We performed an out-of-distribution (OOD) analysis of ∼12,000,000 semi-independent 128 × 128 pixel${}^2$ sea surface temperature (SST) regions, which we define as cutouts, from all nighttime granules in the MODIS R2019 Level-2 public dataset to discover the most complex or extreme phenomena at the ocean’s surface. Our algorithm (ULMO) is a probabilistic autoencoder (PAE), which combines two deep learning modules: (1) an autoencoder, trained on ∼150,000 random cutouts from 2010, to represent any input cutout with a 512-dimensional latent vector akin to a (non-linear) Empirical Orthogonal Function (EOF) analysis; and (2) a normalizing flow, which maps the autoencoder’s latent space distribution onto an isotropic Gaussian manifold. From the latter, we calculated a log-likelihood (LL) value for each cutout and defined outlier cutouts to be those in the lowest 0.1% of the distribution. These exhibit large gradients and patterns characteristic of a highly dynamic ocean surface, and many are located within larger complexes whose unique dynamics warrant future analysis. Without guidance, ULMO consistently locates the outliers where the major western boundary currents separate from the continental margin. Prompted by these results, we began the process of exploring the fundamental patterns learned by ULMO thereby identifying several compelling examples. Future work may find that algorithms such as ULMO hold significant potential/promise to learn and derive other, not-yet-identified behaviors in the ocean from the many archives of satellite-derived SST fields. We see no impediment to applying them to other large remote-sensing datasets for ocean science (e.g., SSH and ocean color). Full article

Changing land use patterns is of great importance in environmental studies and critical for land use management decision making over farming systems in arid and semi-arid regions. Unfortunately, ground data scarcity or inadequacy in many regions can cause large uncertainties in the characterization of phenological changes in arid and semi-arid regions, which can hamper tailored decision making towards best agricultural management practices. Alternatively, state-of-the-art methods for phenological metrics’ extraction and long time-series analysis techniques of multispectral remote sensing imagery provide a viable solution. In this context, this study aims to characterize the changes over farming systems through trend analysis. To this end, four farming systems (fallow, rainfed, irrigated annual, and irrigated perennial) in arid areas of Morocco were studied based on four phenological metrics (PhM) (i.e., great integral, start, end, and length of the season). These were derived from large Moderate resolution Imaging Spectroradiometer (MODIS) normalized difference vegetation index (NDVI) time-series using both a machine learning algorithm and a pixel-based change analysis method. Results showed that during the last twenty-year period (i.e., 2000–2019), a significant dynamism of the plant cover was linked to the behavior of farmers who tend to cultivate intensively and to invest in high-income crops. More specifically, a relevant variability in fallow and rainfed areas, closely linked to the weather conditions, was found. In addition, significant lag trends of the start (−6 days) and end (+3 days) were found, which indicate that the length of the season was related to the spatiotemporal variability of rainfall. This study has also highlighted the potential of multitemporal moderate spatial resolution data to accurately monitor agriculture and better manage land resources. In the meantime, for operationally implementing the use of such work in the field, we believe that it is essential consider the perceptions, opinions, and mutual benefits of farmers and stakeholders to improve strategies and synergies whilst ensuring food, welfare, and sustainability. Full article

With the development of spaceborne global navigation satellite system-reflectometry (GNSS-R), it can be used for terrestrial applications as a promising remote sensing tool, such as soil moisture (SM) retrieval. The reflected L-band GNSS signal from the land surface can simultaneously generate coherent and incoherent scattering, depending on surface roughness. However, the contribution of the incoherent component was directly ignored in previous GNSS-R land soil moisture content retrieval due to the hypothesis of its relatively small proportion. In this paper, a detection method is proposed to distinguish the coherence of land GNSS-R delay-Doppler map (DDM) from the cyclone global navigation satellite system (CYGNSS) mission in terms of DDM power-spreading features, which are characterized by different classification estimators. The results show that the trailing edge slope of normalized integrated time-delay waveform presents a better performance to recognize coherent and incoherent dominated observations, indicating that 89.6% of CYGNSS land observations are dominated by the coherent component. Furthermore, the impact of the land GNSS-Reflected DDM coherence on soil moisture retrieval is evaluated from 19-month CYGNSS data. The experiment results show that the influence of incoherent component and incoherent observations is marginal for CYGNSS soil moisture retrieval, and the RMSE of GNSS-R derived soil moisture reaches 0.04 cm³/cm³. Full article

