Remote Sens., Volume 12, Issue 22 (November-2 2020) – 172 articles

Despite a number of studies on biomass burning (BB) emissions in the atmosphere, observation of the associated aerosols and pollutants requires continuous efforts. Brazil, and more broadly Latin America, is one of the most important seasonal sources of BB, particularly in the Amazon region. Uncertainty about aerosol loading in the source regions is a limiting factor in terms of understanding the role of aerosols in climate modelling. In the present work, we investigated the Amazon BB episode that occurred during August 2019 and made the international headlines, especially when the smoke plumes plunged distant cities such as São Paulo into darkness. Here, we used satellite and ground-based observations at different locations to investigate the long-range transport of aerosol plumes generated by the Amazon fires during the study period. The monitoring of BB activity was carried out using fire related pixel count from the moderate resolution imaging spectroradiometer (MODIS) onboard the Aqua and Terra platforms, while the distribution of carbon monoxide (CO) concentrations and total columns were obtained from the infrared atmospheric sounding interferometer (IASI) onboard the METOP-A and METOP-B satellites. In addition, AERONET sun-photometers as well as the MODIS instrument made aerosol optical depth (AOD) measurements over the study region. Our datasets are consistent with each other and highlight AOD and CO variations and long-range transport of the fire plume from the source regions in the Amazon basin. We used the Lagrangian transport model FLEXPART (FLEXible PARTicle) to simulate backward dispersion, which showed good agreement with satellite and ground measurements observed over the study area. The increase in Rossby wave activity during the 2019 austral winter the Southern Hemisphere may have contributed to increasing the efficiency of large-scale transport of aerosol plumes generated by the Amazon fires during the study period. Full article

The real-time, accurate, and refined monitoring of urban green space status information is of great significance in the construction of urban ecological environment and the improvement of urban ecological benefits. The high-resolution technology can provide abundant information of ground objects, which makes the information of urban green surface more complicated. The existing classification methods are challenging to meet the classification accuracy and automation requirements of high-resolution images. This paper proposed a deep learning classification method for urban green space based on phenological features constraints in order to make full use of the spectral and spatial information of green space provided by high-resolution remote sensing images (GaoFen-2) in different periods. The vegetation phenological features were added as auxiliary bands to the deep learning network for training and classification. We used the HRNet (High-Resolution Network) as our model and introduced the Focal Tversky Loss function to solve the sample imbalance problem. The experimental results show that the introduction of phenological features into HRNet model training can effectively improve urban green space classification accuracy by solving the problem of misclassification of evergreen and deciduous trees. The improvement rate of F1-Score of deciduous trees, evergreen trees, and grassland were 0.48%, 4.77%, and 3.93%, respectively, which proved that the combination of vegetation phenology and high-resolution remote sensing image can improve the results of deep learning urban green space classification. Full article

Unmanned Aerial Vehicles (UAVs) represent easy, affordable, and simple solutions for many tasks, including the collection of traffic data. The main aim of this study is to propose a new, low-cost framework for the determination of highly accurate traffic flow parameters. The proposed framework consists of four segments: terrain survey, image processing, vehicle detection, and collection of traffic flow parameters. The testing phase of the framework was done on the Zagreb bypass motorway. A significant part of this study is the integration of the state-of-the-art pre-trained Faster Region-based Convolutional Neural Network (Faster R-CNN) for vehicle detection. Moreover, the study includes detailed explanations about vehicle speed estimation based on the calculation of the Mean Absolute Percentage Error (MAPE). Faster R-CNN was pre-trained on Common Objects in COntext (COCO) images dataset, fine-tuned on 160 images, and tested on 40 images. A dual-frequency Global Navigation Satellite System (GNSS) receiver was used for the determination of spatial resolution. This approach to data collection enables extraction of trajectories for an individual vehicle, which consequently provides a method for microscopic traffic flow parameters in detail analysis. As an example, the trajectories of two vehicles were extracted and the comparison of the driver’s behavior was given by speed—time, speed—space, and space—time diagrams. Full article

