Search

Mangroves are important ecosystems for coastal biodiversity, resilience and carbon dynamics that are being threatened globally by human pressures and the impacts of climate change. Yet, at several geographic range limits in tropical–temperate transition zones, mangrove ecosystems are expanding poleward in response to changing macroclimatic drivers. Mangroves near range limits often grow to smaller statures and form dynamic, patchy distributions with other coastal habitats, which are difficult to map using moderate‐resolution (30‐m) satellite imagery. As a result, many of these mangrove areas are missing in global distribution maps. To better map small, scrub mangroves, we tested Landsat (30‐m) and Sentinel (10‐m) against very high resolution (VHR) Planet (3‐m) and WorldView (1.8‐m) imagery and assessed the accuracy of machine learning classification approaches in discerning current (2022) mangrove and saltmarsh from other coastal habitats in a rapidly changing ecotone along the east coast of Florida, USA. Our aim is to (1) quantify the mappable differences in landscape composition and complexity, class dominance and spatial properties of mangrove and saltmarsh patches due to image resolution; and (2) to resolve mapping uncertainties in the region. We found that the ability of Landsat to map mangrove distributions at the leading range edge was hampered by the size and extent of mangrove stands being too small for detection (50% accuracy). WorldView was the most successful in discerning mangroves from other wetland habitats (84% accuracy), closely followed by Planet (82%) and Sentinel (81%). With WorldView, we detected 800 ha of mangroves within the Florida range‐limit study area, 35% more mangroves than were detected with Planet, 114% more than Sentinel and 537% more than Landsat. Higher‐resolution imagery helped reveal additional variability in landscape metrics quantifying diversity, spatial configuration and connectedness among mangrove and saltmarsh habitats at the landscape, class and patch scales. Overall, VHR satellite imagery improved our ability to map mangroves at range limits and can help supplement moderate‐resolution global distributions and outdated regional maps. [ABSTRACT FROM AUTHOR]

Abstract Mangroves are important ecosystems for coastal biodiversity, resilience and carbon dynamics that are being threatened globally by human pressures and the impacts of climate change. Yet, at several geographic range limits in tropical–temperate transition zones, mangrove ecosystems are expanding poleward in response to changing macroclimatic drivers. Mangroves near range limits often grow to smaller statures and form dynamic, patchy distributions with other coastal habitats, which are difficult to map using moderate‐resolution (30‐m) satellite imagery. As a result, many of these mangrove areas are missing in global distribution maps. To better map small, scrub mangroves, we tested Landsat (30‐m) and Sentinel (10‐m) against very high resolution (VHR) Planet (3‐m) and WorldView (1.8‐m) imagery and assessed the accuracy of machine learning classification approaches in discerning current (2022) mangrove and saltmarsh from other coastal habitats in a rapidly changing ecotone along the east coast of Florida, USA. Our aim is to (1) quantify the mappable differences in landscape composition and complexity, class dominance and spatial properties of mangrove and saltmarsh patches due to image resolution; and (2) to resolve mapping uncertainties in the region. We found that the ability of Landsat to map mangrove distributions at the leading range edge was hampered by the size and extent of mangrove stands being too small for detection (50% accuracy). WorldView was the most successful in discerning mangroves from other wetland habitats (84% accuracy), closely followed by Planet (82%) and Sentinel (81%). With WorldView, we detected 800 ha of mangroves within the Florida range‐limit study area, 35% more mangroves than were detected with Planet, 114% more than Sentinel and 537% more than Landsat. Higher‐resolution imagery helped reveal additional variability in landscape metrics quantifying diversity, spatial configuration and connectedness among mangrove and saltmarsh habitats at the landscape, class and patch scales. Overall, VHR satellite imagery improved our ability to map mangroves at range limits and can help supplement moderate‐resolution global distributions and outdated regional maps.

Abstract Repeat photography offers distinctive insights into ecological change, with ground‐based oblique photographs often predating early aerial images by decades. However, the oblique angle of the photographs presents challenges for extracting and analyzing ecological information using traditional remote sensing approaches. Several innovative methods have been developed for analyzing repeat photographs, but none offer a comprehensive end‐to‐end workflow incorporating image classification and georeferencing to produce quantifiable landcover data. In this paper, we provide an overview of two new tools, an automated deep learning classifier and intuitive georeferencing tool, and describe how they are used to derive landcover data from 19 images associated with the Mountain Legacy Project, a research team that works with the world's largest collection of systematic high‐resolution historic mountain photographs. We then combined these data to produce a contemporary landcover map for a study area in Jasper National Park, Canada. We assessed georeferencing accuracy by calculating the root‐mean‐square error and mean displacement for a subset of the images, which was 4.6 and 3.7 m, respectively. Overall classification accuracy of the landcover map produced from oblique images was 68%, which was comparable to landcover data produced from aerial imagery using a conventional classification method. The new workflow advances the use of repeat photographs for yielding quantitative landcover data. It has several advantages over existing methods including the ability to produce quick and consistent image classifications with little human input, and accurately georeference and combine these data to generate landcover maps for large areas.

Repeat photography offers distinctive insights into ecological change, with ground‐based oblique photographs often predating early aerial images by decades. However, the oblique angle of the photographs presents challenges for extracting and analyzing ecological information using traditional remote sensing approaches. Several innovative methods have been developed for analyzing repeat photographs, but none offer a comprehensive end‐to‐end workflow incorporating image classification and georeferencing to produce quantifiable landcover data. In this paper, we provide an overview of two new tools, an automated deep learning classifier and intuitive georeferencing tool, and describe how they are used to derive landcover data from 19 images associated with the Mountain Legacy Project, a research team that works with the world's largest collection of systematic high‐resolution historic mountain photographs. We then combined these data to produce a contemporary landcover map for a study area in Jasper National Park, Canada. We assessed georeferencing accuracy by calculating the root‐mean‐square error and mean displacement for a subset of the images, which was 4.6 and 3.7 m, respectively. Overall classification accuracy of the landcover map produced from oblique images was 68%, which was comparable to landcover data produced from aerial imagery using a conventional classification method. The new workflow advances the use of repeat photographs for yielding quantitative landcover data. It has several advantages over existing methods including the ability to produce quick and consistent image classifications with little human input, and accurately georeference and combine these data to generate landcover maps for large areas. [ABSTRACT FROM AUTHOR]