Information about the growth, productivity, and distribution of vegetation, which are highly relied on and sensitive to natural and anthropogenic factors, is essential for agricultural production management and eco-environmental sustainability in the Amur River Basin (ARB). In this paper, the spatial–temporal trends of vegetation dynamics were analyzed at the pixel scale in the ARB for the period of 1982–2013 using remotely sensed data of long-term leaf area index (LAI), fractional vegetation cover (FVC), and terrestrial gross primary productivity (GPP). The spatial autocorrelation characteristics of the vegetation indexes were further explored with global and local Moran’s I techniques. The spatial–temporal relationships between vegetation and climatic factors, land use/cover types and hydrological variables in the ARB were determined using a geographical and temporal weighted regression (GTWR) model based on the observed meteorological data, remotely sensed vegetation information, while the simulated hydrological variables were determined with the soil and water assessment tool (SWAT) model. The results suggest that the variation in area-average annual FVC was significant with an increase rate of 0.0004/year, and LAI, FVC, and GPP all exhibited strong spatial heterogeneity trends in the ARB. For LAI and FVC, the most significant changes in local spatial autocorrelation were recognized over the Sanjiang Plain, and the low–low agglomeration in the Sanjiang Plain decreased continuously. The GTWR model results indicate that natural and anthropogenic factors jointly took effect and interacted with each other to affect the vegetated regime of the region. The decrease in the impact of precipitation to vegetation growth over the Songnen Plain was determined as having started around 1991, which was most likely attributed to dramatic changes in water use styles induced by local land use changes, and corresponded to the negative correlation between pasture areas and vegetation indexes during the same period. The analysis results presented in this paper can provide vital information to decision-makers for use in managing vegetation resources. Full article

Trees growing on private property have become an essential part of urban green policies. In many places, restrictions are imposed on tree removal on private property. However, monitoring compliance of these regulations appears difficult due to a lack of reference data and public administration capacity. We assessed the impact of the temporary suspension of mandatory permits on tree removal, which was in force in 2017 in Poland, on the change in urban tree cover (UTC) in the case of the municipality of Racibórz. The bi-temporal airborne laser scanning (ALS) point clouds (2011 and 2017) and administrative records on tree removal permits were used for analyzing the changes of UTC in the period of 2011–2017. The results show increased tree removal at a time when the mandatory permit was suspended. Moreover, it appeared that most trees on private properties were removed without obtaining permission when it was obligatory. The method based on LiDAR we proposed allows for monitoring green areas, including private properties. Full article

Robust and reliable classification of sea ice types in synthetic aperture radar (SAR) images is needed for various operational and environmental applications. Previous studies have investigated the class-dependent decrease in SAR backscatter intensity with incident angle (IA); others have shown the potential of textural information to improve automated image classification. In this work, we investigate the inclusion of Sentinel-1 (S1) texture features into a Bayesian classifier that accounts for linear per-class variation of its features with IA. We use the S1 extra-wide swath (EW) product in ground-range detected format at medium resolution (GRDM), and we compute seven grey level co-occurrence matrix (GLCM) texture features from the HH and the HV backscatter intensity in the linear and logarithmic domain. While GLCM texture features obtained in the linear domain vary significantly with IA, the features computed from the logarithmic intensity do not depend on IA or reveal only a weak, approximately linear dependency. They can therefore be directly included in the IA-sensitive classifier that assumes a linear variation. The different number of looks in the first sub-swath (EW1) of the product causes a distinct offset in texture at the sub-swath boundary between EW1 and the second sub-swath (EW2). This offset must be considered when using texture in classification; we demonstrate a manual correction for the example of GLCM contrast. Based on the Jeffries–Matusita distance between class histograms, we perform a separability analysis for 57 different GLCM parameter settings. We select a suitable combination of features for the ice classes in our data set and classify several test images using a combination of intensity and texture features. We compare the results to a classifier using only intensity. Particular improvements are achieved for the generalized separation of ice and water, as well as the classification of young ice and multi-year ice. Full article

