Search

This paper is devoted to cloud and snow semantic segmentation using multispectral satellite imagery, received from a multizone scanning instrument (MSU-GS) installed on the Russian satellite Electro-L No. 2. For segmentation, some additional geographic information is used such as latitude, longitude, and altitude. The main difficulty of evaluating snow and cloud masks from MSU-GS data is absence of shortwave infrared (SWIR) spectral channels in the 1.3 - 1.6 μ m range, which are necessary for accurate snow and cloud distinction. This fact makes it impossible to apply any of existing algorithms for cloud and snow destinction used for other multispectral satellite imagery. The results of the presented work include a self-collected dataset, consisting of cloud masks from the meteorological satellites GOES-16 and Meteosat-10 L2 products, snow masks from Terra/MODIS products, considered to be the ground truth for multispectral imagery from Electro-L No. 2 with geographical information for each sample, as well as a trained Multi-Scale Attention Network (MANet), able to perform snow and cloud segmentation for multispectral data from Electro-L No. 2. The purpose of this study is to create a stable algorithm for MSU-GS imagery to conduct an operational snow and cloud coverage monitoring of the full Earth disk, that can not be evaluated by using multispectral data from other Russian satellites. The novelty of the work is the combining geographical and multispectral information with weighted sampling approach for hard samples, as well as using other satellite products for creating ground truth masks for needed satellite imagery. The developed algorithm was tested on various scenes during all seasons with F 1 and IoU metrics. We reach segmentation quality equal to F 1 = 0.7454 , F 1 = 0.8773 and IoU = 0.7398 , IoU = 0.7976 for snow and clouds respectively. The proposed neural network can be used at any time of year during daytime for processing Electro-L No. 2 multispectral data in real time. [ABSTRACT FROM AUTHOR]

Images of military conquest on Sennacherib's palace walls often featured his siege camps. By comparing the visual and textual references to these camps with the surroundings of the cities he besieged (on site and via aerial and satellite imagery, archaeological and historical data, and early maps and surveys), likely locations are proposed for Sennacherib's royal camps. These sites are found to have all had the same name on early maps, Mudawwara , which, in Arabic in the Middle Ages, denoted the enormous tent that housed the sultan on military expeditions. (At times, this name was prefaced with Khirbet al , indicating the ancient stone ruins thereof.) Examining all occurrences of this toponym within Judah and Philistia reveals a distribution consistent with what is known of Sennacherib's invasion route and of the cities besieged. It also resolves some long-standing questions and contributes to identifying the locations of the cities of Libnah and Nob. [ABSTRACT FROM AUTHOR]

The burning of crop residues in fields is a significant global biomass burning activity which is a key element of the terrestrial carbon cycle, and an important source of atmospheric trace gasses and aerosols. Accurate estimation of cropland burned area is both crucial and challenging, especially for the small and fragmented burned scars in China. Here we developed an automated burned area mapping algorithm that was implemented using Sentinel-2 Multi Spectral Instrument (MSI) data and its effectiveness was tested taking Songnen Plain, Northeast China as a case using satellite image of 2020. We employed a logistic regression method for integrating multiple spectral data into a synthetic indicator, and compared the results with manually interpreted burned area reference maps and the Moderate-Resolution Imaging Spectroradiometer (MODIS) MCD64A1 burned area product. The overall accuracy of the single variable logistic regression was 77.38% to 86.90% and 73.47% to 97.14% for the 52TCQ and 51TYM cases, respectively. In comparison, the accuracy of the burned area map was improved to 87.14% and 98.33% for the 52TCQ and 51TYM cases, respectively by multiple variable logistic regression of Sentind-2 images. The balance of omission error and commission error was also improved. The integration of multiple spectral data combined with a logistic regression method proves to be effective for burned area detection, offering a highly automated process with an automatic threshold determination mechanism. This method exhibits excellent extensibility and flexibility taking the image tile as the operating unit. It is suitable for burned area detection at a regional scale and can also be implemented with other satellite data. [ABSTRACT FROM AUTHOR]

Erosion of banks and channel migrations are usually common phenomenon and recurring geo-hazardous problem in the Brahmaputra-Jamuna river system of Bangladesh. The present study intensively analysed multi-temporal Landsat satellite imageries (Landsat MSS, Landsat TM, Landsat ETM+, Landsat OLI TIRS), historical documents (Hunter maps), and literature information employing Remote Sensing and Geographic Information System techniques, and estimation of braiding and sinuosity indices especially emphasizing channel bar development, braiding, and bank-line migration of the river. The computed braiding indices of the river were 1.5, 10.3, 13.4, 11.0, 10.6 and 14.6 for the year of 1853–1857, 1977, 1989, 2000, 2014 and 2018, respectively (overall deciphering increasing trend). Similar to the braiding indices, the sinuosity indices (2.58, 7.02, 9.92, 8.31, 7.42 and 11.25 for the same selected years) of the river have also been changed over time. During 1853–1857 to 2018, 766.7 and 1624.2 km2 of lands extensively eroded on the east and west bank, respectively at a rate of 4.8 and 10.1 km2 yr−1. However, from 1977 to 2018, the erosion rates were 14.4 and 12.5 km2 yr−1, respectively. High discharges, sediment transport associated with random bars formation related braiding expansion, and weak bank materials are presumably the governing factors for causing such simultaneous severe bank erosion and remarkable bank-line migration phenomenon. Although, from 1853–1857 to 1977 the erosion of the river followed the river flow direction. It is expected that the outcomes of this research can contribute further research on morphodynamic characteristics of the braided river for better understanding the river characteristics, the river hydromorphology, water and sediment transport, its bank erosion, and formulating protective measurement plan for their sustainable current flow path maintenance. [ABSTRACT FROM AUTHOR]

A hazard is a natural occurrence that might harm humans, animals or the environment. It may cause loss of life, illness or other health consequences, property damage, social and economic crisis or environmental degradation. Various regions around the world are vulnerable to one or more types of disasters. Flooding is one of the worst environmental catastrophes that impacts both civilisation and the environment globally. Various datasets and methods, such as meteorological data, satellite images and GIS, were used to create the hazard assessment map. For a particular region, flood hazards can be developed by integrating an assessment map for several parameter categories. The aim of the study was to evaluate the hazard of flooding and map the areas that will be flooded in Gujarat. This study develops and tests flood-hazard maps to visualise the spatial variation of hazards in Gujarat, India. The parameters for flood-hazard assessment are mainly considered as elevation, slope, aspect, curvature, lithology, soil, land use/cover, drainage density and distance from the river, and rainfall to create a map in the context of a GIS. The acquired data was evaluated using ArcGIS and fuzzy-logic techniques to build a flood hazard map. Five categories have been assigned to the computed flood hazard map: very low, low, moderate, high, and very high. Engineers, planners and local governments may find this study useful in the future when it comes to land use planning and the control of hazards. Flood hazard potential mapping is necessary to manage and mitigate flooding. [ABSTRACT FROM AUTHOR]

The challenging task of early yield prediction is an essential problem for present-day agriculture. It is commonly solved with a crop model along with relevant observation data: field scouting, in-situ sensors, satellite imagery data and information from previous growing seasons. Crop growth simulation models benefit greatly from application of these data; however, only a limited number of established data assimilation procedures receive notable application. Most studies focus on model parameter calibration, machine learning, ensemble Kalman filters (EnKF) or particle filters. These methods are powerful yet computationally expensive, which limits their extensive application. In this study, we bring into consideration a modern KF variant – the unscented Kalman filter (UKF). We implement the UKF data assimilation for leaf area index (LAI) within WOFOST PCSE model. To demonstrate its efficiency, we conduct simulations with EnKF and UKF assimilation of Sentinel-2 LAI data and compare the results to actual historical yield data of five crops on 2740 fields. Also, a field-level numerical experiment is set up to demonstrate the influence of LAI assimilation on the predicted yield. The results indicate the proposed approach performs consistently and significantly improves the accuracy of predicted yields. [ABSTRACT FROM AUTHOR]