High-precision landcover classification is a fundamental prerequisite for resource and environmental monitoring and land-use status surveys. Imbued with intricate spatial information and texture features, very high spatial resolution remote sensing images accentuate the divergence between features within the same category, thereby amplifying the complexity of landcover classification. Consequently, semantic segmentation models leveraging deep backbone networks have emerged as stalwarts in landcover classification tasks owing to their adeptness in feature representation. However, the classification efficacy of a solitary backbone network model fluctuates across diverse scenarios and datasets, posing a persistent challenge in the construction or selection of an appropriate backbone network for distinct classification tasks. To elevate the classification performance and bolster the generalization of semantic segmentation models, we propose a novel semantic segmentation network architecture, named the aggregated backbone network (ABNet), for the meticulous landcover classification. ABNet aggregates three prevailing backbone networks (ResNet, HRNet, and VoVNet), distinguished by significant structural disparities, using a same-stage fusion approach. Subsequently, it amalgamates these networks with the Deeplabv3+ head after integrating the convolutional block attention mechanism (CBAM). Notably, this amalgamation harmonizes distinct scale features extracted by the three backbone networks, thus enriching the model's spatial contextual comprehension and expanding its receptive field, thereby facilitating more effective semantic feature extraction across different stages. The convolutional block attention mechanism primarily orchestrates channel adjustments and curtails redundant information within the aggregated feature layers. Ablation experiments demonstrate an enhancement of no less than 3% in the mean intersection over union (mIoU) of ABNet on both the LoveDA and GID15 datasets when compared with a single backbone network model. Furthermore, in contrast to seven classical or state-of-the-art models (UNet, FPN, PSPNet, DANet, CBNet, CCNet, and UPerNet), ABNet evinces excellent segmentation performance across the aforementioned datasets, underscoring the efficiency and robust generalization capabilities of the proposed approach. [ABSTRACT FROM AUTHOR]

This study assesses the applicability of different-resolution multispectral remote sensing images for mapping and estimating the aboveground biomass (AGB) of Carpobrotus edulis, a prominent invasive species in European coastal areas. This study was carried out on the Cávado estuary sand spit (Portugal). The performance of three sets of multispectral images with different Ground Sample Distances (GSDs) were compared: 2.5 cm, 5 cm, and 10 cm. The images were classified using the supervised classification algorithm random forest and later improved by applying a sieve filter. Samples of C. edulis were also collected, dried, and weighed to estimate the AGB using the relationship between the dry weight (DW) and vegetation indices (VIs). The resulting regression models were evaluated based on their coefficient of determination (R2), Normalised Root Mean Square Error (NRMSE), p-value, Akaike information criterion (AIC), and the Bayesian information criterion (BIC). The results show that the three tested image resolutions allow for constructing reliable coverage maps of C. edulis, with overall accuracy values of 89%, 85%, and 88% for the classification of the 2.5 cm, 5 cm, and 10 cm GSD images, respectively. The best-performing VI-DW regression models achieved R2 = 0.87 and NRMSE = 0.09 for the 2.5 cm resolution; R2 = 0.77 and NRMSE = 0.12 for the 5 cm resolution; and R2 = 0.64 and NRMSE = 0.15 for the 10 cm resolution. The C. edulis area and total AGB were 3441.10 m2 and 28,327.1 kg (with an AGB relative error (RE) = 0.08) for the 2.5 cm resolution; 3070.04 m2 and 29,170.8 kg (AGB RE = 0.08) for the 5 cm resolution; and 2305.06 m2 and 22,135.7 kg (AGB RE = 0.11) for the 10 cm resolution. Spatial and model differences were analysed in detail to determine their causes. Final analyses suggest that multispectral imagery of up to 5 cm GSD is adequate for estimating C. edulis distribution and biomass. [ABSTRACT FROM AUTHOR]

In hilly areas, landslides can occur due to natural factors such as heavy rainfall, earthquakes, moisture in soil, or man-made factors like unplanned constructions. Landslides can be disastrous leading to a huge loss of property and lives which can be avoided using automatic prediction. Recently, machine learning algorithms have been applied to automatically identify landslides. Numerous feature extraction and classification-based approaches have been implemented on satellite images for semiautomatic detection and prediction of landslides. However, limited research has been done on fully automatic detection with acceptable accuracy. The most challenging task in the classification and prediction of landslides from satellite images is to find an appropriate database for training and yield highly accurate testing results. The primary agenda of a comprehensive study of various techniques used for the detection and classification of landslides using satellite images is to identify the research gap. The secondary objective aims to propose a prototype of novel approach for the same task. Fifty papers based on machine learning and deep learning algorithms from reputed journals are considered for analysis. This article summarizes the performances of different classification techniques from recent literature followed by comparison and discussion with respect to accuracy. Based on the gap identified an effective prototype of the landslide classification approach is proposed. A slightly modified version of the deep learning model ResNet101 is proposed which yields an accuracy of 96.88% when tested on an augmented Beijing dataset of 770 satellite images. The article also offers the researchers the latest status, overview, and potential avenues of machine and deep learning algorithms for landslide detection. The techniques discussed will serve as a valuable resource for identifying research gaps, guiding new researchers, and fostering innovative exploration in the field of landslide classification using satellite images.

Abstract Non‐native species maps are important tools for understanding and managing biological invasions. We demonstrate a novel approach to extend presence modeling to map fractional cover (FC) of non‐native yellow sweet clover Melilotus officinalis in the Northern Great Plains, USA. We used ensembles of MaxEnt models to map FC across landscapes from satellite imagery trained from regional aerial imagery that was trained by local unmanned aerial vehicle (UAV) imagery. Clover cover from field surveys and classified UAV imagery were nearly identical (n = 22, R2 = 0.99). Two classified UAV images provided training data to map clover presence with MaxEnt and National Agricultural Imagery Program (NAIP) aerial imagery. We binned cover predictions from NAIP imagery within each Sentinel‐2 pixel into eight cover classes to create pure (100%) and FC (20%–95%) training data and modeled each class separately using MaxEnt and Sentinel‐2 imagery. We mapped pure clover with one classification threshold and compared its performance to 15 candidate maps that included FC predictions outside pure predictions. Each FC map represented alternative combinations of five MaxEnt thresholds and three approaches to assign cover to pixels with multiple predictions from the FC ensemble. Evaluations of performance with independent datasets revealed maps including FC corresponded to field (n = 32, R2 range: 0.39–0.68) and UAV (n = 20, R2 range: 0.61–0.84) data better than pure clover maps (R2 = 0.15 and 0.31, respectively). Overall, the pure clover map predicted 3.2% cover, whereas the three best performing FC maps predicted 6.6%–8.0% cover. Including FC predictions increased accuracy and cover predictions which can improve ecological understanding of invasions. Our method allows efficient FC mapping for vegetative species discernible in UAV imagery and may be especially useful for mapping rare, irruptive or patchily distributed species with poor representation in field data, which challenges landscape‐level mapping.

Copyright of Journal of Remote Sensing is the property of Editorial Office of Journal of Remote Sensing & Science Publishing Co. 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.)