China launched the Three-North Shelterbelt Forest Program (TNSFP) in 1978 in northern China to combat desertification and dust storms, but it is still controversial in ecologically fragile arid and semi-arid areas, which is partly due to the uncertainties of monitoring of the spatial-temporal changes of forest distribution. In this study, we aim to provide an overall retrospect of the forest changes (i.e., forest gain and forest loss) in northern China during 2007–2017, and to analyze the forest changes in different precipitation zones. We first generated annual forest maps at 30 m spatial resolution during 2007–2017 in northern China through integrating Landsat and PALSAR/PALSAR-2 data. We found the PALSAR/Landsat-based forest maps outperform other four existing products (i.e., JAXA F/NF, FROM-GLC, GlobeLand30, and NLCD-China) from either PALSAR or Landsat data, with a higher overall accuracy 96% ± 1%. The spatial-temporal analyses of forests showed a substantial forest expansion from 316,898 ± 34,537 km² in 2007 to 384,568 ± 35,855 km² in 2017 in the central and eastern areas. We found a higher forest loss rate (i.e., 35%) in the precipitation zones with the annual mean precipitation less than 400 mm (i.e., the arid and semi-arid areas) comparing to that (i.e., 25%) in the zones with more than 400 mm (i.e., the humid areas), which suggests the lower surviving rate in the drylands. This study provides satellite-based evidence for the forest changes in different precipitation zones, and suggests that the likely impacts of precipitation on afforestation effectiveness should be considered in future implementation of ecological restoration projects like TNSFP. Full article

Large rivers are key components of the land-ocean branch of the global water and biogeochemical cycles. River discharges can have important influences on physical, biological, optical, and chemical processes in coastal oceans. It is, therefore, of importance to routinely monitor the time-varying dispersal patterns of river plumes. The European Space Agency (ESA) Soil Moisture and Ocean Salinity (SMOS) and the NASA Soil Moisture Active Passive (SMAP) satellites provide Sea Surface Salinity (SSS) observations capable of characterizing the spatial and temporal variability of major river plumes. The main objective of this study is to examine the consistency of SSS products, from these two missions, and two in-situ gridded salinity products in depicting SSS variations on seasonal to interannual time scales within a few hundred kilometers of major river mouths. We show that SSS from SMOS and SMAP satellites have good consistency in depicting seasonal and interannual SSS variations near major river mouths. The two gridded in-situ products underestimate these variations substantially. This underestimation, most notably associated with the low SSS season following the high-discharge season, is attributable to the limited in-situ sampling of the river plumes when they are the most active. This work underscores the importance of using satellite SSS to study river plumes, as well as to evaluate and constrain models. Full article