Optimizing production–living–ecological space (PLES) can benefit territorial space planning and sustainable development in China. Thus, spatiotemporal evolution characteristics and influence factor analyses are vital. Laiwu, China, was selected as the study area due to its complex terrain and development history. A multitemporal land-use and land-cover classification extracted from Landsat remote-sensing images for 2001–2018 and the self-organizing map method were combined to identify the area's multitemporal PLES. The PLES evolution trajectories were extracted based on the multitemporal PLES. The main factors influencing the PLES spatiotemporal evolution differences were revealed using the random-forest-based factor importance evaluation method. The results showed that changes in the PLES trajectories occupied ∼ 18% of the study area. The ecological space recovery type was mainly observed in previously stable ecological space areas. Changes in the production space expansion (PSE) and living space expansion were mainly agglomerated in the fringe areas of previously stable production–ecological and living space lands. Distance from early built-up areas was the main factor influencing PLES expansion. Ecological space was mainly distributed far away from built-up areas, and living and production spaces were mainly distributed near the built-up areas. Additionally, the slope of the terrain affected the spatial distribution of PLES expansion to a certain extent, and the gross domestic product clearly affected the distribution of PSE. [ABSTRACT FROM AUTHOR]

In this paper, we address the image denoising problem in presence of speckle degradation typically arising in ultra-sound images. Variational methods and Convolutional Neural Networks (CNNs) are considered well-established methods for specific noise types, such as Gaussian and Poisson noise. Nonetheless, the advances achieved by these two classes of strategies are limited when tackling the de-speckle problem. In fact, variational methods for speckle removal typically amounts to solve a non-convex functional with the related issues from the convergence viewpoint; on the other hand, the lack of large datasets of noise-free ultra-sound images has not allowed the extension of the state-of-the-art CNN denoiser methods to the case of speckle degradation. Here, we aim at combining the classical variational methods with the predictive properties of CNNs by considering a weighted total variation regularized model; the local weights are obtained as the output of a statistically inspired neural network that is trained on a small and composite dataset of natural and synthetic images. The resulting non-convex variational model, which is minimized by means of the Alternating Direction Method of Multipliers (ADMM) is proven to converge to a stationary point. Numerical tests show the effectiveness of our approach for the denoising of natural and satellite images. • An hybrid strategy for the despeckling problem combining convolutional neural networks and variational methods is proposed. • The proposed neural architecture is statistically-inspired and not requires the training on a large data-set of images. • A proof of convergence to a stationary point for the alternating direction method is given. [ABSTRACT FROM AUTHOR]

Tuberculosis (TB) transmission and prevalence are dynamic over time, and heterogeneous within populations. Public health programmes therefore require up-to-date, accurate epidemiological data to appropriately allocate resources, target interventions, and track progress towards End TB goals. Current methods of TB surveillance often rely on case notifications, which are biased by access to healthcare, and TB disease prevalence surveys, which are highly resource-intensive, requiring many tens of thousands of people to be tested to identify high-risk groups or capture trends. Surveys of "latent TB infection", or immunoreactivity to Mycobacterium tuberculosis (Mtb), using tests such as interferon-gamma release assays (IGRAs) could provide a way to identify TB transmission hotspots, supplementing information from disease notifications, and with greater spatial and temporal resolution than is possible to achieve in disease prevalence surveys. This cross-sectional survey will investigate the prevalence of Mtb immunoreactivity amongst young children, adolescents and adults in Blantyre, Malawi, a high HIV-prevalence city in southern Africa. Through this study we will estimate the annual risk of TB infection (ARTI) in Blantyre and explore individual- and area-level risk factors for infection, as well as investigating geospatial heterogeneity of Mtb infection (and its determinants), and comparing these to the distribution of TB disease case-notifications. We will also evaluate novel diagnostics for Mtb infection (QIAreach QFT) and sampling methodologies (convenience sampling in healthcare settings and community sampling based on satellite imagery), which may increase the feasibility of measuring Mtb infection at large scale. The overall aim is to provide high-resolution epidemiological data and provide new insights into methodologies which may be used by TB programmes globally. [ABSTRACT FROM AUTHOR]

Internal waves (IWs) are an important ocean process in transmitting energy between multiscale ocean dynamics, making them a crucial oceanic phenomenon. The South China Sea (SCS) is renowned for its frequent large-amplitude IW activities, emphasizing the importance of collecting and analyzing extensive observational data. In this study, we present a comprehensive IW dataset covering the northern SCS covering 112.40–121.32° E and 18.32–23.19° N, spanning from 2000 to 2022 with a 250 m spatial resolution. The IW dataset comprises 3085 high-resolution MODIS true-color IW images paired with precise IW position information extracted from 15830 MODIS images using advanced deep learning techniques. IWs in the northern SCS are divided into four regions based on extracted IW spatial distributions, facilitating detailed analyses of IW characteristics, including spatial and temporal distributions across both the entire northern SCS and its sub-regions. Notably, we uncover typical 'double-peak' distributions corresponding to the lunar day, underscoring IWs' close relationship with tides. Furthermore, we identify two IW-free silence regions attributed to underwater topography influences, indicating varied IW characteristics across regions and suggesting underlying mechanisms warrant further investigation. The constructed dataset holds significant potential for applications in studying IW-environment interactions, developing monitoring and prediction models, validating and enhancing numerical simulations, and serving as an educational resource to foster awareness and interest in IW research. [ABSTRACT FROM AUTHOR]

In recent decades several methods have been developed to extract coastlines from remotely sensed images. In fact, this is one of the principal fields of remote sensing research that continues to receive attention, as testified by the thousands of scientific articles present in the main databases, such as SCOPUS, WoS, etc. The main issue is to automatize the whole process or at least a great part of it, so as to minimize the human error connected to photointerpretation and identification of training sites to support the classification of objects (basically soil and water) present in the observed scene. This article proposes a new fully automatic methodological approach for coastline extraction: it is based on the unsupervised classification of the most decorrelated fictitious band derived from Principal Component Analysis (PCA) applied to the satellite images. The experiments are carried out on datasets characterized by images with different geometric resolution, i.e., Landsat 9 Operational Land Imager (OLI) multispectral images (pixel size: 30 m), a Sentinel-2 dataset including blue, green, red and Near Infrared (NIR) bands (pixel size: 10 m) and a Sentinel-2 dataset including red edge, narrow NIR and Short-Wave Infrared (SWIR) bands (pixel size: 20 m). The results are very encouraging, given that the comparison between each extracted coastline and the corresponding real one generates, in all cases, residues that present a Root Mean Squared Error (RMSE) lower than the pixel size of the considered dataset. In addition, the PCA results are better than those achieved with Normalized Difference Water Index (NDWI) and Modified NDWI (MNDWI) applications. [ABSTRACT FROM AUTHOR]

With the number of new satellites increasing dramatically, comprehensive space surveillance is becoming increasingly important. Therefore, high-resolution inverse synthetic aperture radar (ISAR) imaging of satellites can provide an in-situ assessment of the satellites. This paper demonstrates that pseudo-noise signals can also be used for satellite imaging, in addition to classical linear frequency-modulated chirp signals. Pseudo-noise transmission signals offer the advantage of very low cross-correlation values. This, for instance, enables the possibility of a system with multiple channels transmitting instantaneously. Furthermore, it can significantly reduce signal interference with other systems operating in the same frequency spectrum, which is of particular interest for high-bandwidth, high-power systems such as satellite imaging radars. A new routine has been introduced to generate a wideband pseudo-noise signal with a peak-to-average power ratio (PAPR) similar to that of a chirp signal. This is essential for applications where the transmit signal power budget is sharply limited by the high-power amplifier. The paper presents both theoretical descriptions and analysis of the generated pseudo-noise signal as well as the results of an imaging measurement of a real space target using the introduced pseudo-noise signals. [ABSTRACT FROM AUTHOR]