Rapid urbanization processes and indiscriminate disposal of urban wastewaters are major causes for anthropogenic lake-sediment deposition and eutrophication. However, information about the spatial and temporal variation of macrophyte and phytoplankton distribution as indicators for water contamination is limited. To gain insights into the dynamics, we analyzed lake-cover changes of Bellandur and Varthur Lake in the S-Indian megacity of Bengaluru for the post-rainy seasons of the years 2002–2019. Supervised maximum likelihood classifications were conducted on 62 freely available, true-color satellite images in order to distinguish between macrophytes, algae, and free water surface. The image-derived results were verified by supervised classification and manual mapping of two simultaneously recorded multispectral satellite images (Sentinel-2 and WorldView-2). Seasonal interrelations between macrophytes and algae distribution were similar for both lakes. The increase in macrophyte cover during post-rainy season negatively correlated with algal abundance. Macrophyte expansion progressively suppressed algae development at both lakes, reflective of increasing eutrophication caused by on-going wastewater input. Seasonal variation in precipitation, wind direction, and temperature seemed to trigger intra-annual shifts of macrophytes and algae while similar macrophyte spread intensities during the post-monsoon season indicated independence of nutrient loads in the lake water. Full article

Clouds affect the assimilation of microwave data from satellites and therefore the detection of clouds is important under both clear sky and cloudy conditions. We introduce a new cloud detection method based on the assimilation of data from the advanced microwave sounder unit A (AMSU-A) and the microwave humidity sounder (MHS) into the global and regional assimilation and prediction system (GRAPES) and use forecast experiments to evaluate its impact. The new cloud detection method can retain more observational data than the current method in GRAPES, thereby improving the assimilation of AMSU-A data. Verification of the method showed that, by improving the forecast of the lower-level air temperature and geopotential height, the new cloud detection method improved the forecast of the track of two typhoons. The forecast of a large-scale weather system in GRAPES was also improved by the new method in the later period of the forecast. Full article

Intertidal bars are common features on meso-and macro-tidal sandy beaches with low to moderate wave energy environments. Understanding their morphodynamics is, hence, crucial for enhancing our knowledge on beach processes which is beneficial for coastal management. However, most studies have been limited by assessing bar systems two-dimensionally and typically over the short-term. Morphology and dynamics of an intertidal bar system in a macro-tidal environment have been investigated using bi-annual LiDAR topographic surveys over a period of seven years and along 3.2 km at Groenendijk beach (Belgium). The detected bars demonstrate that a morphology of an intertidal bar is permanently on the beach. However, these individual features are dynamic and highly mobile over the course of half a year. The mean height and width of the bars were 1.1 and 82 m, respectively. The highest, steepest, and asymmetric features were found on the upper beach, while they were least developed in the lower intertidal zone. The bars were evenly distributed over the entire intertidal beach, but the largest concentration observed around the mean sea level indicated the occurrence at preferential locations. The most significant net change across the beach occurs between the mean sea level and mean-high-water neap which corroborates with the profile mobility pattern. The seasonal variability of the bar morphology is moderately related to the seasonally driven changes in storm and wave regime forcings. However, a distinct relationship may be inhibited by the complex combination of forcing-, relaxation time- and feedback-dominated response. This work conducted from bi-annual LiDAR surveys has provided an unprecedented insight into the complex spatial organization of intertidal bars as well as their variability in time from seasonal to annual scale. Full article

Lossy compression is widely used to decrease the size of multichannel remote sensing data. Alongside this positive effect, lossy compression may lead to a negative outcome as making worse image classification. Thus, if possible, lossy compression should be carried out carefully, controlling the quality of compressed images. In this paper, a dependence between classification accuracy of maximum likelihood and neural network classifiers applied to three-channel test and real-life images and quality of compressed images characterized by standard and visual quality metrics is studied. The following is demonstrated. First, a classification accuracy starts to decrease faster when image quality due to compression ratio increasing reaches a distortion visibility threshold. Second, the classes with a wider distribution of features start to “take pixels” from classes with narrower distributions of features. Third, a classification accuracy might depend essentially on the training methodology, i.e., whether features are determined from original data or compressed images. Finally, the drawbacks of pixel-wise classification are shown and some recommendations on how to improve classification accuracy are given. Full article

Deep learning has become an effective method for hyperspectral image classification. However, the high band correlation and data volume associated with airborne hyperspectral images, and the insufficiency of training samples, present challenges to the application of deep learning in airborne image classification. Prototypical networks are practical deep learning networks that have demonstrated effectiveness in handling small-sample classification. In this study, an improved prototypical network is proposed (by adding L2 regularization to the convolutional layer and dropout to the maximum pooling layer) to address the problem of overfitting in small-sample classification. The proposed network has an optimal sample window for classification, and the window size is related to the area and distribution of the study area. After performing dimensionality reduction using principal component analysis, the time required for training using hyperspectral images shortened significantly, and the test accuracy increased drastically. Furthermore, when the size of the sample window was 27 × 27 after dimensionality reduction, the overall accuracy of forest species classification was 98.53%, and the Kappa coefficient was 0.9838. Therefore, by using an improved prototypical network with a sample window of an appropriate size, the network yielded desirable classification results, thereby demonstrating its suitability for the fine classification and mapping of tree species. Full article