The Himalayan region is one of the most crucial mountain systems across the globe, which has significant importance in terms of the largest depository of snow and glaciers for fresh water supply, river runoff, hydropower, rich biodiversity, climate, and many more socioeconomic developments. This region directly or indirectly affects millions of lives and their livelihoods but has been considered one of the most climatically sensitive parts of the world. This study investigates the spatiotemporal variation in maximum extent of snow cover area (SCA) and its response to temperature, precipitation, and elevation over the northwest Himalaya (NWH) during 2000–2019. The analysis uses Moderate Resolution Imaging Spectroradiometer (MODIS)/Terra 8-day composite snow Cover product (MOD10A2), MODIS/Terra/V6 daily land surface temperature product (MOD11A1), Climate Hazards Infrared Precipitation with Station data (CHIRPS) precipitation product, and Shuttle Radar Topography Mission (SRTM) DEM product for the investigation. Modified Mann-Kendall (mMK) test and Spearman’s correlation methods were employed to examine the trends and the interrelationships between SCA and climatic parameters. Results indicate a significant increasing trend in annual mean SCA (663.88 km²/year) between 2000 and 2019. The seasonal and monthly analyses were also carried out for the study region. The Zone-wise analysis showed that the lower Himalaya (184.5 km²/year) and the middle Himalaya (232.1 km²/year) revealed significant increasing mean annual SCA trends. In contrast, the upper Himalaya showed no trend during the study period over the NWH region. Statistically significant negative correlation (−0.81) was observed between annual SCA and temperature, whereas a nonsignificant positive correlation (0.47) existed between annual SCA and precipitation in the past 20 years. It was also noticed that the SCA variability over the past 20 years has mainly been driven by temperature, whereas the influence of precipitation has been limited. A decline in average annual temperature (−0.039 °C/year) and a rise in precipitation (24.56 mm/year) was detected over the region. The results indicate that climate plays a vital role in controlling the SCA over the NWH region. The maximum and minimum snow cover frequency (SCF) was observed during the winter (74.42%) and monsoon (46.01%) season, respectively, while the average SCF was recorded to be 59.11% during the study period. Of the SCA, 54.81% had a SCF above 60% and could be considered as the perennial snow. The elevation-based analysis showed that 84% of the upper Himalaya (UH) experienced perennial snow, while the seasonal snow mostly dominated over the lower Himalaya (LH) and the middle Himalaya (MH). Full article

Surface flatness is an important indicator for the quality assessment of concrete surfaces during and after slab construction in the construction industry. Thanks to its speed and accuracy, terrestrial laser scanning (TLS) has been popularly used for surface flatness inspection of concrete slabs. However, the current TLS based approach for surface flatness inspection has two primary limitations associated with scan range and occluded area. First, the areas far away from the TLS normally suffer from inaccurate measurement caused by low scan density and high incident angle of laser beams. Second, physical barriers such as interior walls cause occluded areas where the TLS is not able to scan for surface flatness inspection. To address these limitations, this study presents a new method that employs flat mirrors to increase the measurement range with acceptable measurement accuracy and make possible the scanning of occluded areas even when the TLS is out of sight. To validate the proposed method, experiments on two laboratory-scale specimens are conducted, and the results show that the proposed approach can enlarge the scan range from 5 m to 10 m. In addition, the proposed method is able to address the occlusion problem of the previous methods by changing the laser beam direction. Based on these results, it is expected that the proposed technique has the potential for accurate and efficient surface flatness inspection in the construction industry. Full article

Accurate localization of road agents (GNSS receivers) is the basis of intelligent transportation systems, which is still difficult to achieve for GNSS positioning in urban areas due to the signal interferences from buildings. Various collaborative positioning techniques were recently developed to improve the positioning performance by the aid from neighboring agents. However, it is still challenging to study their performances comprehensively. The GNSS measurement error behavior is complicated in urban areas and unable to be represented by naive models. On the other hand, real experiments requiring numbers of devices are difficult to conduct, especially for a large-scale test. Therefore, a GNSS realistic urban measurement simulator is developed to provide measurements for collaborative positioning studies. The proposed simulator employs a ray-tracing technique searching for all possible interferences in the urban area. Then, it categorizes them into direct, reflected, diffracted, and multipath signal to simulate the pseudorange, $C/N_0$, and Doppler shift measurements correspondingly. The performance of the proposed simulator is validated through real experimental comparisons with different scenarios based on commercial-grade receivers. The proposed simulator is also applied with different positioning algorithms, which verifies it is sophisticated enough for the collaborative positioning studies in the urban area. Full article

