Search Results (10)

Amid accelerating climate change, intensifying urban heat island effects, and rising public demand for livable, walkable streets, there is an urgent practical need for interpretable and actionable evidence on streetscape quality. Yet, research on streetscape quality has often relied on single data sources and linear models, limiting insight into multidimensional perception; evidence from temperate monsoon cities remains scarce. Using Tianjin’s main urban area as a case study, we integrate street-view imagery with remote sensing imagery to characterize satellite-derived environmental indicators at the point scale and examine the following five perceptual outcomes: comfort, aesthetics, perceived greenness, summer heat perception, and willingness to linger. We develop a three-step interpretable assessment, as follows: Elastic Net logistic regression to establish directional and magnitude baselines; Generalized Additive Models with a logistic link to recover nonlinear patterns and threshold bands with Benjamini–Hochberg false discovery rate control and binned probability calibration; and Shapley additive explanations to provide parallel validation and global and local explanations. The results show that the Green View Index is consistently and positively associated with all five outcomes, whereas Spatial Balance is negative across the observed range. Sky View Factor and the Building Visibility Index display heterogeneous forms, including monotonic, U-shaped, and inverted-U patterns across outcomes; Normalized Difference Vegetation Index and Land Surface Temperature are likewise predominantly nonlinear with peak sensitivity in the midrange. In total, 54 of 55 smoothing terms remain significant after Benjamini–Hochberg false discovery rate correction. The summer heat perception outcome is highly imbalanced: 94.2% of samples are labeled positive. Overall calibration is good. On a standardized scale, we delineate optimal and risk intervals for key indicators and demonstrate the complementary explanatory value of street-view imagery and remote sensing imagery for people-centered perceptions. In Tianjin, a temperate monsoon megacity, the framework provides reproducible, actionable, design-relevant evidence to inform streetscape optimization and offers a template that can be adapted to other cities, subject to local calibration. Full article

The Yangtze River Basin, one of China’s most vital watersheds, sustains both ecological balance and human livelihoods through its extensive lake systems. However, since the 1980s, these lakes have experienced significant ecological degradation, particularly in terms of aquatic vegetation decline. To acquire reliable aquatic vegetation data during the peak growing season (July–September), when clear-sky conditions are scarce, we employed Chinese domestic satellite imagery—Gaofen-1/6 (GF-1/6) Wide Field of View (WFV) and Huanjing-2A/B (HJ-2A/B) Charge-Coupled Device (CCD)—with approximately one-day revisit frequency after constellation networking, 16 m spatial resolution, and excellent spectral consistency, in combination with deep learning algorithms, to monitor aquatic vegetation across the basin. Comparative experiments identified the near-infrared, red, and green bands as the most informative input features, with an optimal input size of 256 × 256. Through visual interpretation and dataset augmentation, we generated a total of 5016 labeled image pairs of this size. The U-Net++ model, equipped with an EfficientNet-B5 backbone, achieved robust performance with an mIoU of 90.16% and an mPA of 95.27% on the validation dataset. On independent test data, the model reached an mIoU of 79.10% and an mPA of 86.42%. Field-based assessment yielded an overall accuracy (OA) of 75.25%, confirming the reliability of the model. As a case study, the proposed model was applied to satellite imagery of Lake Taihu captured during the peak growing season of aquatic vegetation (July–September) from 2020 to 2025. Overall, this study introduces an automated classification approach for aquatic vegetation using 16 m resolution Chinese domestic satellite imagery and deep learning, providing a reliable framework for large-scale monitoring of aquatic vegetation across lakes in the Yangtze River Basin during their peak growth period. Full article

The arrangement and design of urban streets have a profound impact on the thermal conditions within cities, including the mitigation of excessive street land surface temperatures (LSTs). However, previous research has mainly addressed the linear relationships between the physical spatial elements of streets and LST. There has been limited exploration of potential nonlinear relationships and the influence of population density variations. This study explores multi-dimensional street composition indicators obtained from street-view imagery and applies generalized additive models (GAMs) and geographically weighted regression (GWR) to evaluate the indicators’ impact on LST in areas with various population densities. The results indicate the following: (1) The six indicators—green space index (GSI), tree canopy index (TCI), sky open index (SOI), spatial enclosure index (SEI), road width index (RWI), and street walking index (SWI)—all have significant nonlinear effects on summer daytime LST. (2) Among all categories, the GSI negatively affects LST. Moreover, the TCI’s impact on LST shifts from negative to positive as its value increases. The SOI and SWI positively affect LST in all categories. The SEI’s effect on LST changes from negative to positive in the total and high-population (HP) categories, and it remains negative in the low-population (LP) category. The RWI positively affects LST in the total category, shifts from negative to positive in the LP category, and remains negative in the HP category. (3) The influence ranking is GSI > SEI > SWI > SOI > TCI > RWI, with GSI being the most significant factor. These findings provide key insights for mitigating street LSTs through design interventions, contributing to sustainable urban development. Full article