High-precision landcover classification is a fundamental prerequisite for resource and environmental monitoring and land-use status surveys. Imbued with intricate spatial information and texture features, very high spatial resolution remote sensing images accentuate the divergence between features within the same category, thereby amplifying the complexity of landcover classification. Consequently, semantic segmentation models leveraging deep backbone networks have emerged as stalwarts in landcover classification tasks owing to their adeptness in feature representation. However, the classification efficacy of a solitary backbone network model fluctuates across diverse scenarios and datasets, posing a persistent challenge in the construction or selection of an appropriate backbone network for distinct classification tasks. To elevate the classification performance and bolster the generalization of semantic segmentation models, we propose a novel semantic segmentation network architecture, named the aggregated backbone network (ABNet), for the meticulous landcover classification. ABNet aggregates three prevailing backbone networks (ResNet, HRNet, and VoVNet), distinguished by significant structural disparities, using a same-stage fusion approach. Subsequently, it amalgamates these networks with the Deeplabv3+ head after integrating the convolutional block attention mechanism (CBAM). Notably, this amalgamation harmonizes distinct scale features extracted by the three backbone networks, thus enriching the model’s spatial contextual comprehension and expanding its receptive field, thereby facilitating more effective semantic feature extraction across different stages. The convolutional block attention mechanism primarily orchestrates channel adjustments and curtails redundant information within the aggregated feature layers. Ablation experiments demonstrate an enhancement of no less than 3% in the mean intersection over union (mIoU) of ABNet on both the LoveDA and GID15 datasets when compared with a single backbone network model. Furthermore, in contrast to seven classical or state-of-the-art models (UNet, FPN, PSPNet, DANet, CBNet, CCNet, and UPerNet), ABNet evinces excellent segmentation performance across the aforementioned datasets, underscoring the efficiency and robust generalization capabilities of the proposed approach.

Floodplain wetland ecosystems experience significant seasonal water fluctuation over the year, resulting in a dynamic hydroperiod, with a range of vegetation community responses. This paper assesses trends and changes in landcover and hydro-climatological variables, including air temperature, river discharge, and water level in the Upper Columbia River Wetlands (UCRW), British Columbia, Canada. A time series landcover classification from the Landsat image archive was generated using a Random Forest algorithm from 1984 to 2022. Peak river flow timing, duration, and anomalies were examined to evaluate temporal coincidence with observed landcover trends. The land cover classifier used to segment changes in wetland area and open water performed well (Kappa = 0.82). Over the last four decades, observed river discharge and air temperature have increased, precipitation has decreased, the timing of peak flow is earlier, and flow duration has been reduced. The frequency of both high discharge events and dry years have increased, indicating a shift towards more extreme floodplain flow behavior. These hydrometeorological changes are associated with a shift in the timing of snow melt from April to mid-May and are associated with seasonal changes in the vegetative communities over the 39-year period. The area of woody shrub landcover has increased in the spring (April to mid-May), peak flow period (late-May to July) and early fall (August to mid-September) by +6% to +12% since 1984. In the spring and early fall, the area of open water has decreased -3% to -6% since 1984, while it has increased 3% during the peak flow period. The area of marsh land cover (mostly bulrush and cattails) has declined in every season by -29% in spring, -19% in the peak flow period and -5% in early fall. These findings suggest that increasing temperatures have already impacted regional hydrology, wetland hydroperiod and floodplain landcover in the Upper Columbia Valley in Canada. Overall, there is substantial variation in seasonal and annual land cover reflecting the dynamic nature of floodplain wetlands, but the results show that the wetlands are drying out with increasing the areas of woody/shrubby habitat and loss of aquatic habitat. The results suggest that floodplain wetlands, particularly marsh and open water habitats are vulnerable to climatic and hydrological changes that could further reduce their areal extent in the future. [ABSTRACT FROM AUTHOR]

Hyperspectral images (HSIs) provide rich spectral information, facilitating many applications, including landcover classification. However, due to the high dimensionality of HSIs, landcover mapping applications usually suffer from the curse of dimensionality, which degrades the efficiency of supervised classifiers due to insufficient training samples. Feature extraction (FE) is a popular dimension reduction strategy for this issue. This paper proposes an unsupervised FE algorithm that involves extracting endmembers and clustering spectral bands. The proposed method first extracts existing endmembers from the HSI data via a vertex component analysis method. Using these endmembers, it subsequently constructs a prototype space (PS) in which each spectral band is represented by a point. Similar/correlated bands in the PS remain near one another, forming several clusters. Therefore, our method, in the next step, clusters spectral bands into multiple clusters via K-means and fuzzy C-means algorithms. Finally, it combines all the spectral bands in the same cluster using a weighted average operator to decrease the high dimensionality. The extracted features were evaluated by applying an SVM classifier. The experimental results confirmed the superior performance of the proposed method compared with five state-of-the-art dimension reduction algorithms. It outperformed these algorithms in terms of classification accuracy on three widely used hyperspectral images (Indian Pines, KSC, and Pavia Centre). The suggested technique also showed comparable or even stronger performance (up to 9% improvement) compared with its supervised competitor. Notably, the proposed method exhibited higher accuracy even when only a limited number of training samples were available for supervised classification. Using only five training samples per class for the KSC and Pavia Centre datasets, our method's classification accuracy was higher than that of its best-performing unsupervised competitors by about 7% and 1%, respectively, in our experiments. [ABSTRACT FROM AUTHOR]

Non‐native species maps are important tools for understanding and managing biological invasions. We demonstrate a novel approach to extend presence modeling to map fractional cover (FC) of non‐native yellow sweet clover Melilotus officinalis in the Northern Great Plains, USA. We used ensembles of MaxEnt models to map FC across landscapes from satellite imagery trained from regional aerial imagery that was trained by local unmanned aerial vehicle (UAV) imagery. Clover cover from field surveys and classified UAV imagery were nearly identical (n = 22, R2 = 0.99). Two classified UAV images provided training data to map clover presence with MaxEnt and National Agricultural Imagery Program (NAIP) aerial imagery. We binned cover predictions from NAIP imagery within each Sentinel‐2 pixel into eight cover classes to create pure (100%) and FC (20%–95%) training data and modeled each class separately using MaxEnt and Sentinel‐2 imagery. We mapped pure clover with one classification threshold and compared its performance to 15 candidate maps that included FC predictions outside pure predictions. Each FC map represented alternative combinations of five MaxEnt thresholds and three approaches to assign cover to pixels with multiple predictions from the FC ensemble. Evaluations of performance with independent datasets revealed maps including FC corresponded to field (n = 32, R2 range: 0.39–0.68) and UAV (n = 20, R2 range: 0.61–0.84) data better than pure clover maps (R2 = 0.15 and 0.31, respectively). Overall, the pure clover map predicted 3.2% cover, whereas the three best performing FC maps predicted 6.6%–8.0% cover. Including FC predictions increased accuracy and cover predictions which can improve ecological understanding of invasions. Our method allows efficient FC mapping for vegetative species discernible in UAV imagery and may be especially useful for mapping rare, irruptive or patchily distributed species with poor representation in field data, which challenges landscape‐level mapping. [ABSTRACT FROM AUTHOR]