Urban areas represent the primary source region of greenhouse gas emissions. Mapping urban areas is essential for understanding land cover change, carbon cycles, and climate change (urban areas also refer to impervious surfaces, i.e., artificial cover and structures). Remote sensing has greatly advanced urban areas mapping over the last several decades. At present, we have entered the era of big data. Long time series of satellite data such as Landsat and high-performance computing platforms such as Google Earth Engine (GEE) offer new opportunities to map urban areas. The objective of this research was to determine how annual time series images from Landsat 8 Operational Land Imager (OLI) can effectively be composed to map urban areas in three cities in China in support of GEE. Three reducer functions, ee.Reducer.min(), ee.Reducer.median(), and ee.Reducer.max() provided by GEE, were selected to construct four schemes to synthesize the annual intensive time series Landsat 8 OLI data for three cities in China. Then, urban areas were mapped based on the random forest algorithm and the accuracy was evaluated in detail. The results show that (1) the quality of annual composite images was improved significantly, particularly in reducing the impact of cloud and cloud shadows, and (2) the annual composite images obtained by the combination of multiple reducer functions had better performance than that obtained by a single reducer function. Further, the overall accuracy of urban areas mapping with the combination of multiple reducer functions exceeded 90% in all three cities in China. In summary, a suitable combination of reducer functions for synthesizing annual time series images can enhance data quality and ensure differences between characteristics and higher precision for urban areas mapping. Full article

While outdoor navigation systems are already represented everywhere, the enclosed space is much less developed. The project Level 5 Indoor Navigation (L5IN) presents a new approach with mobile phone standard 5G as the orientation signal and without additional infrastructure for navigation in indoor environments. The aim of this project is to use the new available 5G technology to show how navigation systems, which have thus far only been available in the outdoor segment, can now be integrated into existing smartphone systems for indoor navigation. This paper gives an overview of the project and presents the different work packages leading to a holistic approach towards the development of an indoor navigation application for pedestrians. By using a specific app with open interfaces, it is planned to make navigation possible in all buildings modeled according to certain standards. The challenge involved is that, unlike outdoor maps, there is no map basis for buildings. For this reason, different approaches to map generation were examined. In a building information model (BIM), all information will be collected and made available via a database for positioning and visualization. The focus is furthermore on positioning, achieved through smartphone sensors and 5G, so that users can orientate themselves in buildings without having to connect to singular systems. It shall be shown that positioning with a standard deviation of 2–3 m and a confidence interval of 68 % is possible. Another advantage of 5G, the ability to send real-time data in higher data packages, will be used for data transmission. The basic idea of 5G-based indoor navigation will be enabled with radio cells of the providers, which will be set up on the HafenCity University campus. The complex university building will be used as a prototype environment. Full article

Estimating the permittivity of heterogeneous mixtures based on the permittivity of their components is of high importance with many applications in ground penetrating radar (GPR) and in electrodynamics-based sensing in general. Complex Refractive Index Model (CRIM) is the most mainstream approach for estimating the bulk permittivity of heterogeneous materials and has been widely applied for GPR applications. The popularity of CRIM is primarily based on its simplicity while its accuracy has never been rigorously tested. In the current study, an optimised shape factor is derived that is fine-tuned for modelling the dielectric properties of concrete. The bulk permittivity of concrete is expressed with respect to its components i.e., aggregate particles, cement particles, air-voids and volumetric water fraction. Different combinations of the above materials are accurately modelled using the Finite-Difference Time-Domain (FDTD) method. The numerically estimated bulk permittivity is then used to fine-tune the shape factor of the CRIM model. Then, using laboratory measurements it is shown that the revised CRIM model over-performs the default shape factor and provides with more accurate estimations of the bulk permittivity of concrete. Full article

Deep learning methods have been shown to significantly improve the performance of building extraction from optical remote sensing imagery. However, keeping the morphological characteristics, especially the boundaries, is still a challenge that requires further study. In this paper, we propose a novel fully convolutional network (FCN) for accurately extracting buildings, in which a boundary learning task is embedded to help maintain the boundaries of buildings. Specifically, in the training phase, our framework simultaneously learns the extraction of buildings and boundary detection and only outputs extraction results while testing. In addition, we introduce spatial variation fusion (SVF) to establish an association between the two tasks, thus coupling them and making them share the latent semantics and interact with each other. On the other hand, we utilize separable convolution with a larger kernel to enlarge the receptive fields while reducing the number of model parameters and adopt the convolutional block attention module (CBAM) to boost the network. The proposed framework was extensively evaluated on the WHU Building Dataset and the Inria Aerial Image Labeling Dataset. The experiments demonstrate that our method achieves state-of-the-art performance on building extraction. With the assistance of boundary learning, the boundary maintenance of buildings is ameliorated. Full article