation results on the AID and RSSCN7 datasets demonstrate that the proposed deep feature extraction model achieved classification accuracies of 97.53% and 96.73%, respectively, indicating superior performance in deep feature extraction tasks. Finally, the two kinds of features were fused and input into the particle swarm algorithm optimised support vector machine (PSO-SVM) to classify the scenes of remote sensing images, and the classification accuracy reached 92.78%, outperforming four other classification methods.

Copyright of Baghdad Science Journal is the property of Republic of Iraq Ministry of Higher Education & Scientific Research (MOHESR) and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

The increase in water demand and the scarcity of fresh water in arid regions have contributed to the depletion of groundwater. Artificial Groundwater Recharge (AGR) is an advanced strategy that contributes to combating water shortage issues. Limited efforts have been exerted to evaluate and demarcate AGR potential zones in the United Arab Emirates (UAE). The current study aims to delineate AGR potential zone mapping using the traditional analytical hierarchy process (AHP) and a hybrid deep learning model namely, Convolutional Neural Network-Xtreme Gradient Boosting (CNN-XGB) was used for the optimal prediction-based suitability assessment. A total of nine hydrogeological factors were considered for AGR mapping. First, the influence of each parameter was determined based on expert opinion and literature reviews for the AHP approach (0.007 consistency ratio). Second, a hybrid CNN-XGB model (90.8 % accuracy) predicted the AGR and non-AGR classes as part of binary classification and generated an AGR potential zone map. Moreover, the contributing factors were analyzed deeply for the AGR site selection to understand the intercorrelation, importance, and prediction interaction. Using both approaches, a comparative assessment was conducted in the eastern, central, and western parts of Sharjah. The AGR zone based on the CNN-XGB model achieved a precision of (0.8168), recall (0.7873), and F1-score (0.8018). The critical contributing factors for AGR mapping were found to be geology (20%), geomorphology (15%), rainfall (10%), and groundwater level (10%). The AGR map is expected to help explore new sites with potentially higher favourability to retain water, deal with water scarcity, and improve water management in the UAE.

Remote sensing (RS) technologies are extensively exploited by scientists and a vast audience of local authorities, urban managers, and city planners. Coastal regions, geohazard-prone areas, and highly populated cities represent natural laboratories to apply RS technologies and test new methods. Over the last decades, many efforts have been spent on improving Earth’s surface monitoring, including intensifying Earth Observation (EO) operations by the major national space agencies. They oversee to plan and make operational constellations of satellite sensors providing the scientific community with extensive research and development opportunities in the geoscience field. For instance, within this framework, the European Space Agency (ESA) and the Ministry of Science and Technology of China (MOST) have sponsored, since the early 2000s, the DRAGON initiative jointly carried out by the European and Chinese RS scientific communities. This manuscript aims to provide a synthetic overview of some research activities and new methods recently designed and applied and trace the route for further developments. The main findings are related to i) the analysis of flood risk in China, ii) the potential of new methods for the estimation and removal of ground displacement biases in small-baseline oriented interferometric Synthetic Aperture Radar (SAR) methods, iii) the analysis of the inundation risk in low-lying regions using coherent and incoherent SAR methods; and iv) the use of SAR-based technologies for marine applications.

Since 2007, the Yellow Sea green tide has broken out every summer, causing great harm to the environment and society. Although satellite remote sensing (RS) has been used in biomass research, there are several shortcomings, such as mixed pixels, atmospheric interference, and difficult field validation. The biomass of green tide has been lacking a high-precision estimation method. In this study, high-resolution unmanned aerial vehicle (UAV) RS was used to quantitatively map the biomass of green tides. By utilizing experimental data from previous studies, a robust relationship was established to link biomass to the red-green-blue floating algae index (RGB-FAI). Then, the lab-based model for green tide biomass from visible images taken by the UAV camera was developed and validated by field measurements. Results show that the accurate and cost-effective method is able to estimate the green tide biomass and its changes in given local waters of the near and far seas. The study provided an effective complement to the traditional satellite RS, as well as high-precision quantitative techniques for decision-making in disaster management. [ABSTRACT FROM AUTHOR]

Copyright of Irrigation & Drainage is the property of Wiley-Blackwell and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

In recent years, classification and identification of Earth's surface materials has been a challenging research topic in the field of earth science and remote sensing (RS). Although deep learning techniques have achieved some results in remote sensing image classification, there are still some challenges for multimodal remote sensing data classification, such as information redundancy between multimodal remote sensing images. In this paper, we propose a multimodal remote sensing data classification method IFF-Net based on irregular feature fusion, called IFF-Net. The IFF-Net architecture utilizes weight-shared residual blocks for feature extraction while maintaining the independent batch normalization (BN) layer. During the training phase, the redundancy of the current channel is determined by evaluating the judgement factor of the BN layer. If this judgment factor falls below a predefined threshold, it indicates that the current channel information is redundant and should be substituted with another channel. Sparse constraints are imposed on some of the judgment factors in order to remove extra channels and enhance generalization. Furthermore, a module for feature normalization and calibration has been devised to leverage the spatial interdependence of multimodal features in order to achieve improved discrimination. Two standard datasets are used in the experiments to validate the effectiveness of the proposed method. The experimental results show that the IFF-NET method proposed in this paper exhibits significantly superior performance compared to the state-of-the-art methods. [ABSTRACT FROM AUTHOR]

The increase in water demand and the scarcity of fresh water in arid regions have contributed to the depletion of groundwater. Artificial Groundwater Recharge (AGR) is an advanced strategy that contributes to combating water shortage issues. Limited efforts have been exerted to evaluate and demarcate AGR potential zones in the United Arab Emirates (UAE). The current study aims to delineate AGR potential zone mapping using the traditional analytical hierarchy process (AHP) and a hybrid deep learning model namely, Convolutional Neural Network-Xtreme Gradient Boosting (CNN-XGB) was used for the optimal prediction-based suitability assessment. A total of nine hydrogeological factors were considered for AGR mapping. First, the influence of each parameter was determined based on expert opinion and literature reviews for the AHP approach (0.007 consistency ratio). Second, a hybrid CNN-XGB model (90.8 % accuracy) predicted the AGR and non-AGR classes as part of binary classification and generated an AGR potential zone map. Moreover, the contributing factors were analyzed deeply for the AGR site selection to understand the intercorrelation, importance, and prediction interaction. Using both approaches, a comparative assessment was conducted in the eastern, central, and western parts of Sharjah. The AGR zone based on the CNN-XGB model achieved a precision of (0.8168), recall (0.7873), and F1-score (0.8018). The critical contributing factors for AGR mapping were found to be geology (20%), geomorphology (15%), rainfall (10%), and groundwater level (10%). The AGR map is expected to help explore new sites with potentially higher favourability to retain water, deal with water scarcity, and improve water management in the UAE. [ABSTRACT FROM AUTHOR]