Winter wheat is a significant global food crop, and it is crucial to monitor its distribution for better agricultural management, land planning, and environmental sustainability. However, the distribution style of winter wheat planting fields is not consistent due to different terrain conditions. In mountainous areas, winter wheat planting units are smaller in size and fragmented in distribution compared to plain areas. Unfortunately, most crop-mapping research based on deep learning ignores the impact of topographic relief on crop distribution and struggles to handle hilly areas effectively. In this paper, we propose a cross-modal segmentation network for winter wheat mapping in complex terrain using remote-sensing multi-temporal images and DEM data. First, we propose a diverse receptive fusion (DRF) module, which applies a deformable receptive field to optical images during the feature fusion process, allowing it to match winter wheat plots of varying scales and a fixed receptive field to the DEM to extract evaluation features at a consistent scale. Second, we developed a distributed weight attention (DWA) module, which can enhance the feature intensity of winter wheat, thereby reducing the omission rate of planting areas, especially for the small-sized regions in hilly terrain. Furthermore, to demonstrate the performance of our model, we conducted extensive experiments and ablation studies on a large-scale dataset in Lanling county, Shandong province, China. Our results show that our proposed CM-Net is effective in mapping winter wheat in complex terrain. [ABSTRACT FROM AUTHOR]

Change detection is crucial for evaluating land use, land cover changes, and sustainable development, constituting a significant component of Earth observation tasks. The difficulty in extracting features from high-resolution images, coupled with the complexity of image content, poses challenges for traditional change detection algorithms in terms of accuracy and applicability. The recent emergence of deep learning methods has led to substantial progress in the field of change detection. However, existing frameworks often involve the simplistic integration of bi-temporal features in specific areas, lacking the fusion of temporal information and semantic details in the images. In this paper, we propose an attention-guided multi-scale fusion network (AMFNet), which effectively integrates bi-temporal image features and diverse semantics at both the encoding and decoding stages. AMFNet utilizes a unique attention-guided mechanism to dynamically adjust feature fusion, enhancing adaptability and accuracy in change detection tasks. Our method intelligently incorporates temporal information into the deep learning model, considering the temporal dependency inherent in these tasks. We decode based on an interactive feature map, which improves the model's understanding of evolving patterns over time. Additionally, we introduce multi-level supervised training to facilitate the learning of fused features across multiple scales. In comparison with different algorithms, our proposed method achieves F1 values of 0.9079, 0.8225, and 0.8809 in the LEVIR-CD, GZ-CD, and SYSU-CD datasets, respectively. Our model outperforms the SOTA model, SAGNet, by 0.69% in terms of F1 and 1.15% in terms of IoU on the LEVIR-CD dataset, by 2.8% in terms of F1 and 1.79% in terms of IoU on the GZ-CD dataset, and by 0.54% in terms of F1 and 0.38% in terms of IoU on the SYSU-CD dataset. The method proposed in this study can be applied to various complex scenarios, establishing a change detection method with strong model generalization capabilities. [ABSTRACT FROM AUTHOR]

Coastal sediment grain size is an important factor in determining coastal morphodynamics. In this study, we explore a novel approach for retrieving the median sediment grain size (D50) of gravel-dominated beaches using Synthetic Aperture Radar (SAR) spaceborne imagery. We assessed this by using thirty-six Sentinel-1 (C-band SAR) satellite images acquired in May and June 2022 and 2023, and three NovaSAR (S-band SAR) satellite images acquired in May and June 2022, for three different training sites and one test site across England (the UK). The results from the Sentinel-1 C-band data show strong positive correlations (R2 ≥ 0.75 ) between the D50 and the backscatter coefficients for 15/18 of the resultant models. The models were subsequently used to derive predictions of D50 for the test site, with the models which exhibited the strongest correlations resulting in Mean Absolute Errors (MAEs) in the range 2.26–5.47 mm. No correlation (R2 = 0.04) was found between the backscatter coefficients from the S-band NovaSAR data and D50. These results highlight the potential to derive near-real time estimates of coastal sediment grain size for gravel beaches to better inform coastal erosion and monitoring programs. [ABSTRACT FROM AUTHOR]

Over the past three decades, Sri Lanka has observed a substantial rise in landslide occurrences linked to intensified rainfall. However, the lack of comprehensive landslide inventories has hampered the development of effective risk analysis and simulation systems, requiring Sri Lanka to rely heavily on foreign-developed models, despite the difficulty of fully examining the similarities between the characteristics of landslides in Sri Lanka and the areas where the model has been developed. Satellite images have become readily available in recent years and have provided information about the Earth's surface conditions over the past few decades. Thus, this study verifies the utility of satellite images as a cost-effective remote-sensing method to clarify the commonalities and differences in the characteristics of landslides in two regions Ikawa, Japan, and Sabaragamuwa, Sri Lanka, which exhibit different geological formations despite similar annual rainfall. Using Google Earth satellite images from 2013 to 2023, we evaluated land-slide density, types, and geometry. The findings reveal that Ikawa exhibits a higher landslide density and experiences multiple-type landslides. In contrast, both areas have similar initiation areas; however, Sabaragamuwa predominantly experiences single landslides that are widespread and mobile. The findings also reveal that various characteristics of landslides are mainly influenced by varied topography. Here, we confirmed that even in areas where comprehensive information on landslides is conventionally lacking, we can understand the characteristics of landslides by comparing landslide geometry between sites using satellite imagery. [ABSTRACT FROM AUTHOR]

This article focuses on developing models that estimate suspended sediment concentrations (SSCs) for the Lower Brazos River, Texas, U.S. Historical samples of SSCs from gauge stations and satellite imagery from Landsat Missions and Sentinel Mission 2 were utilized to develop models to estimate SSCs for the Lower Brazos River. The models used in this study to accomplish this goal include support vector machines (SVMs), artificial neural networks (ANNs), extreme learning machines (ELMs), and exponential relationships. In addition, flow measurements were used to develop rating curves to estimate SSCs for the Brazos River as a baseline comparison of the models that used satellite imagery to estimate SSCs. The models were evaluated using a Taylor Diagram analysis on the test data set developed for the Brazos River data. Fifteen of the models developed using satellite imagery as inputs performed with a coefficient of determination R2 above 0.69, with the three best performing models having an R2 of 0.83 to 0.85. One of the best performing models was then utilized to estimate the SSCs before, during, and after Hurricane Harvey to evaluate the impact of this storm on the sediment dynamics along the Lower Brazos River and the model's ability to estimate SSCs. [ABSTRACT FROM AUTHOR]