Cities are spatially expanding rapidly, leading to urban sprawl. This study aims to understand the nature of the urban expansion of Chennai city, located on India’s southeastern coast, by determining the urban growth pattern and identifying the urban sprawl areas. The urban growth pattern and sprawl areas between 1998 and 2019 are identified using remote sensing data through the delineation of the Urban Core Boundary (UCB). The urban areas were extracted from the Land Use Land Cover (LULC) classification using combined classification technique to delineate the UCB. All the findings were validated using ground truth information. LULC classification performed with an accuracy of more than 90 % for urban land cover revealed an increase in urban cover by 71.77% from 1998 to 2009 and

In remote sensing, plenty of multispectral images are publicly available from various landcover satellite missions. Contrastive self-supervised learning is commonly applied to unlabeled data but relies on domain-specific transformations used for learning. When focusing on vegetation, standard transformations from image processing cannot be applied to the near-infrared (NIR) channel, which carries valuable information about the vegetation state. Therefore, we use contrastive learning, relying on different views of unlabeled, multispectral images to obtain a pretrained model to improve the accuracy scores on small-sized remote sensing datasets. This study presents the generation of additional views tailored to remote sensing images using atmospheric correction as an alternative transformation to color jittering. The purpose of the atmospheric transformation is to provide a physically consistent transformation. The proposed transformation can be easily integrated with multiple channels to exploit spectral signatures of objects. Our approach can be applied to other remote sensing tasks. Using this transformation leads to improved classification accuracy of up to 6%. [ABSTRACT FROM AUTHOR]

This study assesses the applicability of different-resolution multispectral remote sensing images for mapping and estimating the aboveground biomass (AGB) of Carpobrotus edulis, a prominent invasive species in European coastal areas. This study was carried out on the Cávado estuary sand spit (Portugal). The performance of three sets of multispectral images with different Ground Sample Distances (GSDs) were compared: 2.5 cm, 5 cm, and 10 cm. The images were classified using the supervised classification algorithm random forest and later improved by applying a sieve filter. Samples of C. edulis were also collected, dried, and weighed to estimate the AGB using the relationship between the dry weight (DW) and vegetation indices (VIs). The resulting regression models were evaluated based on their coefficient of determination (R2), Normalised Root Mean Square Error (NRMSE), p-value, Akaike information criterion (AIC), and the Bayesian information criterion (BIC). The results show that the three tested image resolutions allow for constructing reliable coverage maps of C. edulis, with overall accuracy values of 89%, 85%, and 88% for the classification of the 2.5 cm, 5 cm, and 10 cm GSD images, respectively. The best-performing VI-DW regression models achieved R2 = 0.87 and NRMSE = 0.09 for the 2.5 cm resolution; R2 = 0.77 and NRMSE = 0.12 for the 5 cm resolution; and R2 = 0.64 and NRMSE = 0.15 for the 10 cm resolution. The C. edulis area and total AGB were 3441.10 m2 and 28,327.1 kg (with an AGB relative error (RE) = 0.08) for the 2.5 cm resolution; 3070.04 m2 and 29,170.8 kg (AGB RE = 0.08) for the 5 cm resolution; and 2305.06 m2 and 22,135.7 kg (AGB RE = 0.11) for the 10 cm resolution. Spatial and model differences were analysed in detail to determine their causes. Final analyses suggest that multispectral imagery of up to 5 cm GSD is adequate for estimating C. edulis distribution and biomass.

The rapid population growth, intensive use of natural resources, and inadequate planning for sustainable cities have diminished people's access to the natural environment. This has resulted in insufficient greenspace provision and increased exposure inequity in neighborhoods, particularly in arid regions. This study aimed to map urban greenspaces (UGS) in Greater Zarqa Municipality (GZM) and innovatively combine multiple greenspace exposure indicators to identify neighborhoods that are deprived of greenspace. A random forest classification algorithm, utilizing sentinel-2 images and vegetation indices, were used to classify the GZM land into built-up, greenspace, and undeveloped lands. Per capita greenspace, greenspace density, mitigation, restoration, and instoration exposure indicators were calculated and mapped for GZM neighborhoods. The suitability modeler technique was then applied to create an integrated UGS exposure indicator, identifying urban neighborhoods deprived of greenspace. The classification achieved an overall accuracy of 96 % and revealed a very poor urban greenspace density of 2.1 % that is unequally distributed among neighborhoods. The Zarqa Qasabah and Russeifa were poorly vegetated compared to the Hashemyiah district. UGS exposure indicators showed that over 80 % (97 out of 121) of neighborhoods did not meet the minimum per capita greenspace, 10 % greenspace density, or acceptable potential for mitigation, restoration and instoration of greenspace exposure. The combined UGS exposure indicator ranked 4 % of GZM neighborhoods (covering 5 % of GZM land) as high UGS exposure areas, containing only 0.2 % of the built-up area and housing 0.5 % of population. In contrast, the majority of neighborhoods (56 %) were classified as having poor UGS exposure, encompassing 56 % of the built-up area and accommodating 67 % of the GZM population. This integrated indicator approach effectively assessed UGS exposure and provided an unbiased estimation for identifying greenspace-deprived neighborhoods. The findings can guide decision-makers and urban planners in promoting greenspace exposure equity and developing new UGSs in underserved areas. [ABSTRACT FROM AUTHOR]

Copyright of Avian Conservation & Ecology is the property of Resilience Alliance 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.)

Hyperspectral images (HSIs) provide rich spectral information, facilitating many applications, including landcover classification. However, due to the high dimensionality of HSIs, landcover mapping applications usually suffer from the curse of dimensionality, which degrades the efficiency of supervised classifiers due to insufficient training samples. Feature extraction (FE) is a popular dimension reduction strategy for this issue. This paper proposes an unsupervised FE algorithm that involves extracting endmembers and clustering spectral bands. The proposed method first extracts existing endmembers from the HSI data via a vertex component analysis method. Using these endmembers, it subsequently constructs a prototype space (PS) in which each spectral band is represented by a point. Similar/correlated bands in the PS remain near one another, forming several clusters. Therefore, our method, in the next step, clusters spectral bands into multiple clusters via K-means and fuzzy C-means algorithms. Finally, it combines all the spectral bands in the same cluster using a weighted average operator to decrease the high dimensionality. The extracted features were evaluated by applying an SVM classifier. The experimental results confirmed the superior performance of the proposed method compared with five state-of-the-art dimension reduction algorithms. It outperformed these algorithms in terms of classification accuracy on three widely used hyperspectral images (Indian Pines, KSC, and Pavia Centre). The suggested technique also showed comparable or even stronger performance (up to 9% improvement) compared with its supervised competitor. Notably, the proposed method exhibited higher accuracy even when only a limited number of training samples were available for supervised classification. Using only five training samples per class for the KSC and Pavia Centre datasets, our method’s classification accuracy was higher than that of its best-performing unsupervised competitors by about 7% and 1%, respectively, in our experiments.