The time-series state and parameter estimations of indoor localization continue to be a topic of growing importance. To deal with the nonlinear and positive skewed non-Gaussian dynamic of indoor CSS–TOF (Chirp-Spread-Spectrum Time-of-Flight) ranging measurements and position estimations, Monte Carlo Bayesian smoothers are promising as involving the past, present, and future observations. However, the main problems are how to derive trackable smoothing recursions and to avoid the degeneracy of particle-based smoothed distributions. To incorporate the backward smoothing density propagation with the forward probability recursion efficiently, we propose a lightweight Marginalized Particle Smoother (MPS) for nonlinear and non-Gaussian errors mitigation. The performance of the position prediction, filtering, and smoothing are investigated in real-world experiments carried out with vehicle on-board sensors. Results demonstrate the proposed smoother enables a great tool by reducing temporal and spatial errors of mobile trajectories, with the cost of a few sequence delay and a small number of particles. Therefore, MPS outperforms the filtering and smoothing methods under weak assumptions, low computation, and memory requirements. In the view that the sampled trajectories stay numerically stable, the MPS form is validated to be applicable for time-series position tracking. Full article

Pavement markings play a critical role in reducing crashes and improving safety on public roads. As road pavements age, maintenance work for safety purposes becomes critical. However, inspecting all pavement markings at the right time is very challenging due to the lack of available human resources. This study was conducted to develop an automated condition analysis framework for pavement markings using machine learning technology. The proposed framework consists of three modules: a data processing module, a pavement marking detection module, and a visibility analysis module. The framework was validated through a case study of pavement markings training data sets in the U.S. It was found that the detection model of the framework was very precise, which means most of the identified pavement markings were correctly classified. In addition, in the proposed framework, visibility was confirmed as an important factor of driver safety and maintenance, and visibility standards for pavement markings were defined. Full article

In recent years, different deep learning techniques were applied to segment aerial and satellite images. Nevertheless, state of the art techniques for land cover segmentation does not provide accurate results to be used in real applications. This is a problem faced by institutions and companies that want to replace time-consuming and exhausting human work with AI technology. In this work, we propose a method that combines deep learning with a human-in-the-loop strategy to achieve expert-level results at a low cost. We use a neural network to segment the images. In parallel, another network is used to measure uncertainty for predicted pixels. Finally, we combine these neural networks with a human-in-the-loop approach to produce correct predictions as if developed by human photointerpreters. Applying this methodology shows that we can increase the accuracy of land cover segmentation tasks while decreasing human intervention. Full article

The application of remote sensing techniques for disaster management often requires rapid damage assessment to support decision-making for post-treatment activities. As the on-demand acquisition of pre-event very high-resolution (VHR) images is typically limited, PlanetScope (PS) offers daily images of global coverage, thereby providing favorable opportunities to obtain high-resolution pre-event images. In this study, we propose an unsupervised change detection framework that uses post-fire VHR images with pre-fire PS data to facilitate the assessment of wildfire damage. To minimize the time and cost of human intervention, the entire process was executed in an unsupervised manner from image selection to change detection. First, to select clear pre-fire PS images, a blur kernel was adopted for the blind and automatic evaluation of local image quality. Subsequently, pseudo-training data were automatically generated from contextual features regardless of the statistical distribution of the data, whereas spectral and textural features were employed in the change detection procedure to fully exploit the properties of different features. The proposed method was validated in a case study of the 2019 Gangwon wildfire in South Korea, using post-fire GeoEye-1 (GE-1) and pre-fire PS images. The experimental results verified the effectiveness of the proposed change detection method, achieving an overall accuracy of over 99% with low false alarm rate (FAR), which is comparable to the accuracy level of the supervised approach. The proposed unsupervised framework accomplished efficient wildfire damage assessment without any prior information by utilizing the multiple features from multi-sensor bi-temporal images. Full article