In Near and Middle Eastern archaeology, satellite-derived digital elevation models (DEM) of medium spatial resolution (≥30 m) are mostly used to locate and map archaeological mounds (namely ‘tells’), whereas high resolution DEMs (≤10 m) are still poorly exploited. To fill this gap, the 5 m resolution CartoSat-1 Euro-Maps 3D Digital Surface Model (DSM) is assessed vs. the 30 m Shuttle Radar Topography Mission (SRTM) global DEM, the Advanced Land Observing Satellite (ALOS) World 3D–30 m (AW3D30) and a 10 m COSMO-SkyMed DEM, on a test area in Wasit, southern Iraq, where the high density of tells is yet to be exhaustively documented. A total of 344 sites was mapped, with one order of magnitude improvement compared to previous mapping exercises, existing databases and historical maps. The morphometric analysis not only highlights the reliability of CartoSat-1 DSM height and volume estimates, but also suggests that, in the test area, the volume of a tell can robustly be calculated based on the simple knowledge of its basal area, following a quadratic function. Morphology and elevation of at least 53% irregularly shaped tells were impacted by anthropogenic disturbances. Morphometric indices (e.g., Topographic Position Index, DEViation from mean elevation) are a viable automated method to ease tells detection. When integrated with other satellite datasets (e.g., CORONA, Google Earth, Sentinel-2 imagery), the CartoSat-1 DSM can unveil morphological changes and support condition assessment. In Wasit, agriculture and modern development are among the major threats for tells preservation, alongside looting. Full article

Thaw consolidation of degrading permafrost is a serious hazard to the safety and operation of infrastructure. Monitoring thermal changes in the active layer (AL), the proportion of the soil above permafrost that thaws and freezes periodically, is critical to understanding the conditions of the top layer above the permafrost and regulating the construction, operation, and maintenance of facilities. However, this is a very challenging task using ground-based methods such as ground-penetrating radar (GPR) or temperature sensors. This study explores the integration of interferometric measurements from high-resolution X-band Synthetic Aperture Radar (SAR) images and volumetric water content (VWC) data from SoilGrids to quantify detailed spatial variations in active layer thickness (ALT) in Iqaluit, the territorial capital of Nunavut in Canada. A total of 21 SAR images from COSMO Sky-Med (CSK) were first analyzed using the freely connected network interferometric synthetic aperture radar (FCNInSAR) method to map spatial and temporal variations in ground surface subsidence in the study area. Subsequently, we built an ALT retrieval model by introducing the thaw settlement coefficient, which takes soil properties and saturation state into account. The subsidence measurements from InSAR were then integrated with VWC extracted from the SoilGrids database to estimate changes in ALT. For validation, we conducted a comparison between estimated ALTs and in situ measurements in the airport sector. The InSAR survey identifies several sites of ground deformation at Iqaluit, subsiding at rates exceeding 80 mm/year. The subsidence rate changes along the runway coincide with frost cracks and ice-wedge furrows. The obtained ALTs, ranging from 0 to 5 m, vary significantly in different sediments. Maximum ALTs are found for rock areas, while shallow ALTs are distributed in the till blanket (Tb), the intertidal (Mi) sediments, and the alluvial flood plain (Afp) sediment units. The intersection of taxiway and runway has an AL thicker than other parts in the glaciomarine deltaic (GMd) sediments. Our study suggests that combining high-resolution SAR imagery with VWC data can provide more comprehensive ALT knowledge for hazard prevention and infrastructure operation in the permafrost zone. Full article

Early warning of severe weather caused by intense convective weather systems is challenging. To help such activities, meteorological satellites with high temporal and spatial resolution have been utilized for the monitoring of instability trends along with water vapor variation. The current study proposes a retrieval algorithm based on an artificial neural network (ANN) model to quickly and efficiently derive total precipitable water (TPW) and convective available potential energy (CAPE) from Korea’s second geostationary satellite imagery measurements (GEO-KOMPSAT-2A/Advanced Meteorological Imager (AMI)). To overcome the limitations of the traditional static (ST) learning method such as exhaustive learning, impractical, and not matching in a sequence data, we applied an ANN model with incremental (INC) learning. The INC ANN uses a dynamic dataset that begins with the existing weight information transferred from a previously learned model when new samples emerge. To prevent sudden changes in the distribution of learning data, this method uses a sliding window that moves along the data with a window of a fixed size. Through an empirical test, the update cycle and the window size of the model are set to be one day and ten days, respectively. For the preparation of learning datasets, nine infrared brightness temperatures of AMI, six dual channel differences, temporal and geographic information, and a satellite zenith angle are used as input variables, and the TPW and CAPE from ECMWF model reanalysis (ERA5) data are used as the corresponding target values over the clear-sky conditions in the Northeast Asia region for about one year. Through the accuracy tests with radiosonde observation for one year, the INC NN results demonstrate improved performance (the accuracy of TPW and CAPE decreased by approximately 26% and 26% for bias and about 13% and 12% for RMSE, respectively) when compared to the ST learning. Evaluation results using ERA5 data also reveal more stable error statistics over time and overall reduced error distribution compared with ST ANN. Full article