Current Earth observation systems generate massive amounts of satellite image time series to keep track of geographical areas over time to monitor and identify environmental and climate change. Efficiently analyzing such data remains an unresolved issue in remote sensing. In classifying land cover, utilizing SITS rather than one image might benefit differentiating across classes because of their varied temporal patterns. The aim was to forecast the land cover class of a group of pixels as a multi-class single-label classification problem given their time series gathered using satellite images. In this article, we exploit SITS to assess the capability of several spatial and temporal deep learning models with the proposed architecture. The models implemented are the bidirectional gated recurrent unit (GRU), temporal convolutional neural networks (TCNN), GRU + TCNN, attention on TCNN, and attention of GRU + TCNN. The proposed architecture integrates univariate, multivariate, and pixel coordinates for the Reunion Island's landcover classification (LCC). the evaluation of the proposed architecture with deep neural networks on the test dataset determined that blending univariate and multivariate with a recurrent neural network and pixel coordinates achieved increased accuracy with higher F1 scores for each class label. The results suggest that the models also performed exceptionally well when executed in a partitioned manner for the LCC task compared to the temporal models. This study demonstrates that using deep learning approaches paired with spatiotemporal SITS data addresses the difficult task of cost-effectively classifying land cover, contributing to a sustainable environment. [ABSTRACT FROM AUTHOR]

Landcover classification is an important application in remote sensing, but it is always a challenge to distinguish different features with similar characteristics or large-scale differences. Some deep learning networks, such as UperNet, PSPNet, and DANet, use pyramid pooling and attention mechanisms to improve their abilities in multi-scale features extraction. However, due to the neglect of low-level features contained in the underlying network and the information differences between feature maps, it is difficult to identify small-scale objects. Thus, we propose a novel image segmentation network, named HFENet, for mining multi-level semantic information. Like the UperNet, HFENet adopts a top-down horizontal connection architecture while includes two improved modules, the HFE and the MFF. According to the characteristics of different levels of semantic information, HFE module reconstructs the feature extraction part by introducing an attention mechanism and pyramid pooling module to fully mine semantic information. With the help of a channel attention mechanism, MFF module up-samples and re-weights the feature maps to fuse them and enhance the expression ability of multi-scale features. Ablation studies and comparative experiments between HFENet and seven state-of-the-art models (U-Net, DeepLabv3+, PSPNet, FCN, UperNet, DANet and SegNet) are conducted with a self-labeled GF-2 remote sensing image dataset (MZData) and two open datasets landcover.ai and WHU building dataset. The results show that HFENet on three datasets with six evaluation metrics (mIoU, FWIoU, PA, mP, mRecall and mF1) are better than the other models and the mIoU is improved 7.41–10.60% on MZData, 1.17–11.57% on WHU building dataset and 0.93–4.31% on landcover.ai. HFENet can perform better in the task of refining the semantic segmentation of remote sensing images. [ABSTRACT FROM AUTHOR]

A portion of the Aransas-Wood Buffalo population of Whooping Cranes (Grus americana) stopover within the Central Platte River Valley (CPRV) annually. Past studies have found Whooping Cranes select herbaceous wetlands over agricultural fields when evaluated at a migration-corridor scale. However, recent studies conducted within the CPRV have reported Whooping Cranes selected agricultural fields and avoided herbaceous landcover classes. We hypothesized that much of this discrepancy was due to differences in landcover classifications used in previous studies, particularly those related to wetland designations. We used multiple existing, fine-scale geospatial data sources considering both landcover and hydrological factors to define unique and regionally specific ecotopes, which are the smallest homogenous and biologically relevant mappable units of analysis in landscape ecology (e.g., meadow-marsh, upland agriculture, etc.). We examined whether ecotope-based landcover, when evaluated at multiple spatial scales (i.e., 400 m and 1000 m), predicted terrestrial Whooping Crane occurrence within the CPRV. We used generalized linear mixed models within an information-theoretic approach to assess Whooping Crane occurrence within the CPRV. We found distinct ecotopes at the 1000-m scale explained nearly 40% of the variation in Whooping Crane occurrence. Ecotope models outperformed models including only their component parts such as flooding frequency and wetland designation. Whooping Cranes occurred more frequently within wetland portions of both agricultural fields and natural herbaceous communities and were less likely to use analogous upland components. We also found that occurrence was positively associated with proximity to the main channel of the Platte River and that Whooping Cranes avoided roads and developed areas, as several other studies have reported. Our findings indicate herbaceous and agricultural wetland areas should be targeted for Whooping Crane conservation efforts within the CPRV and perhaps regionally.

Current Earth observation systems generate massive amounts of satellite image time series to keep track of geographical areas over time to monitor and identify environmental and climate change. Efficiently analyzing such data remains an unresolved issue in remote sensing. In classifying land cover, utilizing SITS rather than one image might benefit differentiating across classes because of their varied temporal patterns. The aim was to forecast the land cover class of a group of pixels as a multi-class single-label classification problem given their time series gathered using satellite images. In this article, we exploit SITS to assess the capability of several spatial and temporal deep learning models with the proposed architecture. The models implemented are the bidirectional gated recurrent unit (GRU), temporal convolutional neural networks (TCNN), GRU + TCNN, attention on TCNN, and attention of GRU + TCNN. The proposed architecture integrates univariate, multivariate, and pixel coordinates for the Reunion Island’s landcover classification (LCC). the evaluation of the proposed architecture with deep neural networks on the test dataset determined that blending univariate and multivariate with a recurrent neural network and pixel coordinates achieved increased accuracy with higher F1 scores for each class label. The results suggest that the models also performed exceptionally well when executed in a partitioned manner for the LCC task compared to the temporal models. This study demonstrates that using deep learning approaches paired with spatiotemporal SITS data addresses the difficult task of cost-effectively classifying land cover, contributing to a sustainable environment.