Remote sensing (RS) technologies are extensively exploited by scientists and a vast audience of local authorities, urban managers, and city planners. Coastal regions, geohazard-prone areas, and highly populated cities represent natural laboratories to apply RS technologies and test new methods. Over the last decades, many efforts have been spent on improving Earth's surface monitoring, including intensifying Earth Observation (EO) operations by the major national space agencies. They oversee to plan and make operational constellations of satellite sensors providing the scientific community with extensive research and development opportunities in the geoscience field. For instance, within this framework, the European Space Agency (ESA) and the Ministry of Science and Technology of China (MOST) have sponsored, since the early 2000s, the DRAGON initiative jointly carried out by the European and Chinese RS scientific communities. This manuscript aims to provide a synthetic overview of some research activities and new methods recently designed and applied and trace the route for further developments. The main findings are related to i) the analysis of flood risk in China, ii) the potential of new methods for the estimation and removal of ground displacement biases in small-baseline oriented interferometric Synthetic Aperture Radar (SAR) methods, iii) the analysis of the inundation risk in low-lying regions using coherent and incoherent SAR methods; and iv) the use of SAR-based technologies for marine applications. [ABSTRACT FROM AUTHOR]

In this paper, we delve into the innovative application of large language models (LLMs) and their extension, large vision-language models (LVLMs), in the field of remote sensing (RS) image analysis. We particularly emphasize their multi-tasking potential with a focus on image captioning and visual question answering (VQA). In particular, we introduce an improved version of the Large Language and Vision Assistant Model (LLaVA), specifically adapted for RS imagery through a low-rank adaptation approach. To evaluate the model performance, we create the RS-instructions dataset, a comprehensive benchmark dataset that integrates four diverse single-task datasets related to captioning and VQA. The experimental results confirm the model's effectiveness, marking a step forward toward the development of efficient multi-task models for RS image analysis. [ABSTRACT FROM AUTHOR]

Relative radiometric normalization (RRN) is a critical pre-processing step that enables accurate comparisons of multitemporal remote-sensing (RS) images through unsupervised change detection. Although existing RRN methods generally have promising results in most cases, their effectiveness depends on specific conditions, especially in scenarios with land cover/land use (LULC) in image pairs in different locations. These methods often overlook these complexities, potentially introducing biases to RRN results, mainly because of the use of spatially aligned pseudo-invariant features (PIFs) for modeling. To address this, we introduce a location-independent RRN (LIRRN) method in this study that can automatically identify non-spatially matched PIFs based on brightness characteristics. Additionally, as a fast and coregistration-free model, LIRRN complements keypoint-based RRN for more accurate results in applications where coregistration is crucial. The LIRRN process starts with segmenting reference and subject images into dark, gray, and bright zones using the multi-Otsu threshold technique. PIFs are then efficiently extracted from each zone using nearest-distance-based image content matching without any spatial constraints. These PIFs construct a linear model during subject–image calibration on a band-by-band basis. The performance evaluation involved tests on five registered/unregistered bitemporal satellite images, comparing results from three conventional methods: histogram matching (HM), blockwise KAZE, and keypoint-based RRN algorithms. Experimental results consistently demonstrated LIRRN's superior performance, particularly in handling unregistered datasets. LIRRN also exhibited faster execution times than blockwise KAZE and keypoint-based approaches while yielding results comparable to those of HM in estimating normalization coefficients. Combining LIRRN and keypoint-based RRN models resulted in even more accurate and reliable results, albeit with a slight lengthening of the computational time. To investigate and further develop LIRRN, its code, and some sample datasets are available at link in Data Availability Statement. [ABSTRACT FROM AUTHOR]

The self-supervised learning (SSL) technique, driven by massive unlabeled data, is expected to be a promising solution for semantic segmentation of remote sensing images (RSIs) with limited labeled data, revolutionizing transfer learning. Traditional 'local-to-local' transfer from small, local datasets to another target dataset plays an ever-shrinking role due to RSIs' diverse distribution shifts. Instead, SSL promotes a 'global-to-local' transfer paradigm, in which generalized models pre-trained on arbitrarily large unlabeled datasets are fine-tuned to the target dataset to overcome data distribution shifts. However, the SSL pre-trained models may contain both useful and useless features for the downstream semantic segmentation task, due to the gap between the SSL tasks and the downstream task. To adapt such pre-trained models to semantic segmentation tasks, traditional supervised fine-tuning methods that use only a small number of labeled samples may drop out useful features due to overfitting. The main reason behind this is that supervised fine-tuning aims to map a few training samples from the high-dimensional, sparse image space to the low-dimensional, compact semantic space defined by the downstream labels, resulting in a degradation of the distinguishability. To address the above issues, we propose a class distinguishability-enhanced self-training (CDEST) method to support global-to-local transfer. First, the self-training module in CDEST introduces a semi-supervised learning mechanism to fully utilize the large amount of unlabeled data in the downstream task to increase the size and diversity of the training data, thus alleviating the problem of biased overfitting of the model. Second, the supervised and semi-supervised contrastive learning modules of CDEST can explicitly enhance the class distinguishability of features, helping to preserve the useful features learned from pre-training while adapting to downstream tasks. We evaluate the proposed CDEST method on four RSI semantic segmentation datasets, and our method achieves optimal experimental results on all four datasets compared to supervised fine-tuning as well as three semi-supervised fine-tuning methods. [ABSTRACT FROM AUTHOR]