Mangrove forests play an important role in maintaining water quality, mitigating climate change impacts, and providing a wide range of ecosystem services. Effective identification of mangrove species using remote-sensing images remains a challenge. The combinations of multi-source remote-sensing datasets (with different spectral/spatial resolution) are beneficial to the improvement of mangrove tree species discrimination. In this paper, various combinations of remote-sensing datasets including Sentinel-1 dual-polarimetric synthetic aperture radar (SAR), Sentinel-2 multispectral, and Gaofen-3 full-polarimetric SAR data were used to classify the mangrove communities in Xuan Thuy National Park, Vietnam. The mixture of mangrove communities consisting of small and shrub mangrove patches is generally difficult to separate using low/medium spatial resolution. To alleviate this problem, we propose to use label distribution learning (LDL) to provide the probabilistic mapping of tree species, including Sonneratia caseolaris (SC), Kandelia obovata (KO), Aegiceras corniculatum (AC), Rhizophora stylosa (RS), and Avicennia marina (AM). The experimental results show that the best classification performance was achieved by an integration of Sentinel-2 and Gaofen-3 datasets, demonstrating that full-polarimetric Gaofen-3 data is superior to the dual-polarimetric Sentinel-1 data for mapping mangrove tree species in the tropics. Full article

Stereo photogrammetric survey used to be used to extract the height of buildings, then to convert the height to number of stories through certain rules to estimate the number of stories of buildings by means of satellite remote sensing. In contrast, we propose a new method using deep learning to estimate the number of stories of buildings from monocular optical satellite image end to end in this paper. To the best of our knowledge, this is the first attempt to directly estimate the number of stories of buildings from monocular satellite images. Specifically, in the proposed method, we extend a classic object detection network, i.e., Mask R-CNN, by adding a new head to predict the number of stories of detected buildings from satellite images. GF-2 images from nine cities in China are used to validate the effectiveness of the proposed methods. The result of experiment show that the mean absolute error of prediction on buildings whose stories between 1–7, 8–20, and above 20 are 1.329, 3.546, and 8.317, respectively, which indicate that our method has possible application potentials in low-rise buildings, but the accuracy in middle-rise and high-rise buildings needs to be further improved. Full article

The well-known triangle method in optical/thermal remote sensing, its construction, uncertainties, and the significance of its products are first discussed. These topics are then followed by an outline of how the method can be implemented operationally for practical use, including a suggestion for constructing a dynamic crop moisture index. Full article

Unmanned aerial systems (UAS) are cost-effective, flexible and offer a wide range of applications. If equipped with optical sensors, orthophotos with very high spatial resolution can be retrieved using photogrammetric processing. The use of these images in multi-temporal analysis and the combination with spatial data imposes high demands on their spatial accuracy. This georeferencing accuracy of UAS orthomosaics is generally expressed as the checkpoint error. However, the checkpoint error alone gives no information about the reproducibility of the photogrammetrical compilation of orthomosaics. This study optimizes the geolocation of UAS orthomosaics time series and evaluates their reproducibility. A correlation analysis of repeatedly computed orthomosaics with identical parameters revealed a reproducibility of 99% in a grassland and 75% in a forest area. Between time steps, the corresponding positional errors of digitized objects lie between 0.07 m in the grassland and 0.3 m in the forest canopy. The novel methods were integrated into a processing workflow to enhance the traceability and increase the quality of UAS remote sensing. Full article

A project was constructed to integrate remotely sensed data from multiple sensors and platforms to characterize range of ecosystem characteristics in the Peace–Athabasca Delta in Northern Alberta, Canada. The objective of this project was to provide a framework for the processing of multisensor data to extract ecosystem information describing complex deltaic wetland environments. The data used in this study was based on a passive satellite-based earth observation multispectral sensor (Sentinel-2) and airborne discrete light detection and ranging (LiDAR). The data processing strategy adopted here allowed us to employ a data mining approach to grouping of the input variables into ecologically meaningful clusters. Using this approach, we described not only the reflective characteristics of the cover, but also ascribe vertical and horizontal structure, thereby differentiating spectrally similar, but ecologically distinct, ground features. This methodology provides a framework for assessing the impact of ecosystems on radiance, as measured by Earth observing systems, where it forms the basis for sampling and analysis. This final point will be the focus of future work. Full article

More and more scholars are committed to light detection and ranging (LiDAR) as a roadside sensor to obtain traffic flow data. Filtering and clustering are common methods to extract pedestrians and vehicles from point clouds. This kind of method ignores the impact of environmental information on traffic. The segmentation process is a crucial part of detailed scene understanding, which could be especially helpful for locating, recognizing, and classifying objects in certain scenarios. However, there are few studies on the segmentation of low-channel (16 channels in this paper) roadside 3D LiDAR. This paper presents a novel segmentation (slice-based) method for point clouds of roadside LiDAR. The proposed method can be divided into two parts: the instance segmentation part and semantic segmentation part. The part of the instance segmentation of point cloud is based on the regional growth method, and we proposed a seed point generation method for low-channel LiDAR data. Furthermore, we optimized the instance segmentation effect under occlusion. The part of semantic segmentation of a point cloud is realized by classifying and labeling the objects obtained by instance segmentation. For labeling static objects, we represented and classified a certain object through the related features derived from its slices. For labeling moving objects, we proposed a recurrent neural network (RNN)-based model, of which the accuracy could be up to 98.7%. The result implies that the slice-based method can obtain a good segmentation effect and the slice has good potential for point cloud segmentation. Full article