The modification of fire regimes and their impact on vegetation recovery, soil properties, and fuel structure are current key research areas that attempt to identify the thresholds of vegetation's susceptibility to wildfires. This study aimed to evaluate the vulnerability of Mediterranean pine forests (Pinus halepensis Mill. and Pinus pinaster Aiton) to wildfires, analyzing two major forest fires that occurred in Yeste (Spain) in 1994 and 2017, affecting over 14,000 and 3200 hectares, respectively. Four recovery regions were identified based on fire severity—calculated using the delta Normalized Burn Ratio (dNBR) index—and recurrence: areas with high severity in 2017 but not in 1994 (UB94-HS17), areas with high severity in 1994 but not in 2017 (HS94-UB17), areas with high severity in both fires (HS94-HS17), and areas unaffected by either fire (UB94-UB17). The analysis focused on examining the recovery patterns of three spectral indices—the Normalized Difference Vegetation Index (NDVI), Normalized Moisture Index (NDMI), and Normalized Burn Ratio (NBR)—using the Google Earth Engine platform from 1990 to 2023. Additionally, the Relative Recovery Indicator (RRI), the Ratio of Eighty Percent (R80P), and the Year-on-Year average (YrYr) metrics were computed to assess the spectral recovery rates by region. These three spectral indices showed similar dynamic responses to fire. However, the Mann–Kendall and unit root statistical tests revealed that the NDVI and NDMI exhibited distinct trends, particularly in areas with recurrence (HS94-HS17). The NDVI outperformed the NBR and NDMI in distinguishing variations among regions. These results suggest accelerated vegetation spectral regrowth in the short term. The Vegetation Recovery Capacity After Fire (VRAF) index showed values from low to moderate, while the Vulnerability to Fire (V2FIRE) index exhibited values from medium to high across all recovery regions. These findings enhance our understanding of how vegetation recovers from fire and how vulnerable it is to fire. [ABSTRACT FROM AUTHOR]

In 2020, wildfires scarred over 4,000,000 hectares in the western United States, devastating urban populations and ecosystems alike. The significant impact that wildfires have on plants, animals, and human environments makes wildfire adaptation, management, and mitigation strategies a critical task. This study uses satellite imagery from Landsat to calculate burn severity and map the fire progression for the Dolan Fire of central Coastal California which occurred in August 2020. Several environmental factors, such as temperature, humidity, fuel type, topography, surface conditions, and wind velocity, are known to affect wildfire spread and burn severity. The aim of this study is the investigation of the relationship between these environmental factors, estimates of burn severity, and fire spread patterns. Burn severity is calculated and classified using the Difference in Normalized Burn Ratio (dNBR) before being displayed as a time series of maps. The Dolan Fire had a moderate severity burn with an average dNBR of 0.292. The ignition site location, when paired with the patterns of fire spread, is consistent with wind speed and direction data, suggesting fire movement to the southeast of the fire ignition site. Patterns of increased burn severity are compared with both topography (slope and aspect) and fuel type. Locations that were found to be more susceptible to high burn severity featured Long Needle Timber Litter and Mature Timber fuels, intermediate slope angles between 15 and 35°, and north- and east-facing slopes. This study has implications for the future predictive modeling of wildfires that may serve to develop wildfire mitigation strategies, manage climate change impacts, and protect human lives. [ABSTRACT FROM AUTHOR]

Remote sensing image change detection (CD) is an important means in remote sensing data analysis tasks, which can help us understand the surface changes in high-resolution (HR) remote sensing images. Traditional pixel-based and object-based methods are only suitable for low- and medium-resolution images, and are still challenging for complex texture features and detailed image detail processing in HR images. At present, the method based on deep learning has problems such as inconsistent fusion and difficult model training in the combination of the difference feature information of the deep and shallow layers and the attention mechanism, which leads to errors in the distinction between the changing region and the invariant region, edge detection and small target detection. In order to solve the above problems of inconsistent fusions of feature information aggregation and attention mechanisms, and indistinguishable change areas, we propose a multi-scale feature fusion Siamese network based on attention mechanism (ABMFNet). To tackle the issues of inconsistent fusion and alignment difficulties when integrating multi-scale fusion and attention mechanisms, we introduce the attention-based multi-scale feature fusion module (AMFFM). This module not only addresses insufficient feature fusion and connection between different-scale feature layers, but also enables the model to automatically learn and prioritize important features or regions in the image. Additionally, we design the cross-scale fusion module (CFM) and the difference feature enhancement pyramid structure (DEFPN) to assist the AMFFM module in integrating differential information effectively. These modules bridge the spatial disparity between low-level and high-level features, ensuring efficient connection and fusion of spatial difference information. Furthermore, we enhance the representation and inference speed of the feature pyramid by incorporating a feature enhancement module (FEM) into DEFPN. Finally, the BICD dataset proposed by the laboratory and public datasets LEVIR-CD and BCDD are compared and tested. We use F1 score and MIoU values as evaluation metrics. For AMBMFNet, the F1 scores on the three datasets are 77.69%, 81.57%, and 77.91%, respectively, while the MIoU values are 84.65%, 85.84%, and 84.54%, respectively. The experimental results show that ABMFNet has better effectiveness and robustness. [ABSTRACT FROM AUTHOR]

Effectively and efficiently retrieving images from remote-sensing databases is a critical challenge in the realm of remote-sensing big data. Utilizing hand-drawn sketches as retrieval inputs offers intuitive and user-friendly advantages, yet the potential of multi-level feature integration from sketches remains underexplored, leading to suboptimal retrieval performance. To address this gap, our study introduces a novel zero-shot, sketch-based retrieval method for remote-sensing images, leveraging multi-level feature extraction, self-attention-guided tokenization and filtering, and cross-modality attention update. This approach employs only vision information and does not require semantic knowledge concerning the sketch and image. It starts by employing multi-level self-attention guided feature extraction to tokenize the query sketches, as well as self-attention feature extraction to tokenize the candidate images. It then employs cross-attention mechanisms to establish token correspondence between these two modalities, facilitating the computation of sketch-to-image similarity. Our method significantly outperforms existing sketch-based remote-sensing image retrieval techniques, as evidenced by tests on multiple datasets. Notably, it also exhibits robust zero-shot learning capabilities in handling unseen categories and strong domain adaptation capabilities in handling unseen novel remote-sensing data. The method's scalability can be further enhanced by the pre-calculation of retrieval tokens for all candidate images in a database. This research underscores the significant potential of multi-level, attention-guided tokenization in cross-modal remote-sensing image retrieval. For broader accessibility and research facilitation, we have made the code and dataset used in this study publicly available online. [ABSTRACT FROM AUTHOR]

Background: Echinococcosis is a natural focal, highly prevalent disease in China. Factors influencing the spread of echinococcosis are not only related to personal exposure but also closely related to the environment itself. The purpose of this study was to explore the influence of environmental factors on the prevalence of human echinococcosis and to provide a reference for prevention and control of echinococcosis in the future. Methods: Data were collected from 370 endemic counties in China in 2018. By downloading Modis, DEM and other remote-sensing images in 2018. Data on environmental factors, i.e., elevation, land surface temperature (LST) and normalized difference vegetation index (NDVI) were collected. Rank correlation analysis was conducted between each environmental factor and the prevalence of echinococcosis at the county level. Negative binomial regression was used to analyze the impact of environmental factors on the prevalence of human echinococcosis at the county level. Results: According to rank correlation analysis, the prevalence of human echinococcosis in each county was positively correlated with elevation, negatively correlated with LST, and negatively correlated with NDVI in May, June and July. Negative binomial regression showed that the prevalence of human echinococcosis was negatively correlated with annual LST and summer NDVI, and positively correlated with average elevation and dog infection rate. The prevalence of human cystic echinococcosis was inversely correlated with the annual average LST, and positively correlated with both the average elevation and the prevalence rate of domestic animals. The prevalence of human alveolar echinococcosis was positively correlated with both NDVI in autumn and average elevation, and negatively correlated with NDVI in winter. Conclusion: The prevalence of echinococcosis in the population is affected by environmental factors. Environmental risk assessment and prediction can be conducted in order to rationally allocate health resources and improve both prevention and control efficiency of echinococcosis. Author summary: Echinococcosis is a natural focal, highly prevalent disease in China. Factors influencing the spread of echinococcosis are not only related to personal exposure but also closely related to the environment itself. This study covered all endemic counties in China and studied the main environmental factors affecting the epidemic of echinococcosis. to explore the influence of environmental factors on the prevalence of human echinococcosis, and to provide a reference for prevention and control of echinococcosis in the future. Data were collected from 370 endemic counties in China in 2018. By downloading Modis, DEM and other remote-sensing images in 2018. The prevalence of human echinococcosis in each county was positively correlated with elevation, negatively correlated with LST, and negatively correlated with NDVI in May, June and July. Prevalence of human echinococcosis was negatively correlated with annual LST and summer NDVI, and positively correlated with average elevation and dog infection rate. Prevalence of human cystic echinococcosis was inversely correlated with the annual average LST, and positively correlated with both the average elevation and the prevalence rate of domestic animals. The prevalence of human alveolar echinococcosis was positively correlated with both NDVI in autumn and average elevation, and negatively correlated with NDVI in winter. [ABSTRACT FROM AUTHOR]