BACKGROUND AND OBJECTIVES: Oil palm is an agricultural crop essential to Indonesia's economy. Therefore, the number of oil palm plantations has increased, leading to widespread deforestation in Indonesia, including Jambi Province. In this investigation, remote sensing with a geographic information system approach is used to evaluate deforestation and the land changes caused by oil palm expansion conducted by smallholders that eventually influence environmental change. This study conducts a spatiotemporal (spatial and temporal) analysis of oil palm land clearing in Jambi Province that results in land changes and environmental impacts. METHODS: This research used data from Landsat 8 satellite imagery. The land cover classification was conducted using the Maximum Likelihood approach, whereas the overlay method was used for land change analysis. The accuracy assessment of classification results used a confusion matrix by considering the overall accuracy and Kappa Coefficient. Within the field observation, the validation class was the oil palm class, and documentation and plotting using the global positioning system were conducted. Other classes were validated using the region of interest collected through Google Earth. This research used the Aviation Reconnaissance Coverage Geographic Information System 10.1 software to transform the categorization results into vector data. FINDINGS: This study shows that the land cover classification results have high accuracy and that the area of oil palm land from 2015 to 2019 has increased along with a decrease in land used, such as forests and others. The area of oil palm land in 2014 was 2,071,345 hectares, whereas that in 2019 was 2,110,545 hectares. In particular, the land cover area increased by 39.2 thousand hectares because of land clearing and deforestation. Moreover, the built-up area has increased in the last five years by 165,358 hectares. The number of oil palm plantations in relatively plain areas tends to be greater than that in areas with relatively high altitudes and steep slopes. Small farmers' area of oil palm land has increased by 1,000 hectares from 2014 to 2018. The most remarkable increase of approximately 38,889 hectares has occurred from 2016 to 2017. CONCLUSION: This study demonstrates that using Landsat 8 imagery with Geographic Information System approaches provides the optimal method for an in-depth analysis of land cover changes related to oil palm expansion and land clearing that occur on a broad spatial and temporal scale in Jambi Province. This study shows that smallholder oil palm plantations in the Jambi region play an important role in increasing deforestation not only in Jambi Province but also throughout Indonesia. This study is expected to serve as a valuable resource for informing policy decisions aimed at addressing the issue of deforestation resulting from the prospective increase in oil palm crops in the forthcoming period. [ABSTRACT FROM AUTHOR]

Accurate estimations of actual evapotranspiration (ETa) are essential to various environmental issues. Artificial intelligence-based models are a promising alternative to the most common direct ETa estimation techniques and indirect methods by remote sensing (RS)-based surface energy balance models. Artificial Neural Networks (ANNs) are proven to be suitable for predicting reference evapotranspiration (ETo) and ETa based on RS data. This study aims to develop a methodology based on ANNs for estimating daily ETa values using NDVI and land surface temperature, coupled with limited site-specific climatic variables in a large irrigation catchment. The ANN model has been applied to the two different scenarios. Data from only the 38 days of satellite overpass dates was selected in Scenario I, while in Scenario II all datasets, i.e., the 769-day data were used. An irrigation scheme, located in the Mediterranean region of Turkiye, was selected, and a total of 38 Landsat images and local climatic data collected in 2021 and 2022 were used in the ANN model. The ETa results by the ANN model for Scenarios I and II showed that the R2 values for training (0.79 and 0.86), testing (0.75 and 0.81), and the entire dataset (0.76 and 0.84) were all remarkably high. Moreover, the results of the new ANN model in two scenarios showed an acceptable agreement with ETa-METRIC values. The proposed ANN model demonstrated the potential for obtaining daily ETa using limited climatic data and RS imagery. As a result, the suggested ANN model for daily ETa computation offers a trustworthy way to determine crop water usage in real time for sustainable water management in agriculture. It may also be used to assess how crop evapotranspiration in drought-prone areas will be affected by climate change in the 21st century. [ABSTRACT FROM AUTHOR]

This article presents an assessment of the impact of mining activities in the Emalahleni municipality, using GIS and RS technologies. The random forest algorithm was used to classify the land use and land cover in the Emalahleni municipality over a three-decade period (1990–2020). The classifications are settlement, water, mining area, vegetation, and bare land. The majority of the study area was found to be rocky ground, accounting for approximately 60% of the total study area. Change detection maps were created for vegetation and mining to assess the extent of land degradation in the study area over the three-decade period. The findings in this study highlight the importance of understanding the changes in land use and vegetation cover in the study area and its impact on the environment, as well as the local community. It is crucial to develop sustainable land management strategies that ensure that a reasonable balance concerning the economic development activities is achieved, such as mining with environmental management for its long-term viability for future generations. The data presented in this study provides a useful baseline for further research and can inform land-use planning and decision-making processes in Emalahleni. [ABSTRACT FROM AUTHOR]

Contrastive learning allows us to learn general features for downstream tasks without the need for labeled data by leveraging intrinsic signals within remote sensing images. Existing contrastive learning methods encourage invariant feature learning by bringing positive samples defined by random transformations in feature spaces closer, where transformed samples of the same image at different intensities are considered equivalent. However, remote sensing images differ from natural images in their top-down perspective results in the arbitrary orientation of objects and in that the images contain rich in-plane rotation information. Maintaining invariance to rotation transformations can lead to the loss of rotation information in features, thereby affecting angle information predictions for differently rotated samples in downstream tasks. Therefore, we believe that contrastive learning should not focus only on strict invariance but encourage features to be equivariant to rotation while maintaining invariance to other transformations. To achieve this goal, we propose an invariant–equivariant covariant network (Co-ECL) based on collaborative and reverse mechanisms. The collaborative mechanism encourages rotation equivariance by predicting the rotation transformations of input images and combines invariant and equivariant learning tasks to jointly supervise the feature learning process to achieve collaborative learning. The reverse mechanism introduces a reverse rotation module in the feature learning stage, applying reverse rotation transformations with equal intensity to features in invariant learning tasks as in the data transformation stage, thereby ensuring their independent realization. In experiments conducted on three publicly available oriented object detection datasets of remote sensing images, our method consistently demonstrated the best performance. Additionally, these experiments on multi-angle datasets demonstrated that our method has good robustness on rotation-related tasks. [ABSTRACT FROM AUTHOR]

Changes in LULC triggered by urbanization lead to an increase in impermeable surface, which seriously deteriorates urban climatic conditions and thermal status (LST). Under this circumstance, we analyzed the spatiotemporal deviation of LST and LULC from 2008 to 2023 by using remote sensing Landsat satellite images of Bhairab, Kishoreganj. Major findings are the highly increasing trend of settlement area (7%–23% in summer and 8.5%–19.0% in winter) and waterbody whereas the decreasing trend of agriculture, vegetation and barren land. The thermal status observation indicates the extreme weather conditions, whereas the summer became more hotter (31 °C–34 °C max T), and the winter became more colder (28 °C–24 °C max T). The insights can assist local authorities in restructuring future development plans to mitigate the urban climate environment and foster a vibrant social life in Bhairab.