High-resolution laser scans from unmanned aerial vehicles (UAV) provide a highly detailed description of tree structure at the level of fine branches. Apart from ultrahigh spatial resolution, unmanned aerial laser scanning (ULS) can also provide high temporal resolution due to its operability and flexibility during data acquisition. We examined the phenomenon of bending branches of dead trees during one year from ULS multi-temporal data. In a multi-temporal series of three ULS datasets, we detected a synchronized reversible change in the inclination angles of the branches of 43 dead trees in a stand of blue spruce (Picea pungens Engelm.). The observed phenomenon has important consequences for both tree physiology and forest remote sensing (RS). First, the inclination angle of branches plays a crucial role in solar radiation interception and thus influences the total photosynthetic gain. The ability of a tree to change the branch position has important ecophysiological consequences, including better competitiveness across the site. Branch shifting in dead trees could be regarded as evidence of functional mycorrhizal interconnections via roots between live and dead trees. Second, we show that the detected movement results in a significant change in several point cloud metrics often utilized for deriving forest inventory parameters, both in the area-based approach (ABA) and individual tree detection approaches, which can affect the prediction of forest variables. To help quantify its impact, we used point cloud metrics of automatically segmented individual trees to build a generalized linear model to classify trees with and without the observed morphological changes. The model was applied to a validation set and correctly identified 86% of trees that displayed branch movement, as recorded by a human observer. The ULS allows for the study of this phenomenon across large areas, not only at individual tree levels. Full article

Remote sensing can be applied to optimize efficiency in pest detection, as an insect sampling tool. This efficiency can result in more precise recommendations for decision making in pest management. Pest detection with remote sensing is often feasible because plant biotic stress caused by herbivory triggers a defensive physiological response in plants, which generally results in changes to leaf reflectance. Therefore, the key objective of this study was to use hyperspectral proximal remote sensing and gas exchange parameters to characterize peanut leaf responses to herbivory by Stegasta bosqueella (Lepidoptera: Gelechiidae) and Spodoptera cosmioides (Lepidoptera: Noctuidae), two major pests in South American peanut (Arachis hypogaea) production. The experiment was conducted in a randomized complete block design with a 2 × 3 factorial scheme (two lepidopterous species and 3 categories of injury). The injury treatments were: (1) natural infestation by third instars of S. bosqueella, (2) natural infestation by third instars of S. cosmioides, and (3) simulation of injury with scissors to mimic larval injury. We verified that peanut leaf reflectance is different between herbivory by the two larval species, but similar among real and simulated defoliation. Similarly, we observed differences in photosynthetic rate, stomatal conductance, transpiration, and photosynthetic water use efficiency only between species but not between real and simulated larval defoliation. Our results provide information that is essential for the development of sampling and economic thresholds of S. bosqueella and S. cosmioides on the peanut. Full article

Quantifying forest fires remain a challenging task for the implementation of public policies aimed to mitigate climate change. In this paper, we propose a new method to provide an annual burned area map of Mato Grosso State located in the Brazilian Amazon region, taking advantage of the high spatial and temporal resolution sensors. The method consists of generating the vegetation, soil, and shade fraction images by applying the Linear Spectral Mixing Model (LSMM) to the Landsat-8 OLI (Operational Land Imager), PROBA-V (Project for On-Board Autonomy–Vegetation), and Suomi NPP-VIIRS (National Polar-Orbiting Partnership-Visible Infrared Imaging Radiometer Suite) datasets. The shade fraction images highlight the burned areas, in which values are represented by low reflectance of ground targets, and the mapping was performed using an unsupervised classifier. Burned areas were evaluated in terms of land use and land cover classes over the Amazon, Cerrado and Pantanal biomes in the Mato Grosso State. Our results showed that most of the burned areas occurred in non-forested areas (66.57%) and old deforestation (21.54%). However, burned areas over forestlands (11.03%), causing forest degradation, reached more than double compared with burned areas identified in consolidated croplands (5.32%). The results obtained were validated using the Sentinel-2 data and compared with active fire data and existing global burned areas products, such as the MODIS (Moderate Resolution Imaging Spectroradiometer product) MCD64A1 and MCD45A1, and Fire CCI (ESA Climate Change Initiative) products. Although there is a good visual agreement among the analyzed products, the areas estimated were quite different. Our results presented correlation of 51% with Sentinel-2 and agreement of r² = 0.31, r² = 0.29, and r² = 0.43 with MCD64A1, MCD45A1, and Fire CCI products, respectively. However, considering the active fire data, it was achieved the better performance between active fire presence and burn mapping (92%). The proposed method provided a general perspective about the patterns of fire in various biomes of Mato Grosso State, Brazil, that are important for the environmental studies, specially related to fire severity, regeneration, and greenhouse gas emissions. Full article

