Depth Dataset Research Articles

DTS-Depth: Real-Time Single-Image Depth Estimation Using Depth-to-Space Image Construction.

As most of the recent high-resolution depth-estimation algorithms are computationally so expensive that they cannot work in real time, the common solution is using a low-resolution input image to reduce the computational complexity. We propose a different approach, an efficient and real-time convolutional neural network-based depth-estimation algorithm using a single high-resolution image as the input. The proposed method efficiently constructs a high-resolution depth map using a small encoding architecture and eliminates the need for a decoder, which is typically used in the encoder–decoder architectures employed for depth estimation. The proposed algorithm adopts a modified MobileNetV2 architecture, which is a lightweight architecture, to estimate the depth information through the depth-to-space image construction, which is generally employed in image super-resolution. As a result, it realizes fast frame processing and can predict a high-accuracy depth in real time. We train and test our method on the challenging KITTI, Cityscapes, and NYUV2 depth datasets. The proposed method achieves low relative absolute error (0.028 for KITTI, 0.167 for CITYSCAPES, and 0.069 for NYUV2) while working at speed reaching 48 frames per second on a GPU and 20 frames per second on a CPU for high-resolution test images. We compare our method with the state-of-the-art methods on depth estimation, showing that our method outperforms those methods. However, the architecture is less complex and works in real time.

LGHAP: the Long-term Gap-free High-resolution Air Pollutant concentration dataset, derived via tensor-flow-based multimodal data fusion

Abstract. Developing a big data analytics framework for generating the Long-term Gap-free High-resolution Air Pollutant concentration dataset (abbreviated as LGHAP) is of great significance for environmental management and Earth system science analysis. By synergistically integrating multimodal aerosol data acquired from diverse sources via a tensor-flow-based data fusion method, a gap-free aerosol optical depth (AOD) dataset with a daily 1 km resolution covering the period of 2000–2020 in China was generated. Specifically, data gaps in daily AOD imageries from the Moderate Resolution Imaging Spectroradiometer (MODIS) aboard Terra were reconstructed based on a set of AOD data tensors acquired from diverse satellites, numerical analysis, and in situ air quality measurements via integrative efforts of spatial pattern recognition for high-dimensional gridded image analysis and knowledge transfer in statistical data mining. To our knowledge, this is the first long-term gap-free high-resolution AOD dataset in China, from which spatially contiguous PM2.5 and PM10 concentrations were then estimated using an ensemble learning approach. Ground validation results indicate that the LGHAP AOD data are in good agreement with in situ AOD observations from the Aerosol Robotic Network (AERONET), with an R of 0.91 and RMSE equaling 0.21. Meanwhile, PM2.5 and PM10 estimations also agreed well with ground measurements, with R values of 0.95 and 0.94 and RMSEs of 12.03 and 19.56 µg m−3, respectively. The LGHAP provides a suite of long-term gap-free gridded maps with a high resolution to better examine aerosol changes in China over the past 2 decades, from which three major variation periods of haze pollution in China were revealed. Additionally, the proportion of the population exposed to unhealthy PM2.5 increased from 50.60 % in 2000 to 63.81 % in 2014 across China, which was then reduced drastically to 34.03 % in 2020. Overall, the generated LGHAP dataset has great potential to trigger multidisciplinary applications in Earth observations, climate change, public health, ecosystem assessment, and environmental management. The daily resolution AOD, PM2.5, and PM10 datasets are publicly available at https://doi.org/10.5281/zenodo.5652257 (Bai et al., 2021a), https://doi.org/10.5281/zenodo.5652265 (Bai et al., 2021b), and https://doi.org/10.5281/zenodo.5652263 (Bai et al., 2021c), respectively. Monthly and annual datasets can be acquired from https://doi.org/10.5281/zenodo.5655797 (Bai et al., 2021d) and https://doi.org/10.5281/zenodo.5655807 (Bai et al., 2021e), respectively. Python, MATLAB, R, and IDL codes are also provided to help users read and visualize these data.