Differently from conventional procedures, the proposed solution advocates for a groundbreaking paradigm in water quality monitoring through the integration of satellite Remote Sensing data, Artificial Intelligence techniques, and onboard processing. While conventional procedures present several drawbacks mainly related to late intervention capabilities, the objective of what proposed is to offer nearly real-time detection of contaminants in coastal waters addressing a significant gap in the existing literature and allowing fast alerts and intervention. In fact, the expected outcomes include substantial advancements in environmental monitoring, public health protection, and resource conservation. Namely, the specific focus of our study is on the estimation of Turbidity and pH parameters, for their implications on human and aquatic health. Nevertheless, the designed framework can be extended to include other parameters of interest in the water environment and beyond. Originating from our participation in the European Space Agency OrbitalAI Challenge, this article describes the distinctive opportunities and issues for the contaminants' monitoring on the $\Phi$sat-2 mission. The specific characteristics of this mission, with the tools made available, will be presented, with the methodology proposed by the authors for the onboard monitoring of water contaminants in near real-time. Preliminary promising results are presented, along with an introduction to ongoing and future work.

With the rapid development of deep learning (DL), change detection (CD) in remote sensing (RS) image has achieved remarkable success. Nevertheless, as the image resolution improves, the visual features extracted by current methods have limited expression ability, and the networks generally suffer from spatial degradation, both of which lead to incomplete boundary detection and the undetection problem of small changed areas. At the same time, the registration errors in image pairs make remote sensing image change detection (RSCD) more challenging. To alleviate the aforementioned issues, this article proposes a transformer with feature interaction and fusion network (TFIFNet) for CD. To be specific, the proposed network utilizes the advantages of transformer in long-range dependence modeling first, which can learn feature representations with spatial-temporal information from a global perspective. Then, to alleviate the irrelevant changes caused by image registration errors, the bitemporal feature interaction module (BFIM) is proposed, which utilizes an attention mechanism to learn the bitemporal background distribution. Subsequently, an intertemporal joint-attention (JointAtt) is introduced to learn the consistency of bitemporal features for further refinement. Finally, to address the issue caused by spatial degradation during the process of network training, a triple feature fusion module (TFFM) is proposed. This module can learn spatial information from adjacent layer's features as additional spatial information. Extensive experimental studies show that the proposed network achieves the most advanced results on two CD benchmark datasets.

When oil spills occur at sea, effective detection and monitoring are required to establish a successful response plan, and remote sensing emerges as an appropriate technology to support this process. Furthermore, Earth observation is progressively relying on low-cost multispectral sensors developed for monitoring particular features across various scenarios. However, despite these advancements, the ongoing challenge lies in reducing computational costs, resource requirements, and energy consumption. This work aims to select the spectral index that best detects coastal spills among those documented. The long-term goal is to develop a low-cost multispectral sensor with suitable bands. For this purpose, this study uses data from different sensors that acquired data of the Deepwater Horizon accident in the Gulf of Mexico. The confusion matrices, accuracy, and F1-score generated from the kNN pixel classification based on the indices values are measures of its performance. For this study, the recently introduced normalized difference oil index (NDOI) proves to be the best option for identifying coastal spills since it minimizes the false positives related to suspended sand and is quick to calculate. In addition, it has demonstrated that it helps distinguish different spill thicknesses and estimates the oil volume. Therefore, future research will focus on developing and validating a low-cost multispectral system that uses the NDOI bands to detect spills.

In the field of remote sensing, it is not feasible to obtain high spatial resolution multispectral (HRMS) images from a single satellite sensor. The existing methods use pansharpening techniques to obtain HRMS images by fusing panchromatic (PAN) and multispectral (MS) images. However, due to the scale difference between PAN and MS images, most pansharpening methods often use explicit sampling methods to integrate features at different scales. These explicit-based sampling techniques represent pixels as discrete points through predefined functions, rendering it challenging to fit the distribution among diverse modal data, this results in the loss of image texture details during the fusion process. Implicit neural networks can enhance the generative capability of images by incorporating pixel coordinate information, which is crucial for the fusion of remote sensing images with different spatial resolutions. Inspired by implicit neural representation, we propose a progressive implicit neural feature fusion network (PINFNet) for remote sensing images. A progressive implicit neural feature fusion is proposed; it establishes a coordinate modal relationship between the spatial and spectral information through the guidance of the high spatial features in PAN images. This enables the proposed PINFNet to progressively learn and integrate spatial and spectral information at different scales. Our method, as opposed to discrete sampling techniques, is capable of establishing a continuous representation between diverse modal data, which in turn preserves more texture detail information. Extensive experiments have shown that this approach outperforms state-of-the-art methods while maintaining high efficiency.

Convolutional neural networks (CNNs), in particular, demonstrate the remarkable power of feature learning in remote sensing for land use and cover classification, as demonstrated by recent deep learning techniques driven by vast amounts of data. In this work, we proposed a new network-level fusion deep architecture based on 16-tiny Vision Transformer and SIBNet. In the initial phase, data augmentation has been performed to resolve the problem of data imbalances. In the next step, we proposed a self-attention bottleneck-based inception CNN network named SIBNet. In this network, two architectures are followed. The blocks are designed using inception architecture, and each inception module is created with bottleneck blocks. The 16-tiny vision transformer architecture has been implemented for RS images and fused using a network-level fusion with SIBNet for the first time. Hyperparameters of the proposed model have been initialized using Bayesian Optimization for better training on the RS images. After the fusion, the model was on RS image datasets and extracted deep features from the self-attention layer. The extracted features are classified using a neural network classifier with multiple hidden layers. The experimental process of the proposed architecture has been performed on two publically available datasets, such as EuroSAT and NWPU, and obtained an accuracy of 97.8 and 98.9%, respectively. A detailed ablation study has been performed to test the proposed models and shows that the fusion model achieved improved accuracy. In addition, a comparison is conducted with recent techniques and proposed methods, showing improved precision, recall, and accuracy.