The ability to quantify green vegetation across space and over time is useful for studying grassland health and function and improving our understanding of the impact of land use and climate change on grasslands. Directly measuring the fraction of green vegetation cover is labor-intensive and thus only practical on relatively smaller experimental sites. Remote sensing vegetation indices, as a commonly-used method for large-area vegetation mapping, were found to produce inconsistent accuracies when mapping green vegetation in semi-arid grasslands, largely due to mixed pixels including both photosynthetic and non-photosynthetic material. The spectral mixture approach has the potential to map the fraction of green vegetation cover in a heterogeneous landscape, thanks to its ability to decompose a spectral signal from a mixed pixel into a set of fractional abundances. In this study, a time series of fractional green vegetation cover (FGVC) from 1999 to 2014 is estimated using the spectral mixture approach for a semi-arid mixed grassland, which represents a typical threatened, species-rich habitat in Central Canada. The shape of pixel clouds in each of the Landsat images is used to identify three major image endmembers (green vegetation, bare soil/litter, and water/shadow) for automated image spectral unmixing. The FGVC derived through the spectral mixture approach correlates highly with field observations (R² = 0.86). Change in the FGVC over the study period was also mapped, and green vegetation in badlands and uplands is found to experience a slight increase, while vegetation in riparian zone shows a decrease. Only a small portion of the study area is undergoing significant changes, which is likely attributable to climate variability, bison reintroduction, and wildfire. The results of this study suggest that the automated spectral unmixing approach is promising, and the time series of medium-resolution images is capable of identifying changes in green vegetation cover in semi-arid grasslands. Further research should investigate driving forces for areas undergoing significant changes. Full article

A fully connected “deep” neural network algorithm with the Community Radiative Transfer Model (FCDN_CRTM) is proposed to explore the efficiency and accuracy of reproducing the Visible Infrared Imaging Radiometer Suite (VIIRS) radiances in five thermal emission M (TEB/M) bands. The model was trained and tested in the nighttime global ocean clear-sky domain, in which the VIIRS observation minus CRTM (O-M) biases have been well validated in recent years. The atmosphere profile from the European Centre for Medium-Range Weather Forecasts (ECMWF) and sea surface temperature (SST) from the Canadian Meteorology Centre (CMC) were used as FCDN_CRTM input, and the CRTM-simulated brightness temperatures (BTs) were defined as labels. Six dispersion days’ data from 2019 to 2020 were selected to train the FCDN_CRTM, and the clear-sky pixels were identified by an enhanced FCDN clear-sky mask (FCDN_CSM) model, which was demonstrated in Part 1. The trained model was then employed to predict CRTM BTs, which were further validated with the CRTM BTs and the VIIRS sensor data record (SDR) for both efficiency and accuracy. With iterative refinement of the model design and careful treatment of the input data, the agreement between the FCDN_CRTM and the CRTM was generally good, including the satellite zenith angle and column water vapor dependencies. The mean biases of the FCDN_CRTM minus CRTM (F-C) were typically ~0.01 K for all five bands, and the high accuracy persisted during the whole analysis period. Moreover, the standard deviations (STDs) were generally less than 0.1 K and were consistent for approximately half a year, before they significantly degraded. The validation with VIIRS SDR data revealed that both the predicted mean biases and the STD of the VIIRS observation minus FCDN_CRTM (V-F) were comparable with the VIIRS minus direct CRTM simulation (V-C). Meanwhile, both V-F and V-C exhibited consistent global geophysical and statistical distribution, as well as stable long-term performance. Furthermore, the FCDN_CRTM processing time was more than 40 times faster than CRTM simulation. The highly efficient, accurate, and stable performances indicate that the FCDN_CRTM is a potential solution for global and real-time monitoring of sensor observation minus model simulation, particularly for high-resolution sensors. Full article