Urban heat islands will occur if city neighborhoods contain insufficient green spaces to create a comfortable environment, and residents' health will be adversely affected. Current satellite imagery can only effectively identify large-scale green spaces and cannot capture street trees or potted plants within three-dimensional building spaces. In this study, we used a deep convolutional neural network semantic segmentation model on Google Street View to extract environmental features at the neighborhood level in Taipei City, Taiwan, including the green vegetation index (GVI), building view factor, and sky view factor. Monthly temperature data from 2018 to 2021 with a 0.01° spatial resolution were used. We applied a linear mixed-effects model and geographically weighted regression to explore the association between pedestrian-level green spaces and ambient temperature, controlling for seasons, land use information, and traffic volume. Their results indicated that a higher GVI was significantly associated with lower ambient temperatures and temperature differences. Locations with higher traffic flows or specific land uses, such as religious or governmental, are associated with higher ambient temperatures. In conclusion, the GVI from street-view imagery at the community level can improve the understanding of urban green spaces and evaluate their effects in association with other social and environmental indicators. [ABSTRACT FROM AUTHOR]

This paper addresses the challenge of training deep learning models for fire smoke scene detection from multi-sensor, multi-spectral satellite imagery, where spectral bands vary and training data is scarce, especially for new sensors. We introduce a novel cross-sensor transfer learning approach enhanced by spectral pattern extraction, notably aided by a deep learning (DL) module called Input Amplification (IA). Our contribution includes the creation of two datasets, Landsat_smk2770 and Sentinel2_smk, with varying spectral bands. We employ a model named IA_VIB_SD which incorporates IA and is designed specifically for fire smoke scene detection. We investigated the transferability of the Landsat_smk2770-trained IA_VIB_SD model to the Sentinel2_smk dataset using various transfer learning techniques, and compared the performance of the transferred model with the benchmark IA_VIB_SD model exclusively trained on pure Sentinel2_smk data. Our proposed transfer learning approach resulted in a transferred model with an average accuracy 5% higher than the benchmark model. Notably, Our proposed transfer learning approach outperformed existing transfer learning methods by more than 1% in terms of the accuracy, even when trained on a mere 10% of the Sentinel2_smk dataset. This research advances fire smoke scene detection from multi-sensor, multi-spectral satellite imagery. [ABSTRACT FROM AUTHOR]

This study leveraged Convolutional Neural Network (CNN) models to estimate canopy height in Southeast Australian forests before and after the 2019–2020 bushfire event, using inputs from Sentinel-1, Sentinel-2, spectral indices, and terrain features and GEDI canopy height (rh99) as target variables. Our research consisted of three primary objectives: (1) an evaluation of GEDI rh99 canopy height in relation to an nDSM derived from airborne LiDAR, (2) the development of two CNN models for pre- and post-fire scenarios, and (3) utilizing the trained CNN models to generate pre- and post-fire canopy height maps and canopy height change maps across the continuous landscape. GEDI rh99 accuracy analysis revealed ${R^2}$ R 2 = 0.85, RMSE = 7.25 m and nRMSE = 0.23 for pre-fire GEDI and ${R^2}$ R 2 = 0.78, RMSE = 10.1 m and nRMSE = 0.3 for post-fire GEDI. The pre-fire CNN model achieved ${R^2}$ R 2 = 0.75, RMSE = 7.29 m and nRMSE = 0.22, and post-fire CNN model achieved ${R^2}$ R 2 = 0.62, RMSE = 11.67 m, and nRMSE = 0.34 when validated against nDSM. Bias analysis was conducted, revealing that GEDI rh99 underestimated nDSM across all canopy height ranges, and slope has no significant impact on GEDI accuracy. Notably, post-fire GEDI rh99 exhibited significant underestimation in high to extreme fire severity. The CNN models' prediction displayed overestimation in short forests < 20 m and increasing underestimation in taller forests > 20 m and underestimation in high and extreme fire severity. Subsequent investigation indicated that canopy layer thinning in high fire severity conditions resulted in weak GEDI waveform signals and consequent bias. Additionally, the GEDI rh99 bias was propagated to the CNN models, together with insensitivity of spectral band values to canopy height in dense and burnt forests potentially contributed to models' bias. Finally, we demonstrated CNN models' ability to monitor forest recovery by generating canopy height maps spanning East Gippsland from 2019 to 2023. [ABSTRACT FROM AUTHOR]

Nowadays, establishing security in data transmission is essential, and it is achieved by cryptography. Encryption of still or video images in specific applications such as Internet of Things, medical and satellite imaging, in applications requiring high-speed encryption, or even in applications where a personal computer is unavailable or cannot be used needs special hardware. In this paper, an image encryption algorithm based on chaos theory named Parallel Chaotic Checksum-based Image Encryption or PCCIE algorithm is proposed that has been able to provide a fast, efficient and secure algorithm with a hardware perspective on the design and parallel system structure. Using high-level synthesis, PCCIE is implemented on a Field Programmable Gate Array (FPGA). The proposed algorithm using small and independent local image buffers solved FPGA internal memory limitation for encryption of large images. Ultimately, a Hexa-core crypto-processor with single-precision floating-point and fixed-point precision has been designed, capable of encrypting 256 × 256 and Full HD images in 2.13 and 59.52 milliseconds, respectively, at 469 and 16 frames per second. [ABSTRACT FROM AUTHOR]

Extracting building footprints from extensive very-high spatial resolution (VHSR) remote sensing data is crucial for diverse applications, including surveying, urban studies, population estimation, identification of informal settlements, and disaster management. Although convolutional neural networks (CNNs) are commonly utilized for this purpose, their effectiveness is constrained by limitations in capturing long-range relationships and contextual details due to the localized nature of convolution operations. This study introduces the masked-attention mask transformer (Mask2Former), based on the Swin Transformer, for building footprint extraction from large-scale satellite imagery. To enhance the capture of large-scale semantic information and extract multiscale features, a hierarchical vision transformer with shifted windows (Swin Transformer) serves as the backbone network. An extensive analysis compares the efficiency and generalizability of Mask2Former with four CNN models (PSPNet, DeepLabV3+, UpperNet-ConvNext, and SegNeXt) and two transformer-based models (UpperNet-Swin and SegFormer) featuring different complexities. Results reveal superior performance of transformer-based models over CNN-based counterparts, showcasing exceptional generalization across diverse testing areas with varying building structures, heights, and sizes. Specifically, Mask2Former with the Swin transformer backbone achieves a mean intersection over union between 88% and 93%, along with a mean F-score (mF-score) ranging from 91% to 96.35% across various urban landscapes. [ABSTRACT FROM AUTHOR]