The availability of high-resolution satellite images has accelerated the creation of new datasets designed to tackle broader remote sensing (RS) problems. Although popular tasks, such as scene classification, have received significant attention, the recent release of the Land-1.0 RS dataset marks the initiation of endeavors to estimate land-use and land-cover (LULC) fraction values per RGB satellite image. This challenging problem involves estimating LULC composition, i.e., the proportion of different LULC classes from satellite imagery, with major applications in environmental monitoring, agricultural/urban planning, and climate change studies. Currently, supervised deep learning models—the state-of-the-art in image classification—require large volumes of labeled training data to provide good generalization. To face the challenges posed by the scarcity of labeled RS data, self-supervised learning (SSL) models have recently emerged, learning directly from unlabeled data by leveraging the underlying structure. This is the first article to investigate the performance of SSL in LULC fraction estimation on RGB satellite patches using in-domain knowledge. We also performed a complementary analysis on LULC scene classification. Specifically, we pretrained Barlow Twins, MoCov2, SimCLR, and SimSiam SSL models with ResNet-18 using the Sentinel2GlobalLULC small RS dataset and then performed transfer learning to downstream tasks on Land-1.0. Our experiments demonstrate that SSL achieves competitive or slightly better results when trained on a smaller high-quality in-domain dataset of 194 877 samples compared to the supervised model trained on ImageNet-1k with 1 281 167 samples. This outcome highlights the effectiveness of SSL using in-distribution datasets, demonstrating efficient learning with fewer but more relevant data.

In current remote sensing segmentation tasks, the difficulty of segmenting spectrally similar objects is a significant issue. Solving this problem is crucial for improving segmentation accuracy. Traditional image-domain segmentation methods rely on color and texture features, but spectrally similar objects have negligible color differences, leading to suboptimal segmentation results. To address this, we propose a network framework called Correlated Mapping Attention Cooperative Network (CMACNet) by extending the problem from the image domain to the feature domain. Image-domain methods depend on color and texture features, whereas feature-domain methods process higher-level abstract features, avoiding issues caused by color similarity. Specifically, CMACNet first employs an autoencoder structure. The autoencoder compresses the input data and attempts to reconstruct the original data, ensuring that the latent space representations capture essential and representative features of the input data, thereby extracting highly generalized and versatile features. Next, we introduce the correlated mapping attention mechanism, which adaptively adjusts the attention to different features based on their correlations, effectively addressing the challenge of segmenting spectrally similar objects. Furthermore, to efficiently establish global relationships among features, we design a cross global interaction layer for global feature remapping. Comprehensive experiments on the Vaihingen and Potsdam datasets demonstrate that CMACNet outperforms existing state-of-the-art methods, achieving mean intersection over union scores of 84.77% and 87.69%, respectively.

Foundation models have reshaped the landscape of remote sensing (RS) by enhancing various image interpretation tasks. Pretraining is an active research topic, encompassing supervised and self-supervised learning methods to initialize model weights effectively. However, transferring the pretrained models to downstream tasks may encounter task discrepancy due to their formulation of pretraining as image classification or object discrimination tasks. In this study, we explore the multitask pretraining (MTP) paradigm for RS foundation models to address this issue. Using a shared encoder and task-specific decoder architecture, we conduct multitask supervised pretraining on the segment anything model annotated remote sensing segmentation dataset, encompassing semantic segmentation, instance segmentation, and rotated object detection. MTP supports both convolutional neural networks and vision transformer foundation models with over 300 million parameters. The pretrained models are finetuned on various RS downstream tasks, such as scene classification, horizontal, and rotated object detection, semantic segmentation, and change detection. Extensive experiments across 14 datasets demonstrate the superiority of our models over existing ones of similar size and their competitive performance compared to larger state-of-the-art models, thus validating the effectiveness of MTP.

The use of remote sensing images for land cover classification is an important and challenging pixel-level classification task. However, the different distribution of the same land cover categories across different datasets, the accuracy of the classification is significantly reduced when a classification model trained on one dataset is used directly on another dataset. To address the issue, numerous unsupervised domain adaptation (UDA) methods have been proposed. However, the existing UDA methods focus mainly on natural images and are not suited to remote sensing images with large variations in spectral information and texture features. Therefore, we develop a new full-level domain adaptation network (FLDA-NET) applicable for cross-domain land cover classification of remote sensing images. It aligns the source domain and target domain through a two-stage process encompassing image-level, feature-level, and output-level. In stage I, we align at image-level by converting the source domain image to the target domain image style. In stage II, at the feature-level we align the entropy of the two domain features. At the output-level we do not use simple global alignment, but category-level alignment. Furthermore, a self-training strategy based on superpixel segmentation and softmax probability is proposed to further enhance the model's performance on the target domain. Extensive experiments on our proposed FLDA-NET are performed on the Potsdam and Vaihingen datasets and compared with other advanced UDA methods. The outcome demonstrates that this approach greatly improves the ability of cross-domain land cover classification in remote sensing images.

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.

Building change detection (BCD) is a widely used method for monitoring human activities. Despite advancements in deep learning (DL) in computer vision, recent DL-based BCD methods still face challenges in extracting discriminative features due to irrelevant noisy changes and the lack of consideration for specific semantic information related to changes. To address this limitation, we propose the semantic-guided network (SGNet), a multiscale pure Transformer-based BCD method that delves into more discriminative class-specific feature representations for changed buildings. Specifically, we first breakdown the change detection process into multiple stages: changed semantics extraction, enhancement, fusion, and decoding. Then, we analyze the nature of building change events in remote sensing images (RSIs) and categorize them into three main groups. To detect positive changes and reduce noise, we developed the various changes extraction module. In addition, we introduce the semantic-guided changed-semantics augmentation module to enhance the semantic information of target changes while suppressing irrelevant regions or objects. We also propose the various changes fusion module to model semantic latency in bitemporal RSIs. Extensive experiments on two building change datasets, i.e., LEVIR-CD and WHU-CD demonstrate that our SGNet(MiT-b0) outperforms the state-of-the-art baselines and achieves F1 score of 90.99% and 92.47%, respectively, with improvements of 1.9% and 7.89%, respectively, highlighting the exceptional sample-efficient learning capability.

Remote sensing (RS) imagery captures the earth's ever-changing landscapes, reflecting evolving land cover patterns propelled by natural processes and human activities. However, existing RS scene classification methods mainly operate under a closed-set hypothesis, which stumbles when encountering novel emerging scenes. This article addresses the intricate task of RS scene classification without labels for novel scenes under incremental learning, termed class-incremental novel category discovery. We propose a contrastive learning-based novel category discovery pipeline tailored for RS image scene classification, enhancing the ability to learn unlabeled novel class data. Furthermore, within this pipeline, we introduce a positive pair filter to identify more positive sample pairs from novel classes, improving the feature representation capability on unlabeled data. Besides, our contrastive learning pipeline incorporates an old-feature replaying method to alleviate catastrophic forgetting in old classes. Extensive evaluations across three public RS datasets showcase the superiority of our method over state-of-the-art approaches.