Effective 3D tree reconstruction based on point clouds from terrestrial Light Detection and Ranging (LiDAR) scans (TLS) has been widely recognized as a critical technology in forestry and ecology modeling. The major advantages of using TLS lie in its rapidly and automatically capturing tree information at millimeter level, providing massive high-density data. In addition, TLS 3D tree reconstruction allows for occlusions and complex structures from the derived point cloud of trees to be obtained. In this paper, an automatic tree skeleton extraction approach based on multi-view slicing is proposed to improve the TLS 3D tree reconstruction, which borrowed the idea from the medical imaging technology of X-ray computed tomography. Firstly, we extracted the precise trunk center and then cut the point cloud of the tree into slices. Next, the skeleton from each slice was generated using the kernel mean shift and principal component analysis algorithms. Accordingly, these isolated skeletons were smoothed and morphologically synthetized. Finally, the validation in point clouds of two trees acquired from multi-view TLS further demonstrated the potential of the proposed framework in efficiently dealing with TLS point cloud data. Full article

Although the characteristics of biomass burning events and the ambient ecosystem determine emitted smoke composition, the conditions that modulate the partitioning of black carbon (BC) and brown carbon (BrC) formation are not well understood, nor are the spatial or temporal frequency of factors driving smoke particle evolution, such as hydration, coagulation, and oxidation, all of which impact smoke radiative forcing. In situ data from surface observation sites and aircraft field campaigns offer deep insight into the optical, chemical, and microphysical traits of biomass burning (BB) smoke aerosols, such as single scattering albedo (SSA) and size distribution, but cannot by themselves provide robust statistical characterization of both emitted and evolved particles. Data from the NASA Earth Observing System’s Multi-Angle Imaging SpectroRadiometer (MISR) instrument can provide at least a partial picture of BB particle properties and their evolution downwind, once properly validated. Here we use in situ data from the joint NOAA/NASA 2019 Fire Influence on Regional to Global Environments Experiment-Air Quality (FIREX-AQ) field campaign to assess the strengths and limitations of MISR-derived constraints on particle size, shape, light-absorption, and its spectral slope, as well as plume height and associated wind vectors. Based on the satellite observations, we also offer inferences about aging mechanisms effecting downwind particle evolution, such as gravitational settling, oxidation, secondary particle formation, and the combination of particle aggregation and condensational growth. This work builds upon our previous study, adding confidence to our interpretation of the remote-sensing data based on an expanded suite of in situ measurements for validation. The satellite and in situ measurements offer similar characterizations of particle property evolution as a function of smoke age for the 06 August Williams Flats Fire, and most of the key differences in particle size and absorption can be attributed to differences in sampling and changes in the plume geometry between sampling times. Whereas the aircraft data provide validation for the MISR retrievals, the satellite data offer a spatially continuous mapping of particle properties over the plume, which helps identify trends in particle property downwind evolution that are ambiguous in the sparsely sampled aircraft transects. The MISR data record is more than two decades long, offering future opportunities to study regional wildfire plume behavior statistically, where aircraft data are limited or entirely lacking. Full article

The San Luis Potosi metropolitan area has suffered considerable damage from land subsidence over the past decades, which has become visible since 1990. This paper seeks to evaluate the effects of groundwater withdrawal on land subsidence in the San Luis Potosi Valley and the development of surface faults due to the differential compaction of sediments. For this purpose, we applied the Coherent Pixels Technique (CPT), a Persistent Scatterer Interferometry (PSI) technique, using 112 Sentinel-1 acquisitions from October 2014 to November 2019 to estimate the deformation rate. The results revealed that the deformation areas in the municipality of Soledad de Graciano Sánchez mostly exhibit subsidence values between −1.5 and −3.5 cm/year; whereas in San Luis Potosi these values are between −1.8 and −4.2 cm/year. The PSI results were validated by five Global Navigation Satellite System (GNSS) benchmarks available, providing a data correlation between the results obtained with both techniques of 0.986. This validation suggests that interferometric derived deformations agree well with results obtained from GNSS data. The strong relationship between trace fault, land subsidence,e and groundwater extraction suggests that groundwater withdrawal is resulting in subsidence induced faulting, which follows the pattern of structural faults buried by sediments. Full article