The proliferation of small unmanned aerial systems (sUAS) is making very high-resolution imagery attainable for vegetation classifications, potentially allowing land managers to monitor vegetation in response to management or wildlife activities and offering researchers opportunities to further examine relationships among wildlife species and their habitats. The broad adoption of sUAS for remote sensing among these groups may be hampered by complex coding, expensive equipment, and time-consuming protocols. We used a consumer sUAS, semiautomated flight planning software, and graphical user interface GIS software to classify grassland vegetation with the aim of providing a user-friendly framework for managers and ecological researchers. We compared the overall accuracy from classifications using this sUAS imagery (89.22%) to classifications using freely available National Agriculture Imagery Program imagery (76.25%) to inform decisions about cost and accuracy. We also compared overall accuracy between manual classification (89.22%) and random forest classification (69.26%) to aid with similar decisions. Finally, we examined the impact of resolution and the addition of a canopy height model on classification accuracy, obtaining mixed results. Our findings can help new users make informed choices about imagery sources and methodologies, and our protocols can serve as a template for those groups wanting to perform similar vegetation classifications on grassland sites without the need for survey-grade equipment or coding. These should help more land managers and researchers obtain appropriate grassland vegetation classifications for their projects within their budgetary and logistical constraints.

Landcover classification is an important application in remote sensing, but it is always a challenge to distinguish different features with similar characteristics or large-scale differences. Some deep learning networks, such as UperNet, PSPNet, and DANet, use pyramid pooling and attention mechanisms to improve their abilities in multi-scale features extraction. However, due to the neglect of low-level features contained in the underlying network and the information differences between feature maps, it is difficult to identify small-scale objects. Thus, we propose a novel image segmentation network, named HFENet, for mining multi-level semantic information. Like the UperNet, HFENet adopts a top-down horizontal connection architecture while includes two improved modules, the HFE and the MFF. According to the characteristics of different levels of semantic information, HFE module reconstructs the feature extraction part by introducing an attention mechanism and pyramid pooling module to fully mine semantic information. With the help of a channel attention mechanism, MFF module up-samples and re-weights the feature maps to fuse them and enhance the expression ability of multi-scale features. Ablation studies and comparative experiments between HFENet and seven state-of-the-art models (U-Net, DeepLabv3+, PSPNet, FCN, UperNet, DANet and SegNet) are conducted with a self-labeled GF-2 remote sensing image dataset (MZData) and two open datasets landcover.ai and WHU building dataset. The results show that HFENet on three datasets with six evaluation metrics (mIoU, FWIoU, PA, mP, mRecall and mF1) are better than the other models and the mIoU is improved 7.41–10.60% on MZData, 1.17–11.57% on WHU building dataset and 0.93–4.31% on landcover.ai. HFENet can perform better in the task of refining the semantic segmentation of remote sensing images.

As an important application in remote sensing, landcover classification remains one of the most challenging tasks in very-high-resolution (VHR) image analysis. As the rapidly increasing number of Deep Learning (DL) based landcover methods and training strategies are claimed to be the state-of-the-art, the already fragmented technical landscape of landcover mapping methods has been further complicated. Although there exists a plethora of literature review work attempting to guide researchers in making an informed choice of landcover mapping methods, the articles either focus on the review of applications in a specific area or revolve around general deep learning models, which lack a systematic view of the ever advancing landcover mapping methods. In addition, issues related to training samples and model transferability have become more critical than ever in an era dominated by data-driven approaches, but these issues were addressed to a lesser extent in previous review articles regarding remote sensing classification. Therefore, in this paper, we present a systematic overview of existing methods by starting from learning methods and varying basic analysis units for landcover mapping tasks, to challenges and solutions on three aspects of scalability and transferability with a remote sensing classification focus including (1) sparsity and imbalance of data; (2) domain gaps across different geographical regions; and (3) multi-source and multi-view fusion. We discuss in detail each of these categorical methods and draw concluding remarks in these developments and recommend potential directions for the continued endeavor.

The role of forests to sequester carbon is considered an important strategy for mitigating climate change and achieving net zero emissions. However, forests in North Korea have continued to be cleared since the 1990s due to the lack of food and energy resources. Deforestation in this country has not been accurately classified nor consistently reported because of the characteristics of small patches. This study precisely determined the area of deforested land in North Korea through the vegetation phenological classification using high-resolution satellite imagery and deep learning algorithms. Effective afforestation target sites in North Korea were identified with priority grade. The U-Net deep learning algorithm and time-series Sentinel-2 satellite images were applied to phenological classification; the results reflected the small patch-like characteristics of deforestation in North Korea. Based on the phenological classification, the land cover of the country was classified with an accuracy of 84.6%; this included 2.6 million ha of unstocked forest and reclaimed forest. Sites for afforestation were prioritized into five grades based on deforested characteristics, altitude and slope. Forest area is expanded and the forest ecosystem is restored through successful afforestation, this may improve the overall ecosystem services in North Korea. In the long term, it will be possible to contribute to carbon neutrality and greenhouse gas reduction on the Korean Peninsula level through optimal afforestation by using these outcomes.

In this paper, we discuss the scientific outcomes of the 2015 data fusion contest organized by the Image Analysis and Data Fusion Technical Committee (IADF TC) of the IEEE Geoscience and Remote Sensing Society (IEEE GRSS). As for previous years, the IADF TC organized a data fusion contest aiming at fostering new ideas and solutions for multisource studies. The 2015 edition of the contest proposed a multiresolution and multisensorial challenge involving extremely high-resolution RGB images and a three-dimensional (3-D) LiDAR point cloud. The competition was framed in two parallel tracks, considering 2-D and 3-D products, respectively. In this paper, we discuss the scientific results obtained by the winners of the 2-D contest, which studied either the complementarity of RGB and LiDAR with deep neural networks (winning team) or provided a comprehensive benchmarking evaluation of new classification strategies for extremely high-resolution multimodal data (runner-up team). The data and the previously undisclosed ground truth will remain available for the community and can be obtained at http://www.grss-ieee.org/community/technical-committees/data-fusion/2015-ieee-grss-data-fusion-contest/. The 3-D part of the contest is discussed in the Part-B paper [1].