In recent years, the application of deep learning to change detection (CD) has significantly progressed in remote sensing images. CD tasks have mostly used architectures, such as CNN and Transformer to locate image changes. However, these architectures have shortcomings in representing boundary details and are prone to false alarms and missed detections under complex lighting and weather conditions. For that, we propose a new network, Siamese meets diffusion network (SMDNet), a CD model that combines discriminative and generative architecture. By leveraging the power of the Siam-U2Net feature differential encoder (SU-FDE) and denoising diffusion implicit model (DDIM), it not only improves the accuracy of object edge detection but also enhances the data through iterative denoising and thinning reconstruction detail detection accuracy. Improves the model's robustness under environmental changes. First, we propose an SU-FDE module that uses shared weight features to capture differences between time series images, refine edge detection, and combine it with the attention mechanism to identify vital coarse features, thereby improving model sensitivity and accuracy. Finally, the progressive sampling of DDIM is used to integrate further these key features, and the adaptability of the model in different environments is enhanced with the help of the denoising ability of the diffusion model and the accurate capture of the probability distribution of image data. The performance evaluation of SMDNet on LEVIR-CD, DSIFN-CD, and CDD datasets yields validated F1 scores of 89.17%, 88.48%, and 88.23%, respectively. This substantiates the advanced capabilities of our model in accurately identifying variations and intricate details.

In remote sensing (RS), multiple modalities of data are usually available, e.g., RGB, multispectral, hyperspectral, light detection and ranging (LiDAR), and synthetic aperture radar (SAR). Multimodal machine learning systems, which fuse these rich multimodal data modalities, have shown better performance compared to unimodal systems. Most multimodal research assumes that all modalities are present, aligned, and noiseless during training and testing time. However, in real-world scenarios, it is common to observe that one or more modalities are missing, noisy, and nonaligned, in either training or testing or both. In addition, acquiring large-scale, noise-free annotations is expensive, as a result, lacking sufficient annotated datasets or having to deal with inconsistent labels are open challenges. These challenges can be addressed under a learning paradigm called multimodal colearning. This article focuses on multimodal colearning techniques for RS data. We first review what data modalities are available in the RS domain and the key benefits and challenges of combining multimodal data in the RS context. We then review the RS tasks that would benefit from multimodal processing including classification, segmentation, target detection, anomaly detection, and temporal change detection. We then dive deeper into technical details by reviewing more than 200 recent efforts in this area and provide a comprehensive taxonomy to systematically review state-of-the-art approaches in four key colearning challenges including missing modalities, noisy modalities, limited modality annotations, and weakly paired modalities. Based on these insights, we propose emerging research directions to inform potential future research in multimodal colearning for RS.

Globally, pests and plant diseases severely threaten forestry and agriculture. Plant protection could be substantially enhanced by using noncontact, extremely effective, and reasonably priced techniques for identifying and tracking pests and plant diseases across large geographic areas. Precision agriculture is the study of using other technologies, such as hyperspectral remote sensing, to increase cultivation instead of traditional agricultural methods with less negative environmental effects. In this article, we proposed a novel deep-learning architecture and optimization algorithm for crop leaf disease recognition. In the initial step, a multilevel contrast enhancement technique is proposed for a better visual of the disease on the leaves of cotton and wheat. After that, we proposed three novel residual block and self-attention mechanisms, named 3-residual block-deep convolutional neural network (RBNet) Self, 5-RBNet Self, and 9-RBNet Self. After that, the proposed models are trained on enhanced images and later extracted deep features from the self-attention layer. The 5-RBNET Self and 9-RBNET Self performed well in terms of accuracy and precision rate; therefore, we did not consider the 3-RBNET Self for the next process. The dragonfly optimization algorithm is proposed for the best feature selection and applied to the self-attention features of 5-RBNET Self and 9-RBNET Self models to improve the classification performance further and reduce the computational cost. The proposed method is evaluated on two publically available crop disease images, such as the cotton, wheat, and EuroSAT datasets. For both crops, the proposed method obtained a maximum accuracy of 98.60% and 93.90%, respectively, whereas for the EuroSAT, the proposed method obtained an accuracy of 83.10%. Compared to the results with recent techniques, the proposed method shows improved accuracy and precision rate.

In recent years, the application of deep learning in remote-sensing (RS) image change detection (CD) has been deepening, especially in the challenges faced in lightweight model design, that is, how to effectively balance model complexity and detection accuracy. Although some simplified models have achieved compression in existing research, there are shortcomings in maintaining detailed information and improving detection performance. On the other hand, large network architectures limit their actual deployment in resource-limited environments. This article innovatively proposes a lightweight CD network called Multilevel Feature Cross-Fusing Network (MFCF-Net) to address this issue. MFCF-Net uses a lightweight convolutional neural network for feature extraction and introduces the adjacent layer enhancement module in the feature extraction stage to significantly enhance the network's ability to extract high-dimensional features while only moderately increasing parameters. Furthermore, MFCF-Net integrates dense skip connections and cross-attention mechanisms in the decoder to efficiently propagate contextual information and accurately capture and fuse global spatial features, especially for detecting small changes. Experimental results show that on four public RS CD datasets, MFCF-Net achieves excellent detection performance and has a smaller model size (with parameters as low as 1.35M). Particularly on the WHU-CD dataset, compared with the current state-of-the-art method, MFCF-Net achieves significant improvements, with an F1-score increase in 1.4% and an intersection-over-union improvement of 2.45%.

AI-driven precision agriculture applications can benefit from the large data source that remote sensing (RS) provides, as it can gather agricultural monitoring data at various scales throughout the year. Numerous advantages for sustainable agricultural applications, including yield prediction, crop monitoring, and climate change adaptation, can be obtained from RS and artificial intelligence. In this work, we proposed a fully automated optimized self-attention fused convolutional neural network (CNN) architecture for land use and land cover classification using RS data. A new contrast enhancement equation has been proposed and utilized in the proposed architecture for the data augmentation. After that, a fused self-attention CNN architecture was proposed. The proposed architecture initially consists of two custom models named IBNR-65 and Densenet-64. Both models have been designed based on the inverted bottleneck residual mechanism and dense blocks. After that, both models were fused using a depth-wise concatenation and append a self-attention layer for deep features extraction. After that, we trained the model and performed classification using neural network (NN) classifiers. The results obtained from the NN classifiers are insufficient; therefore, we implemented a Bayesian optimization and fine-tuned the hyperparameters of NN. In addition, we proposed a quantum hippopotamus optimization algorithm for the best feature selection. The selected features are finally classified using fine-tuned NN classifiers and obtained improved accuracy of 98.20, 89.50, and 91.70%, and the highest precision rate is 98.23, recall is 98.20, and F1-score is 98.21, respectively, for SIRI-WHU, EuroSAT, and NWPU datasets. Moreover, a detailed ablation study was conducted, and the performance was compared with SOTA. The proposed architecture shows improved accuracy, sensitivity, precision, and computational time performance.