The paper presents the range and applications of thematic tasks for ultra-high spatial resolution data from small unmanned aerial vehicles (UAVs) in the integral system of environmental multi-platform and multi-scaled monitoring of Lake Sevan, which is one of the greatest freshwater lakes in Eurasia. From the 1930s, it had been subjected to human-driven changing of the water level with associated and currently exacerbated environmental issues. We elaborated the specific techniques of optical and thermal surveys for the different coastal sites and phenomena in study. UAV-derived optical imagery and thermal stream were processed by a Structure-from-Motion algorithm to create digital surface models (DSMs) and ortho-imagery for several key sites. UAV imagery were used as additional sources of detailed spatial data under large-scale mapping of current land-use and point sources of water pollution in the coastal zone, and a main data source on environmental violations, especially sewage discharge or illegal landfills. The revealed present-day coastal types were mapped at a large scale, and the net changes of shoreline position and rates of shore erosion were calculated on multi-temporal UAV data using modified Hausdorff’s distance. Based on highly-detailed DSMs, we revealed the areas and objects at risk of flooding under the projected water level rise to 1903.5 m along the west coasts of Minor Sevan being the most popular recreational area. We indicated that the structural and environmental state of marsh coasts and coastal wetlands as potential sources of lake eutrophication and associated algal blooms could be more efficiently studied under thermal UAV surveys than optical ones. We proposed to consider UAV surveys as a necessary intermediary between ground data and satellite imagery with different spatial resolutions for the complex environmental monitoring of the coastal area and water body of Lake Sevan as a whole. Full article

Large-scale spatial databases contain information of different objects in the public domain and are of great importance for many stakeholders. These data are not only used to inventory the different assets of the public domain but also for project planning, construction design, and to create prediction models for disaster management or transportation. The use of mobile mapping systems instead of traditional surveying techniques for the data acquisition of these datasets is growing. However, while some objects can be (semi)automatically extracted, the mapping of manhole covers is still primarily done manually. In this work, we present a fully automatic manhole cover detection method to extract and accurately determine the position of manhole covers from mobile mapping point cloud data. Our method rasterizes the point cloud data into ground images with three channels: intensity value, minimum height and height variance. These images are processed by a transfer learned fully convolutional neural network to generate the spatial classification map. This map is then fed to a simplified class activation mapping (CAM) location algorithm to predict the center position of each manhole cover. The work assesses the influence of different backbone architectures (AlexNet, VGG-16, Inception-v3 and ResNet-101) and that of the geometric information channels in the ground image when commonly only the intensity channel is used. Our experiments show that the most consistent architecture is VGG-16, achieving a recall, precision and F₂-score of 0.973, 0.973 and 0.973, respectively, in terms of detection performance. In terms of location performance, our approach achieves a horizontal 95% confidence interval of 16.5 cm using the VGG-16 architecture. Full article

Based on the hypothesis of the Manhattan world, we propose a tightly-coupled monocular visual-inertial odometry (VIO) system that combines structural features with point features and can run on a mobile phone in real-time. The back-end optimization is based on the sliding window method to improve computing efficiency. As the Manhattan world is abundant in the man-made environment, this regular world can use structural features to encode the orthogonality and parallelism concealed in the building to eliminate the accumulated rotation error. We define a structural feature as an orthogonal basis composed of three orthogonal vanishing points in the Manhattan world. Meanwhile, to extract structural features in real-time on the mobile phone, we propose a fast structural feature extraction method based on the known vertical dominant direction. Our experiments on the public datasets and self-collected dataset show that our system is superior to most existing open-source systems, especially in the situations where the images are texture-less, dark, and blurry. Full article

Historical land cover maps are of high importance for scientists and policy makers studying the dynamic character of land cover change in the Sudano-Sahel, including anthropogenic and climatological drivers. Despite its relevance, an accurate high resolution record of historical land cover maps is currently lacking over the Sudano-Sahel. In this study, 30 m resolution historically consistent land cover and cover fraction maps are provided over the Sudano-Sahel for the period 1986–2015. These land cover/cover fraction maps are achieved based on the Landsat archive preprocessed on Google Earth Engine and a random forest classification/regression model, while historical consistency is achieved using the hidden Markov model. Using these historical maps, a multitude of variability in the dynamic Sudano-Sahel region over the past 30 years is revealed. On the one hand, Sahel-wide cropland expansion and the re-greening of the Sahel is observed in the discrete land cover classification. On the other hand, subtle changes such as forest degradation are detected based on the cover fraction maps. Additionally, exploiting the 30 m spatial resolution, fine-scale changes, such as smallholder or subsistence farming, can be detected. The historical land cover/cover fraction maps presented in this study are made available via an open-access platform. Full article