Real time, accurate and reliable estimation of maize yield is valuable to policy makers in decision making. The current study was planned for yield estimation of spring maize using remote sensing and crop modeling. In crop modeling, the CERES-Maize model was calibrated and evaluated with the field experiment data and after calibration and evaluation, this model was used to forecast maize yield. A Field survey of 64 farm was also conducted in Faisalabad to collect data on initial field conditions and crop management data. These data were used to forecast maize yield using crop model at farmers’ field. While in remote sensing, peak season Landsat 8 images were classified for landcover classification using machine learning algorithm. After classification, time series normalized difference vegetation index (NDVI) and land surface temperature (LST) of the surveyed 64 farms were calculated. Principle component analysis were run to correlate the indicators with maize yield. The selected LSTs and NDVIs were used to develop yield forecasting equations using least absolute shrinkage and selection operator (LASSO) regression. Calibrated and evaluated results of CERES-Maize showed the mean absolute % error (MAPE) of 0.35-6.71% for all recorded variables. In remote sensing all machine learning algorithms showed the accuracy greater the 90%, however support vector machine (SVM-radial basis) showed the higher accuracy of 97%, that was used for classification of maize area. The accuracy of area estimated through SVM-radial basis was 91%, when validated with crop reporting service. Yield forecasting results of crop model were precise with RMSE of 255 kg ha−1, while remote sensing showed the RMSE of 397 kg ha−1. Overall strength of relationship between estimated and actual grain yields were good with R2 of 0.94 in both techniques. For regional yield forecasting remote sensing could be used due greater advantages of less input dataset and if focus is to assess specific stress, and interaction of plant genetics to soil and environmental conditions than crop model is very useful tool. [ABSTRACT FROM AUTHOR]

This paper reports the outcomes of the 2014 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee (IADF TC) of the IEEE Geoscience and Remote Sensing Society (IEEE GRSS). As for previous years, the IADF TC organized a data fusion contest aiming at fostering new ideas and solutions for multisource remote sensing studies. In the 2014 edition, participants considered multiresolution and multisensor fusion between optical data acquired at 20-cm resolution and long-wave (thermal) infrared hyperspectral data at 1-m resolution. The Contest was proposed as a double-track competition: one aiming at accurate landcover classification and the other seeking innovation in the fusion of thermal hyperspectral and color data. In this paper, the results obtained by the winners of both tracks are presented and discussed.

Images provided by the ESA Sentinel-2 mission are rapidly becoming the main source of information for the entire remote sensing community, thanks to their unprecedented combination of spatial, spectral and temporal resolution, as well as their associated open access policy. Due to a sensor design trade-off, images are acquired (and delivered) at different spatial resolutions (10, 20 and 60 m) according to specific sets of wavelengths, with only the four visible and near infrared bands provided at the highest resolution (10 m). Although this is not a limiting factor in general, many applications seem to emerge in which the resolution enhancement of 20 m bands may be beneficial, motivating the development of specific super-resolution methods. In this work, we propose to leverage Convolutional Neural Networks (CNNs) to provide a fast, upscalable method for the single-sensor fusion of Sentinel-2 (S2) data, whose aim is to provide a 10 m super-resolution of the original 20 m bands. Experimental results demonstrate that the proposed solution can achieve better performance with respect to most of the state-of-the-art methods, including other deep learning based ones with a considerable saving of computational burden.

Land cover Classified maps obtained from deep learning methods such as Convolutional neural networks (CNNs) and fully convolutional networks (FCNs) usually have high classification accuracy but with the detailed structures of objects lost or smoothed. In this work, we develop a methodology based on fully convolutional networks (FCN) that is trained in an end-to-end fashion using aerial RGB images only as input. Skip connections are introduced into the FCN architecture to recover high spatial details from the lower convolutional layers. The experiments are conducted on the city of Goma in the Democratic Republic of Congo. We compare the results to a state-of-the art approach based on a semi-automatic Geographic object image-based analysis (GEOBIA) processing chain. State-of-the art classification accuracies are obtained by both methods whereby FCN and the best baseline method have an overall accuracy of 91.3% and 89.5% respectively. The maps have good visual quality and the use of an FCN skip architecture minimizes the rounded edges that is characteristic of FCN maps. Additional experiments are done to refine FCN classified maps using segments obtained from GEOBIA generated at different scale and minimum segment size. High OA of up to 91.5% is achieved accompanied with an improved edge delineation in the FCN maps, and future work will involve explicitly incorporating boundary information from the GEOBIA segmentation into the FCN pipeline in an end-to-end fashion. Finally, we observe that FCN has a lower computational cost than the standard patch-based CNN approach especially at inference.

Deep learning based land cover classification algorithms have recently been proposed in the literature. In hyperspectral images (HSIs), they face the challenges of large dimensionality, spatial variability of spectral signatures, and scarcity of labeled data. In this paper, we propose an end-to-end deep learning architecture that extracts band specific spectral-spatial features and performs land cover classification. The architecture has fewer independent connection weights and thus requires fewer training samples. The method is found to outperform the highest reported accuracies on popular HSI data sets. [ABSTRACT FROM PUBLISHER]

[Display omitted] • Terai vegetation is dynamic, and grasslands have declined in the last thirty years. • Fire occurrence has the strongest influence on grassland to woodland transformation. • Grassland decline was linked with increased area under croplands in some sites. The Terai-Duar Savanna and Grassland ecoregion (hereafter Terai), located at the base of the Himalayas in the Indian subcontinent, support diverse ecosystems with pure grasslands, savanna, and forests in varying proportions. There are indications that grasslands and savanna are being lost to woody encroachment across the ecoregion. A significant fraction of plant and animal taxa are endemic to grasslands, so the decline of grasslands is likely to impact biodiversity and ecosystem function. We assessed large-scale vegetation changes to Terai habitats over three decades (1989–2019) and quantified the role of environmental factors in driving the observed changes. Selecting eight large protected wildlife habitats (four each from India and Nepal), we performed supervised vegetation classification for three-time points. We then quantified grassland-woodland transitions and used Bayesian Conditional Autoregressive spatial models to test the influence of climatic, environmental, and anthropogenic factors on observed changes. Including the protected sites with substantial grassland areas, we found that the total extent of grasslands was 1417 km2 (28 % of total area) in 1988–1989, which declined by 34.4 % to 923 km2 in three decades, while woodland area increased by 8,7% from 3235 km2 to 3516 km2. Grasslands were also converted to cropland or inundated by flooding, but to a lesser extent. Dry season grass fire had the strongest influence on grassland persistence, followed by anthropogenic impacts. However, the eight sites differed with respect to the nature and extent of the changes in vegetation transitions, perhaps reflecting site differences in climatic conditions and anthropogenic influence. [ABSTRACT FROM AUTHOR]

In this paper, we discuss the scientific outcomes of the 2015 data fusion contest organized by the Image Analysis and Data Fusion Technical Committee (IADF TC) of the IEEE Geoscience and Remote Sensing Society (IEEE GRSS). As for previous years, the IADF TC organized a data fusion contest aiming at fostering new ideas and solutions for multisource studies. The 2015 edition of the contest proposed a multiresolution and multisensorial challenge involving extremely high-resolution RGB images and a three-dimensional (3-D) LiDAR point cloud. The competition was framed in two parallel tracks, considering 2-D and 3-D products, respectively. In this paper, we discuss the scientific results obtained by the winners of the 2-D contest, which studied either the complementarity of RGB and LiDAR with deep neural networks (winning team) or provided a comprehensive benchmarking evaluation of new classification strategies for extremely high-resolution multimodal data (runner-up team). The data and the previously undisclosed ground truth will remain available for the community and can be obtained at http://www.grss-ieee.org/community/technical-committees/data-fusion/2015-ieee-grss-data-fusion-contest/. The 3-D part of the contest is discussed in the Part-B paper [1]. [ABSTRACT FROM PUBLISHER]