Geospatial objects pose significant challenges, including dense distribution, substantial interclass variations, and minimal intraclass variations. These complexities make achieving precise foreground object segmentation in high-resolution remote sensing images highly challenging. Current segmentation approaches often rely on the standard encoder–decoder architecture to extract object-related information, but overlook the inherent uncertainty issues that arise during the process. In this article, we aim to enhance segmentation by introducing an uncertainty-guided decoding mechanism and propose the uncertainty-guided segmentation network (UGSNet). Specifically, building upon the conventional encoder–decoder architecture, we initially employ the pyramid vision transformer to extract multilevel features containing extensive long-range information. We then introduce an uncertainty-guided decoding mechanism, addressing both epistemic and aleatoric uncertainties, to progressively refine segmentation with higher certainty at each level. With this uncertainty-guided decoding mechanism, our UGSNet achieves accurate geospatial object segmentation. To validate the effectiveness of UGSNet, we conduct extensive experiments on the large-scale ISAID dataset, and the results unequivocally demonstrate the superiority of our method over other state-of-the-art segmentation methods.

Continuous monitoring of water quality parameters (WQPs) is crucial due to the global degradation of water quality, primarily caused by climate change and population growth. Typically, machine learning (ML) models are employed to retrieve WQPs, but they require a large amount of training samples to accurately capture the data relationships. Even with sufficient training data, discrepancies still exist between values of predicted and in-situ WQPs. This study proposes a fuzzy similarity analysis (FSA) technique to enhance ML estimates of WQPs by using the prediction errors in effective training samples. The method was successfully applied to retrieve turbidity (Turb) and specific conductance (SC) in Lake Houston, USA, using Sentinel-2 remote sensing data. Three ML algorithms, namely mixture density networks, support vector regression, and partial least squares regression, were tested to evaluate the method's effectiveness. The results showed that FSA significantly improved the accuracy of all ML predictions. This improvement resulted in up to a 9.15% reduction in mean absolute percentage error and a 12% increase in R2 for Turb, while for SC, the improvements were 5.47% in MAPE and 7% in R2. The adaptability of the proposed method to other WQPs, various satellite data, and different ML models is promising for monitoring water quality in inland waters.

The advances in remote sensing technologies have boosted applications for Earth observation. These technologies provide multiple observations or views with different levels of information. They might contain static or temporary views with different levels of resolution, in addition to having different types and amounts of noise due to sensor calibration or deterioration. A great variety of deep learning models have been applied to fuse the information from these multiple views, known as deep multiview (MV) or multimodal fusion learning. However, the approaches in the literature vary greatly since different terminology is used to refer to similar concepts or different illustrations are given to similar techniques. This article gathers works on MV fusion for Earth observation by focusing on the common practices and approaches used in the literature. We summarize and structure insights from several different publications concentrating on unifying points and ideas. In this manuscript, we provide a harmonized terminology while at the same time mentioning the various alternative terms that are used in literature. The topics covered by the works reviewed focus on supervised learning with the use of neural network models. We hope this review, with a long list of recent references, can support future research and lead to a unified advance in the area.

Landslides are catastrophic geological events that can cause significant damage to properties and result in the loss of human lives. Deep-learning technology applied to optical remote sensing images can enable effective landslide-prone area detection. However, conventional landslide detection (LD) models often employ complex structural designs to ensure detection accuracy. The complexity often hampers the detection speed, rendering these models inadequate for the swift emergency monitoring of landslides. To address these problems, we propose a new lightweight deep-learning-based framework, BisDeNet, for efficient LD. To improve the efficiency of the proposed BisDeNet, we replaced the context path in the original BiSeNet with DenseNet due to its strong feature extraction ability, few required parameters, and low model complexity. Two sites with different and representative landslide developments were selected as the study areas to verify the performance of our proposed BisDeNet. Additionally, we introduced landslide causative factors to enhance the sampling dataset. To evaluate the effectiveness of our approach, we compared the performance of our BisDeNet with the performances of three other BiSeNet-based methods and an advanced transformer-based model data-efficient image transformer (DeiT). Our experimental results indicate that the F1-scores of BisDeNet in the two study areas are 0.9006 and 0.8850, which are 26.22% and 1.86% higher than the scores of BiSeNet, respectively, but slightly lower than that of the DeiT model. Furthermore, our proposed BisDeNet requires the fewest number of parameters and the least memory out of the five models.

Remote sensing (RS) scene classification plays an important role in the intelligent interpretation of RS data. Recently, convolutional neural network (CNN)-based and attention-based methods have become the mainstream of RS scene classification with impressive results. However, existing CNN-based methods do not utilize long-range information, and existing attention-based methods do not fully exploit multiscale information, although both aspects of information are essential for a comprehensive understanding of RS scene images. To overcome the above limitations, we propose a progressive feature fusion (PFF) framework based on graph convolutional network (GCN), namely PFFGCN for RS scene classification in this article, which has a strong ability to learn both multiscale and contextual (local/long-range) information in RS scene images. It mainly consists of two modules: a multilayer feature extraction module and a multiscale contextual information fusion (MCIF) module. The MFE module is utilized to extract multilevel features and global features, and the MCIF module is constructed to capture rich contextual information from multilevel features and fuse them in a progressive manner. In MCIF, GCN is adopted to explore intrinsic attributes (including the topological structure and the contextual information) hidden in each feature map. Through the PFF strategy, the graph features at each level are fused with the next-level features to reduce the semantic gap between nonadjacent features and enhance the multiscale representation of the model. Besides, grouped GCN based on channel grouping is further proposed to improve the efficiency of PFFGCN. The proposed method is extensively evaluated on various RS scene classification datasets, and the experimental results demonstrate that the proposed method outperforms current state-of-the-art methods.