• Proposed a Hybrid Model for Paddy Crop prediction based on phenological parameters. • CNN-LSTM attained RMSE value of 0.219 t/ha compared to other existing methods. • Random Forest method achieved highest accuracy of 96.6% in paddy classification. Rice is one of the predominant food sources to fulfill the dietary requirements of well-being in India. Therefore, accurate and timely paddy crop yield prediction is crucial to ensure the food security of the country. In this direction, the present study proposed a hybrid deep-learning method based on Conv-1D and LSTM layers using the classification-derived phenological with meteorological parameters for paddy crop yield prediction. The paddy crop classification has been conducted using high-resolution (10 m) multispectral imagery based on GPS coordinates collected during the paddy field visits to extract the phenological parameters for input to the prediction model. In this context, the efficiency of Random Forest, Naïve Bayes, SVM, and Gradient Tree boost classifiers was assessed. Furthermore, we have also analyzed the accuracy of Landsat-8, Sentinel-1 GRD, and Sentinel-2 satellite imagery in paddy crop classification based on area estimation. The Statistical Abstract of Haryana was utilized to validate the paddy crop area estimation and yield prediction. The classification outcomes showed that the Random Forest method attained the highest accuracy of 96.6 % compared to other GEE-based classifiers. The proposed Hybrid Deep learning approach achieved an RMSE value of 0.219 t/ha compared to CNN, LSTM, CNN-Bi-LSTM, and Regression techniques for crop yield prediction. The study conclusion highlighted that the sentinel-2 satellite imagery performed well and found that the proposed hybrid approach provided an alternative for paddy crop yield prediction. [ABSTRACT FROM AUTHOR]

• Synergistic use of drone, satellite, and machine learning technologies improves LAI estimation. • Robust validation and advanced performance metrics confirm model accuracy and precision. • Utilizing Vegetation Indices to enhance the precision of LAI quantification. In this study, we conducted a comprehensive assessment of Leaf Area Index (LAI) estimation using three distinct sources of satellite data: Sentinel-2 imagery, drone imagery (UAVs), and Mohammed VI satellite data. The main objective was to identify the most reliable and precise dataset for predicting LAI, with a focus on evaluating the performance of Random Forest models. For Sentinel-2 imagery, our Random Forest model achieves a robust R-squared (R2) value of 0.89, signifying a strong alignment between predicted and measured LAI values. The associated root-mean-square error (RMSE) is 0.4, indicating high predictive accuracy. In the context of UAVs, our Random Forest model excels, exhibiting an impressive R2 value of 0.93, highlighting a substantial correlation between predicted and measured LAI. The RMSE for drone imagery stands at 0.37, showcasing exceptional predictive accuracy. Finally, the Random Forest model trained on Mohammed VI satellite data yields an R2 value of 0.92, underlining its strong fit with measured LAI values. The RMSE for Mohammed VI imagery is 0.39, further underscoring the model's exceptional predictive accuracy. This comparative analysis underscores the importance of selecting the most suitable satellite data source for LAI estimation in Argania spinosa. UAV imagery emerges as the most accurate choice, closely followed by Mohammed VI Satellite and Sentinel-2 imagery. These findings offer valuable insights for effective monitoring of Argania spinosa and advancing sustainable land management practices in rural ecosystems. [ABSTRACT FROM AUTHOR]

It is important to assess the rapid land-use/land-cover change (LULCC) and its impact on ecosystem service value (ESV), affecting the socio-economic and climatic stabilization of wetlands. In this study, a multi-resolution image segmentation and k-nearest neighbours algorithm were used for the thematic classification of satellite images of 2003 and 2018 in the Deepor Beel wetland, a lake of international significance. A notable increase in built-up areas was observed from 9.07 to 32.19 sq. km during this period. Proximity analysis in the 500 m buffer from the Deepor Beel boundary revealed an increasing built-up areas in close proximity. The ESV evaluation estimated a net decrease in the monetary value of 4.85 × 104 USD of the wetland for the respective years. The study recommends strict demarcation of zones of influence on the ground and regular monitoring of LULCC to protect important wetlands and preserve their ecosystem services. [ABSTRACT FROM AUTHOR]

Radar imaging SATellite (RISAT-1A), also known as Earth observation satellite-04 (EOS-04), is a follow-on mission of India’s first indigenously developed spaceborne C-band synthetic aperture radar (SAR) on-board RISAT-1 satellite. This article provides a description of the post-launch calibration and data quality evaluation of EOS-04 launched on 14 February 2022. Calibration devices (corner reflectors) of different shapes and sizes were deployed at Ahmedabad and Amrapur calibration sites in Gujarat, India from 2 to 24 April 2022, and their response in the EOS-04 data was used to assess the radiometric and polarimetric calibration. The results of the analysis showed satisfactory radiometric and polarimetric data quality. Geolocation accuracy was assessed using the ground-surveyed position of the corner reflectors and was found to be in accordance with the specified values of less than 50 m. [ABSTRACT FROM AUTHOR]

The C-band Synthetic Aperture Radar (SAR) payload of Earth Observation Satellite (EOS-04), is a follow-on mission of Radar Imaging Satellite (RISAT-1). Though the overall configuration of the C-Band SAR payload has been retained from its predecessor, EOS-04 boasts of incorporating features, which target to keep up with the technological strides, and to improve the data quality. All the major modes of RISAT-1 are retained in EOS04 whereas fine resolution stripmap-2 mode, which was quad-polarization mode earlier, is upgraded to full-polarization mode. The payload also has better repeat cycle with improved systematic coverage mode. This article covers system level advancements, and radio frequency and digital electronics hardware, implemented in EOS-04. The satellite was launched on 14 February 2022 and since then all the major imaging modes are being operated successfully. [ABSTRACT FROM AUTHOR]

The increasing rate of adoption of innovative technological achievements along with the penetration of the Next Generation Internet (NGI) technologies and Artificial Intelligence (AI) in the water sector are leading to a shift to a Water-Smart Society. New challenges have emerged in terms of data interoperability, sharing, and trustworthiness due to the rapidly increasing volume of heterogeneous data generated by multiple technologies. Hence, there is a need for efficient harmonization and smart modeling of the data to foster advanced AI analytical processes, which will lead to efficient water data management. The main objective of this work is to propose two Smart Data Models focusing on the modeling of the satellite imagery data and the flood risk assessment processes. The utilization of those models reinforces the fusion and homogenization of diverse information and data, facilitating the adoption of AI technologies for flood mapping and monitoring. Furthermore, a holistic framework is developed and evaluated via qualitative and quantitative performance indicators revealing the efficacy of the proposed models concerning the usage of the models in real cases. The framework is based on the well-known and compatible technologies on NGSI-LD standards which are customized and applicable easily to support the water data management processes effectively. [ABSTRACT FROM AUTHOR]

This paper is the first to examine the operation of the HawkEye satellite in the presence of dust aerosol. The study region is the Black Sea. Dust transport dates were identified using visual inspection of satellite imagery, back-kinematic HYSPLIT trajectory analysis, CALIPSO aerosol stratification and typing maps, and the global forecasting model SILAM. In a comparative analysis of in-situ and satellite measurements of the remote sensing reflectance, an error in the atmospheric correction of HawkEye measurements was found both for a clean atmosphere and in the presence of an absorbing aerosol. It is shown that, on average, the dependence of the atmospheric correction error on wavelength has the form of a power function of the form from λ−3 to λ−9. The largest errors are in the short-wavelength region of the spectrum (412–443 nm) for the dust and dusty marine aerosol domination dates. A comparative analysis of satellite and in situ measurements of the optical characteristics of the atmosphere, namely the AOD and the Ångström parameter, was carried out. It is shown that the aerosol model used by HawkEye underestimates the Angström parameter and, most likely, large errors and outliers in satellite measurements are associated with this. [ABSTRACT FROM AUTHOR]