Semantic segmentation of very-high-resolution (VHR) remote sensing images is of great significance, in which remote sensing can be applied to numerous fields. However, VHR remote sensing images are taken at different seasons and regions, causing the large intra-class and low inter-class variations of pixels. Thus, the state-of-the-art semantic segmentation network have considerable misclassifications and blurring of object boundaries. To solve the above problems, a deep learning-based semantic segmentation framework (DLSS) of VHR remote sensing images is proposed in this study, which comprising three stages. At the pre-processing stage, a novel data pre-processing method named Image Block Segmentation (IBS) is proposed to coarse segmentation of VHR remote sensing images at the image block scale. At the image segmentation stage, the different strategies are adopted to segment image blocks of different categories for fine segmentation. Through these two stages, this study implements a coarse-to-fine segmentation strategy, which reduces the phenomenon of misclassification by using different network models for low inter class variations of pixels. At the post-processing stage, a novel post-processing method termed Superpixel Cluster (SPC) is proposed to modify the segmentation results. SPC can capture fine details of objects and aggregating continuous pixels with similar characteristics into a set of superpixels, so as to ensure the boundary accuracy and internal consistency of ground object. Extensive experiments, including a comprehensive ablation study, confirm that IBS is capable of effectively reducing the misclassification, and SPC can correct the segmentation results significantly. The experimental results on the Gaofen Image Dataset (GID) suggest that the overall accuracy (OA) of the commonly utilized models combined with DLSS framework can increase, and the average is 2.05%. The code of DLSS is available at https://github.com/dxj620/Deep-learning-semantic-segementation. • A coarse-to-fine semantic segmentation framework of remote sensing images is designed. • Scene classification is used to reduce the impact of large intra-class and low inter-class variations. • Superpixel segmentation is used to improve boundary accuracy and internal consistency. [ABSTRACT FROM AUTHOR]

This paper reports the outcomes of the 2014 Data Fusion Contest organized by the Image Analysis and Data Fusion Technical Committee (IADF TC) of the IEEE Geoscience and Remote Sensing Society (IEEE GRSS). As for previous years, the IADF TC organized a data fusion contest aiming at fostering new ideas and solutions for multisource remote sensing studies. In the 2014 edition, participants considered multiresolution and multisensor fusion between optical data acquired at 20-cm resolution and long-wave (thermal) infrared hyperspectral data at 1-m resolution. The Contest was proposed as a double-track competition: one aiming at accurate landcover classification and the other seeking innovation in the fusion of thermal hyperspectral and color data. In this paper, the results obtained by the winners of both tracks are presented and discussed. [ABSTRACT FROM PUBLISHER]

This study proposed the development plan of a novel aerial-to-ground remote sensing (AGRS) system for surveying the land scenes of interest. Specifically, the AGRS system is composed by integrating an unmanned aerial vehicle (UAV) imaging system and a mobile mapping system (MMS), onboard whose platform a control station is also added. The UAV-MMS-collaboration can be classified into two modes – loosely and tightly, respectively related to two efficacy levels of the AGRS – fine-scale mapping in general and target investigating in special cases. The latter scenario can be illustrated by the tasks of fast-responses to the time-critical events, e.g., seeking the accessible roads into disaster areas. These all pose challenging issues. To ensure the premise for AGRS development, a field test was carried out in prior to examine the collaborative effect between its two RS-functional modules. Two typical topics were explored, i.e., self-indicated orthorectification of the UAV images and landcover classification based on information fusion. The final positive results have basically validated the feasibility of the development of the AGRS system. [ABSTRACT FROM PUBLISHER]

Abstract: The present study aims to evaluate the field-based approach for the classification of landcover using high-resolution SAR data. TerraSAR-X (TSX) strip mode imagery, coupled with digital ortho-photos (DOPs) with 20cm spatial resolution was used for landcover classification and parcel mapping respectively. Different filtering and analysis techniques were applied to extract textural information from the TSX image in order to assess the enhancement of the classification accuracy. Several attributes of parcels were derived from the available TSX images in order to define the most suitable parameters discriminating between different landcover types. Then, these attributes were further statistically analysed in order to define separability and thresholds between different landcover types. The results showed that textural analysis resulted in high classification accuracy. Hence, this paper confirms that integrated landcover classification using the textural information of TerraSAR-X has a high potential for landcover mapping. [Copyright &y& Elsevier]

As an important application in remote sensing, landcover classification remains one of the most challenging tasks in very-high-resolution (VHR) image analysis. As the rapidly increasing number of Deep Learning (DL) based landcover methods and training strategies are claimed to be the state-of-the-art, the already fragmented technical landscape of landcover mapping methods has been further complicated. Although there exists a plethora of literature review work attempting to guide researchers in making an informed choice of landcover mapping methods, the articles either focus on the review of applications in a specific area or revolve around general deep learning models, which lack a systematic view of the ever advancing landcover mapping methods. In addition, issues related to training samples and model transferability have become more critical than ever in an era dominated by data-driven approaches, but these issues were addressed to a lesser extent in previous review articles regarding remote sensing classification. Therefore, in this paper, we present a systematic overview of existing methods by starting from learning methods and varying basic analysis units for landcover mapping tasks, to challenges and solutions on three aspects of scalability and transferability with a remote sensing classification focus including (1) sparsity and imbalance of data; (2) domain gaps across different geographical regions; and (3) multi-source and multi-view fusion. We discuss in detail each of these categorical methods and draw concluding remarks in these developments and recommend potential directions for the continued endeavor. [ABSTRACT FROM AUTHOR]

Multiple satellite sensors are used to analyze physical processes that determine energy fluxes and their interaction at the urban surface. The study is based on summertime microclimate analyses of the Los Angeles and Paris metropolises. The method consists of deriving some parameters governing the surface heat fluxes, constructing statistics of thermal infrared images, and using a GIS to combine them with a landcover classification from SPOT-HRV multispectral images, and with data from intensive in-situ experiments. The average images reveal spatial and temporal variations of land surface temperature (LST), and distinct microclimatic patterns. The combined interpretation of the statistics images and of the landcover classification shows: (i) the effect of surface physical properties, especially in downtown business and industrial districts that display heat-islands larger than 7 °C; (ii) the temperating influence of water; (iii) the negative correlation between afternoon land surface temperature and normalized vegetation index, which confirms the cooling effect of urban parks; (iv) the correlation between variations of surface temperature and ozone concentration at diurnal and longer time scales. [Copyright &y& Elsevier]