The increased development of quantum computing hardware in recent years has led to increased interest in its application to various areas. Finding effective ways to apply this technology to real-world use-cases is a current area of research in the remote sensing community. This article proposes an adiabatic quantum kitchen sinks (AQKS) kernel approximation algorithm with parallel quantum annealing on the D-Wave Advantage quantum annealer. The proposed implementation is applied to support vector regression and Gaussian process regression algorithms. To evaluate its performance, a regression problem related to estimating chlorophyll concentration in water is considered. The proposed algorithm was tested on two real-world datasets and its results were compared with those obtained by a classical implementation of kernel-based algorithms and a random kitchen sinks implementation. On average, the parallel AQKS achieved comparable results to the benchmark methods, indicating its potential for future applications.

There are still various challenges in remote sensing semantic segmentation due to objects diversity and complexity. Transformer-based models have significant advantages in capturing global feature dependencies for segmentation. However, it unfortunately ignores local feature details. On the other hand, convolutional neural network (CNN), with a different interaction mechanism from transformer-based models, captures more small-scale local features instead of global features. In this article, a new semantic segmentation net framework named SSNet is proposed, which incorporates an encoder–decoder structure, optimizing the advantages of both local and global features. In addition, we build feature fuse module and feature inject module to largely fuse these two-style features. The former module captures the dependencies between different positions and channels to extract multiscale features, which promotes the segmentation precision on similar objects. The latter module condenses the global information in transformer and injects it into CNN to obtain a broad global field of view, in which the depthwise strip convolution improves the segmentation accuracy on tiny objects. A CNN-based decoder progressively recovers the feature map size, and a block called atrous spatial pyramid pooling is adopted in decoder to obtain a multiscale context. The skip connection is established between the decoder and the encoder, which retains important feature information of the shallow layer network and is conducive to achieving flow of multiscale features. To evaluate our model, we compare it with current state-of-the-art models on WHDLD and Potsdam datasets. The experimental results indicate that our proposed model achieves more precise semantic segmentation.

Change detection (CD) using deep learning techniques is a prominent topic in the field of remote sensing (RS). However, the existing methods require large amounts of labeled samples for supervised learning, which is time-consuming and labor-intensive. To address this challenge, semi-supervised learning methods that utilize a limited number of labeled samples along with a large pool of unlabeled samples have emerged as a compelling solution. We propose a novel semi-supervised CD (SSCD) network that combines self-training and consistency regularization, namely STCRNet. During the self-training phase, STCRNet selects unlabeled samples with reliable pseudolabels based on their prediction stability across different training epochs and the consistency between class activation maps and prediction results within the model. Then, we apply data augmentation to the reliable samples and enforce consistency regularization on the augmented samples using the pseudolabels to enhance the network's robustness. Moreover, feature consistency regularization is applied to the remaining unlabeled samples with image perturbations, thereby broadening the feature space and improving the model's generalization performance. The experimental results on two widely used datasets demonstrate that STCRNet achieves state-of-the-art performance, especially with a significantly small amount (5%–10%) of labeled samples. STCRNet presents a promising solution for SSCD.

Spectral indices are of fundamental importance in providing insights into the distinctive characteristics of oil spills, making them indispensable tools for effective action planning. The normalized difference oil index (NDOI) is a reliable metric and suitable for the detection of coastal oil spills, effectively leveraging the visible and near-infrared (VNIR) spectral bands offered by commercial sensors. The present study explores the calculation of NDOI with a primary focus on leveraging remotely sensed imagery with rich spectral data. This undertaking necessitates a robust infrastructure to handle and process large datasets, thereby demanding significant memory resources and ensuring scalability. To overcome these challenges, a novel cloud-based approach is proposed in this study to conduct the distributed implementation of the NDOI calculation. This approach offers an accessible and intuitive solution, empowering developers to harness the benefits of cloud platforms. The evaluation of the proposal is conducted by assessing its performance using the scene acquired by the airborne visible infrared imaging spectrometer (AVIRIS) sensor during the 2010 oil rig disaster in the Gulf of Mexico. The catastrophic nature of the event and the subsequent challenges underscore the importance of remote sensing (RS) in facilitating decision-making processes. In this context, cloud-based approaches have emerged as a prominent technological advancement in the RS field. The experimental results demonstrate noteworthy performance by the proposed cloud-based approach and pave the path for future research for fast decision-making applications in scalable environments.

In recent years, the development of quantum annealers has enabled experimental demonstrations and has increased research interest in applications of quantum annealing, such as in quantum machine learning and in particular for the popular quantum support vector machine (SVM). Several versions of the quantum SVM have been proposed, and quantum annealing has been shown to be effective in them. Extensions to multiclass problems have also been made, which consist of an ensemble of multiple binary classifiers. This article proposes a novel quantum SVM formulation for direct multiclass classification based on quantum annealing, called quantum multiclass SVM (QMSVM). The multiclass classification problem is formulated as a single quadratic unconstrained binary optimization problem solved with quantum annealing. The main objective of this article is to evaluate the feasibility, accuracy, and time performance of this approach. Experiments have been performed on the D-Wave Advantage quantum annealer for a classification problem on remote sensing data. Results indicate that, despite the memory demands of the quantum annealer, QMSVM can achieve an accuracy that is comparable to standard SVM methods, such as the one-versus-one (OVO), depending on the dataset (compared to OVO: 0.8663 versus 0.8598 on Toulouse, 0.8123 versus 0.8521 on Potsdam). More importantly, it scales much more efficiently with the number of training examples, resulting in nearly constant time (compared to OVO: 85.72 versus 248.02 s on Toulouse, 58.89 versus 580.17 s on Potsdam). This article shows an approach for bringing together classical and quantum computation, solving practical problems in remote sensing with current hardware.

Deep learning (DL) has emerged as a powerful technique for a wide range of computer vision applications. Consequently, DL is also being adopted to process geospatial and remote sensing (RS) images. As these methods are sporadic over different studies, many review papers have also been published to gather the approaches and summarize the existing models in this field. However, a state-of-the-art review paper is still scarce in this field that will present a bibliometric analysis as well as a critical analysis of the recent works. Therefore, this article aims to spur the researchers with a bibliometric analysis to identify the current research trend. As a research sample, in total, 281 related papers were collected from the Web of Science source, and bibliometric analysis was accomplished using VOSviewer software. Among the collection of associated works from the database, 28 papers were selected according to the defined criteria for detailed analysis. Besides this, a few research questions were generated to extract necessary information from the literature for extracting the pros and cons of the selected works. DL techniques were applied in these works and achieved results. Furthermore, the papers were also categorized based on the addressed RS application domain.