Total Cloud Cover (TCC) retrieval from ground-based optical imagery is a problem that has been tackled by several generations of researchers. The number of human-designed algorithms for the estimation of TCC grows every year. However, there has been no considerable progress in terms of quality, mostly due to the lack of systematic approach to the design of the algorithms, to the assessment of their generalization ability, and to the assessment of the TCC retrieval quality. In this study, we discuss the optimization nature of data-driven schemes for TCC retrieval. In order to compare the algorithms, we propose a framework for the assessment of the algorithms’ characteristics. We present several new algorithms that are based on deep learning techniques: A model for outliers filtering, and a few models for TCC retrieval from all-sky imagery. For training and assessment of data-driven algorithms of this study, we present the Dataset of All-Sky Imagery over the Ocean (DASIO) containing over one million all-sky optical images of the visible sky dome taken in various regions of the world ocean. The research campaigns that contributed to the DASIO collection took place in the Atlantic ocean, the Indian ocean, the Red and Mediterranean seas, and the Arctic ocean. Optical imagery collected during these missions are accompanied by standard meteorological observations of cloudiness characteristics made by experienced observers. We assess the generalization ability of the presented models in several scenarios that differ in terms of the regions selected for the train and test subsets. As a result, we demonstrate that our models based on convolutional neural networks deliver a superior quality compared to all previously published approaches. As a key result, we demonstrate a considerable drop in the ability to generalize the training data in the case of a strong covariate shift between the training and test subsets of imagery which may occur in the case of region-aware subsampling. Full article

Characterizing the atmosphere is one of the most complex studies one can undertake due to the non-linearity and phenomenological variability. Clouds are also among the most variable atmospheric constituents, changing their size and shape over a short period of time. There are several sectors in which the study of cloudiness is of vital importance. In the renewable field, the increasing development of solar technology and the emerging trend for constructing and operating solar plants across the earth’s surface requires very precise control systems that provide optimal energy production management. Similarly, airports are hubs where cloud coverage is required to provide high-precision periodic observations that inform airport operators about the state of the atmosphere. This work presents an autonomous cloud detection system, in real time, based on the digital image processing of a low-cost sky camera. An algorithm was developed to identify the clouds in the whole image using the relationships established between the channels of the RGB and Hue, Saturation, Value (HSV) color spaces. The system’s overall success rate is approximately 94% for all types of sky conditions; this is a novel development which makes it possible to identify clouds from a ground perspective without the use of radiometric parameters. Full article

The Landsat record represents an amazing resource for discovering land-cover changes and monitoring the Earth’s surface. However, making the most use of the available data, especially for automated applications ingesting thousands of images without human intervention, requires a robust screening of cloud and cloud-shadow, which contaminate clear views of the land surface. We constructed a deep convolutional neural network (CNN) model to semantically segment Landsat 8 images into regions labeled clear-sky, clouds, cloud-shadow, water, and snow/ice. For training, we constructed a global, hand-labeled dataset of Landsat 8 imagery; this labor-intensive process resulted in the uniquely high-quality dataset needed for the creation of a high-quality model. The CNN model achieves results on par with the ability of human interpreters, with a total accuracy of 97.1%, omitting only 3.5% of cloud pixels and 4.8% of cloud shadow pixels, which is seven to eight times fewer missed pixels than the masks distributed with the imagery. By harnessing the power of advanced tensor processing units, the classification of full images is I/O bound, making this approach a feasible method to generate masks for the entire Landsat 8 archive. Full article

In the species-rich and structurally complex forests of the Eastern United States, disturbance events are often partial and therefore difficult to detect using remote sensing methods. Here we present a set of new algorithms, collectively called Vegetation Regeneration and Disturbance Estimates through Time (VeRDET), which employ a novel patch-based approach to detect periods of vegetation disturbance, stability, and growth from the historical Landsat image records. VeRDET generates a yearly clear-sky composite from satellite imagery, calculates a spectral vegetation index for each pixel in that composite, spatially segments the vegetation index image into patches, temporally divides the time series into differently sloped segments, and then labels those segments as disturbed, stable, or regenerating. Segmentation at both the spatial and temporal steps are performed using total variation regularization, an algorithm originally designed for signal denoising. This study explores VeRDET’s effectiveness in detecting forest change using four vegetation indices and two parameters controlling the spatial and temporal scales of segmentation within a calibration region. We then evaluate algorithm effectiveness within a 386,000 km² area in the Eastern United States where VeRDET has overall error of 23% and omission error across disturbances ranging from 22% to 78% depending on agent. Full article