Current methods for detecting atmospheric plumes and inferring point-source rates from high-resolution satellite imagery are labor-intensive and not scalable with regard to the growing satellite dataset available for methane point sources. Here, we present a two-step algorithm called U-Plume for automated detection and quantification of point sources from satellite imagery. The first step delivers plume detection and delineation (masking) with a U-Net machine learning architecture for image segmentation. The second step quantifies the point-source rate from the masked plume using wind speed information and either a convolutional neural network (CNN) or a physics-based integrated mass enhancement (IME) method. The algorithm can process 62 images (each measuring 128 pixels × 128 pixels) per second on a single 2.6 GHz Intel Core i7-9750H CPU. We train the algorithm using large-eddy simulations of methane plumes superimposed on noisy and variable methane background scenes from the GHGSat-C1 satellite instrument. We introduce the concept of point-source observability, Ops=Q/(UWΔB) , as a single dimensionless number to predict plume detectability and source rate quantification error from an instrument as a function of source rate Q , wind speed U , instrument pixel size W , and instrument-dependent background noise ΔB. We show that Ops can powerfully diagnose the ability of an imaging instrument to observe point sources of a certain magnitude under given conditions. U-Plume successfully detects and masks plumes from sources as small as 100 kgh-1 in GHGSat-C1 images over surfaces with low background noise and successfully handles larger point sources over surfaces with substantial background noise. We find that the IME method for source quantification is unbiased over the full range of source rates, while the CNN method is biased towards the mean of its training range. The total error in source rate quantification is dominated by wind speed at low wind speeds and by the masking algorithm at high wind speeds. A wind speed of 2–4 ms-1 is optimal for detection and quantification of point sources from satellite data. [ABSTRACT FROM AUTHOR]

Remote sensing datasets usually have a wide range of spatial and spectral resolutions. They provide unique advantages in surveillance systems, and many government organizations use remote sensing multispectral imagery to monitor security-critical infrastructures or targets. Artificial Intelligence (AI) has advanced rapidly in recent years and has been widely applied to remote image analysis, achieving state-of-the-art (SOTA) performance. However, AI models are vulnerable and can be easily deceived or poisoned. A malicious user may poison an AI model by creating a stealthy backdoor. A backdoored AI model performs well on clean data but behaves abnormally when a planted trigger appears in the data. Backdoor attacks have been extensively studied in machine learning-based computer vision applications with natural images. However, much less research has been conducted on remote sensing imagery, which typically consists of many more bands in addition to the red, green, and blue bands found in natural images. In this paper, we first extensively studied a popular backdoor attack, BadNets, applied to a remote sensing dataset, where the trigger was planted in all of the bands in the data. Our results showed that SOTA defense mechanisms, including Neural Cleanse, TABOR, Activation Clustering, Fine-Pruning, GangSweep, Strip, DeepInspect, and Pixel Backdoor, had difficulties detecting and mitigating the backdoor attack. We then proposed an explainable AI-guided backdoor attack specifically for remote sensing imagery by placing triggers in the image sub-bands. Our proposed attack model even poses stronger challenges to these SOTA defense mechanisms, and no method was able to defend it. These results send an alarming message about the catastrophic effects the backdoor attacks may have on satellite imagery. [ABSTRACT FROM AUTHOR]

When natural image detection methods are applied to remote sensing images, their detection performance is often unsatisfactory due to the random distribution of objects, complex backgrounds, and significant scale changes. In order to better detect objects with complex backgrounds and significant scale changes in remote sensing images, this study presents SGMFNet, a remote sensing image object detection network based on spatial global attention (SGA) and multi-scale feature fusion (MFF). The SGA inserted into the backbone network can better model context information, suppress irrelevant background, and build powerful feature information, making it easier for subsequent MFF to extract scale-invariant information from adjacent feature layers. This study evaluates the performance of SGMFNet on remote sensing datasets DIOR, NWPU VHR-10, and RSD-GOD. Quantitative and qualitative results on three datasets demonstrate the superiority of SGMFNet in remote sensing object detection and its outperformance compared with other state-of-the-art methods. Therefore, SGMFNet can assist in high-precision urban planning, military monitoring, and other tasks. [ABSTRACT FROM AUTHOR]

Terraces, farmlands built along hillside contours, are common anthropogenically designed landscapes. Terraces control soil and water loss and improve land productivity; therefore, obtaining their spatial distribution is necessary for soil and water conservation and agricultural production. Spatial information of large-scale terraces can be obtained using satellite images and through deep learning. However, when extracting terraces, accurately segmenting the boundaries of terraces and identifying small terraces in diverse scenarios continues to be challenging. To solve this problem, we combined two deep learning modules, ANB-LN and DFB, to produce a new deep learning framework (NLDF-Net) for terrace extraction using remote sensing images. The model first extracted the features of the terraces through the coding area to obtain abstract semantic features, and then gradually recovered the original size through the decoding area using feature fusion. In addition, we constructed a terrace dataset (the HRT-set) for Guangdong Province and conducted a series of comparative experiments on this dataset using the new framework. The experimental results show that our framework had the best extraction effect compared to those of other deep learning methods. This framework provides a method and reference for extracting ground objects using remote sensing images. [ABSTRACT FROM AUTHOR]

This paper describes the creation of a fast, deterministic, 3D fractal cloud renderer for the AFIT Sensor and Scene Emulation Tool (ASSET). The renderer generates 3D clouds by ray marching through a volume and sampling the level-set of a fractal function. The fractal function is distorted by a displacement map, which is generated using horizontal wind data from a Global Forecast System (GFS) weather file. The vertical windspeed and relative humidity are used to mask the creation of clouds to match realistic large-scale weather patterns over the Earth. Small-scale detail is provided by the fractal functions which are tuned to match natural cloud shapes. This model is intended to run quickly, and it can run in about 700 ms per cloud type. This model generates clouds that appear to match large-scale satellite imagery, and it reproduces natural small-scale shapes. This should enable future versions of ASSET to generate scenarios where the same scene is consistently viewed from both GEO and LEO satellites from multiple perspectives. [ABSTRACT FROM AUTHOR]

Chlorophyll-a concentration (Chl-a) is commonly used as a proxy for phytoplankton abundance in surface waters of large lakes. Mapping spatial and temporal Chl-a distributions derived from multispectral satellite data is therefore increasingly popular for monitoring trends in trophic state of these important ecosystems. We evaluated products of eleven atmospheric correction processors (LEDAPS, LaSRC, Sen2Cor, ACOLITE, ATCOR, C2RCC, DOS 1, FLAASH, iCOR, Polymer, and QUAC) and 27 reflectance indexes (including band-ratio, three-band, and four-band algorithms) recommended for Chl-a concentration retrieval. These were applied to the western basin of Lake Ontario by pairing 236 satellite scenes from Landsat 5, 7, 8, and Sentinel-2 acquired between 2000 and 2022 to 600 near-synchronous and co-located in situ-measured Chl-a concentrations. The in situ data were categorized based on location, seasonality, and Carlson's Trophic State Index (TSI). Linear regression Chl-a models were calibrated for each processing scheme plus data category. The models were compared using a range of performance metrics. Categorization of data based on trophic state yielded improved outcomes. Furthermore, Sentinel-2 and Landsat 8 data provided the best results, while Landsat 5 and 7 underperformed. A total of 28 Chl-a models were developed across the different data categorization schemes, with RMSEs ranging from 1.1 to 14.1 μg/L. ACOLITE-corrected images paired with the blue-to-green band ratio emerged as the generally best performing scheme. However, model performance was dependent on the data filtration practices and varied between satellites. [ABSTRACT FROM AUTHOR]

The traditional method for extracting the heights of urban buildings involves utilizing dense matching algorithms on stereo images to generate a digital surface model (DSM). However, for urban buildings, the disparity discontinuity issue that troubles the dense matching algorithm makes the elevations of high-rise buildings and the surrounding areas inaccurate. The occlusion caused by trees in greenbelts makes it difficult to accurately extract the ground elevation around the building. To tackle these problems, a method for building height extraction from Gaofen-7 (GF-7) stereo images enhanced by contour matching is presented. Firstly, a contour matching algorithm was proposed to extract accurate building roof elevation from GF-7 images. Secondly, a ground filtering algorithm was employed on the DSM to generate a digital elevation model (DEM), and ground elevation can be extracted from this DEM. The difference between the rooftop elevation and the ground elevation represents the building height. The presented method was verified in Yingde, Guangzhou, Guangdong Province, and Xi'an, Shaanxi Province. The experimental results demonstrate that our proposed method outperforms existing methods in building height extraction concerning accuracy. [ABSTRACT FROM AUTHOR]

Haze or cloud always shrouds satellite images, obscuring valuable geographic information for military surveillance, natural calamity surveillance and mineral resource exploration. Satellite image dehazing (SID) provides the possibility for better applications of satellite images. Most of the existing dehazing methods are tailored for natural images and are not very effective for satellite images with non-homogeneous haze since the semantic structure information and inconsistent attenuation are not fully considered. To tackle this problem, this study proposes a hierarchical semantic-guided contextual structure-aware network (SCSNet) for spectral satellite image dehazing. Specifically, a hybrid CNN–Transformer architecture integrated with a hierarchical semantic guidance (HSG) module is presented to learn semantic structure information by synergetically complementing local representation from non-local features. Furthermore, a cross-layer fusion (CLF) module is specially designed to replace the traditional skip connection during the feature decoding stage so as to reinforce the attention to the spatial regions and feature channels with more serious attenuation. The results on the SateHaze1k, RS-Haze, and RSID datasets demonstrated that the proposed SCSNet can achieve effective dehazing and outperforms existing state-of-the-art methods. [ABSTRACT FROM AUTHOR]

Pixel-level classification of very-high-resolution images is a crucial yet challenging task in remote sensing. While transformers have demonstrated effectiveness in capturing dependencies, their tendency to partition images into patches may restrict their applicability to highly detailed remote sensing images. To extract latent contextual semantic information from high-resolution remote sensing images, we proposed a gaze–saccade transformer (GSV-Trans) with visual perceptual attention. GSV-Trans incorporates a visual perceptual attention (VPA) mechanism that dynamically allocates computational resources based on the semantic complexity of the image. The VPA mechanism includes both gaze attention and eye movement attention, enabling the model to focus on the most critical parts of the image and acquire competitive semantic information. Additionally, to capture contextual semantic information across different levels in the image, we designed an inter-layer short-term visual memory module with bidirectional affinity propagation to guide attention allocation. Furthermore, we introduced a dual-branch pseudo-label module (DBPL) that imposes pixel-level and category-level semantic constraints on both gaze and saccade branches. DBPL encourages the model to extract domain-invariant features and align semantic information across different domains in the feature space. Extensive experiments on multiple pixel-level classification benchmarks confirm the effectiveness and superiority of our method over the state of the art. [ABSTRACT FROM AUTHOR]

Crop mapping using satellite imagery is crucial for agriculture applications. However, a fundamental challenge that hinders crop mapping progress is the scarcity of samples. The latest foundation model, Segment Anything Model (SAM), provides an opportunity to address this issue, yet few studies have been conducted in this area. This study investigated the parcel segmentation performance of SAM on commonly used medium-resolution satellite imagery (i.e., Sentinel-2 and Landsat-8) and proposed a novel automated sample generation framework based on SAM. The framework comprises three steps. First, an image optimization automatically selects high-quality images as the inputs for SAM. Then, potential samples are generated based on the masks produced by SAM. Finally, the potential samples are subsequently subjected to a sample cleaning procedure to acquire the most reliable samples. Experiments were conducted in Henan Province, China, and southern Ontario, Canada, using six proven effective classifiers. The effectiveness of our method is demonstrated through the combination of field-survey-collected samples and differently proportioned generated samples. Our results indicated that directly using SAM for parcel segmentation remains challenging, unless the parcels are large, regular in shape, and have distinct color differences from surroundings. Additionally, the proposed approach significantly improved the performance of classifiers and alleviated the sample scarcity problem. Compared to classifiers trained only by field-survey-collected samples, our method resulted in an average improvement of 16% and 78.5% in Henan and Ontario, respectively. The random forest achieved relatively good performance, with weighted-average F1 of 0.97 and 0.996 obtained using Sentinel-2 imagery in the two study areas, respectively. Our study contributes insights into solutions for sample scarcity in crop mapping and highlights the promising application of foundation models like SAM. [ABSTRACT FROM AUTHOR]

In response to the challenges posed by small objects in remote sensing images, such as low resolution, complex backgrounds, and severe occlusions, this paper proposes a lightweight improved model based on YOLOv8n. During the detection of small objects, the feature fusion part of the YOLOv8n algorithm retrieves relatively fewer features of small objects from the backbone network compared to large objects, resulting in low detection accuracy for small objects. To address this issue, firstly, this paper adds a dedicated small object detection layer in the feature fusion network to better integrate the features of small objects into the feature fusion part of the model. Secondly, the SSFF module is introduced to facilitate multi-scale feature fusion, enabling the model to capture more gradient paths and further improve accuracy while reducing model parameters. Finally, the HPANet structure is proposed, replacing the Path Aggregation Network with HPANet. Compared to the original YOLOv8n algorithm, the recognition accuracy of mAP@0.5 on the VisDrone data set and the AI-TOD data set has increased by 14.3% and 17.9%, respectively, while the recognition accuracy of mAP@0.5:0.95 has increased by 17.1% and 19.8%, respectively. The proposed method reduces the parameter count by 33% and the model size by 31.7% compared to the original model. Experimental results demonstrate that the proposed method can quickly and accurately identify small objects in complex backgrounds. [ABSTRACT FROM AUTHOR]

Currently, the visual detection of a target's shock flow field through background schlieren technology is a novel detection system. However, there are very few studies on the long-distance background schlieren imaging mechanism and its application in system design in the field of target detection. This paper proposes a design optimization method for space-based BOS detection system metrics. By establishing sensitivity evaluation models and image signal-to-noise ratio evaluation models for BOS detection systems, the influence of the different flight parameters and key parameters of BOS systems (detection spectral bands and spatial resolution) on target detection efficiency is explored. Furthermore, an optimization method based on the image signal-to-noise ratio of the BOS system and the overall metrics for specific scenarios are provided. The simulation results demonstrate that under satellite background images and speckle background images, the system metrics can detect and identify the schlieren of high-speed targets, with better applicability to disordered and complex real background images. This research contributes to advancing the development of high-speed target detection technology based on BOS. [ABSTRACT FROM AUTHOR]

Satellite image time‐series are time series produced from remote sensing images; they generally correspond to features or indicators extracted from those images. With the increasing availability of remote sensing images and new methodologies to process such data, image time‐series methods have been used extensively for assessing temporal pattern detection, monitoring, classification, object detection, and feature estimation. Since the study of time series is broad, this article focuses on analyzing articles related to forecasting the value of one or more attributes of the image time‐series. The image time series forecasting (ITSF) problem appears in different disciplines; most focus on improving the quality of life by harnessing natural resources for sustainable development and minimizing the lethality of dangerous natural phenomena. Scientists tackle these problems using different tools or methods depending on the application. This review analyzes the field's leading, most recent contributions, grouping them by application area and solution methods. Our findings indicate that artificial neural networks, regression trees, support vector regression, and cellular automata are the most common methods for ITSF. Application areas address this problem as renewable energy, agriculture, and land‐use change. This study retrieved and analyzed relevant information about the recent activity of image time series forecasting, generating a reproducible list of the most pertinent articles in the field published from 2009 to 2021. To the author's best knowledge, this is the first review presenting and analyzing a reproducible list of the most relevant state‐of‐the‐art articles focusing on the applications, techniques, and research trends for ITSF. This article is categorized under:Algorithmic Development > Spatial and Temporal Data MiningTechnologies > Machine LearningTechnologies > Prediction [ABSTRACT FROM AUTHOR]