Modelling of Greek Lakes Water Quality Using Earth Observation in the Framework of the Water Framework Directive (WFD)

Given the great importance of lakes in Earth’s environment and human life, continuous water quality (WQ) monitoring within the frame of the Water Framework Directive (WFD) is the most crucial aspect for lake management. In this study, Earth Observation (EO) data from Landsat 7 Enhanced Thematic Mapper Plus (ETM+) and Landsat 8 Operational Land Imager (OLI) sensors have been combined with co-orbital in situ measurements from 50 lakes located in Greece with the main objective of delivering robust WQ assessment models. Correlation analysis among in situ co-orbital WQ data (Chlorophylla, Secchi depths, Total phosphorus-TP-) contributed to distinguishing their inter-relationships and improving the WQ models’ accuracy. Subsequently, stepwise multiple regression analysis (MLR) of the available TP and Secchi depth datasets was implemented to explore the potential to establish optimal quantitative models regardless of lake characteristics. Then, further MLR analysis concerning whether the lakes are natural or artificial was conducted with the basic aim of generating different remote sensing derived models for different types of lakes, while their combination was further utilized to assess their trophic status. Correlation matrix results showed a high and positive relationship between TP and Chlorophyll-a (0.85), whereas high negative relationships were found between Secchi depth with TP (−0.84) and Chlorophyll-a (−0.83). MLRs among Landsat data and Secchi depths resulted in 3 optimal models concerning the assessment of Secchi depth of all lakes (Secchigeneral; R = 0.78; RMSE = 0.24 m), natural (Secchinatural; R = 0.95; RMSE = 0.14 m) and artificial (Secchiartificial; R = 0.62; RMSE = 0.1 m), with reliable accuracy. Study findings showed that TP-related MLR analyses failed to deliver a statistically acceptable model for the reservoirs; nevertheless, they delivered a robust TPgeneral (R = 0.71; RMSE = 1.41 mg/L) and TPnatural model (R = 0.93; RMSE = 1.43 mg/L). Subsequently, trophic status classification was conducted herein, calculating Carlson’s Trophic State Index (TSI) initially throughout all lakes and then oriented toward natural-only and artificial-only lakes. Those three types of TSI (general, natural, artificial) were calculated based on previously published satellite-derived Chlorophyll-a (Chl-a) assessment models and the hereby specially designed WQ models (Secchi depth, TP). The higher deviation of satellite-derived TSI values in relation to in situ ones was detected in reservoirs and shallower lakes (mean depth < 5 m), indicating noticeable divergences among natural and artificial lakes. All in all, the study findings provide important support toward the perpetual WQ monitoring and trophic status prediction of Greek lakes and, by extension, their sustainable management, particularly in cases when ground truth data is limited.

Deeper by the Dozen: Diving into a Database of 17,675 Depths for U.S. Lakes and Reservoirs

AbstractDepth is a fundamental property of lakes, essential for understanding and quantifying a range of biological, chemical, and physical processes of individual lakes as well as the collective functioning of the millions of lakes across the globe. Despite this importance, lake depth is rarely available for large numbers of lakes across the broad scales of regions and continents. We describe a new open‐access dataset, LAGOS‐US DEPTH, which contains 17,675 maximum depths and 6,137 mean depths for lakes in the conterminous United States. These data represent one of the largest compilations of lake depths in the world and are connected to other data products through the LAGOS‐US research platform. Here, we describe characteristics of lake maximum depth across the conterminous United States and identify gaps in data coverage that we encourage other researchers to fill by linking their own depth datasets for lakes within the LAGOS‐US spatial footprint. Extending this open‐access effort to include other regions and countries across the globe to build a more comprehensive and representative database of lake depth would better position scientists to quantify and articulate the critical roles that lakes play globally in biogeochemical cycling, maintaining biodiversity, and in maintaining the many ecosystem services that lakes provide.

Edge Detection-Based Feature Extraction for the Systems of Activity Recognition.

Human activity recognition (HAR) is a fascinating and significant challenging task. Generally, the accuracy of HAR systems relies on the best features from the input frames. Mostly, the activity frames have the hostile noisy conditions that cannot be handled by most of the existing edge operators. In this paper, we have designed an adoptive feature extraction method based on edge detection for HAR systems. The proposed method calculates the direction of the edges under the presence of nonmaximum conquest. The benefits are in ease that depends upon the modest procedures, and the extension possibility is to determine other types of features. Normally, it is practical to extract extra low-level information in the form of features when determining the shapes and to get the appropriate information, the additional cultured shape detection procedure is utilized or discarded. Basically, this method enlarges the percentage of the product of the signal-to-noise ratio (SNR) and the highest isolation along with localization. During the processing of the frames, again some edges are demonstrated as a footstep function; the proposed approach might give better performance than other operators. The appropriate information is extracted to form feature vector, which further be fed to the classifier for activity recognition. We assess the performance of the proposed edge-based feature extraction method under the depth dataset having thirteen various kinds of actions in a comprehensive experimental setup.

A Geometry-Discrete Minimum Reflectance Aerosol Retrieval Algorithm (GeoMRA) for Geostationary Meteorological Satellite Over Heterogeneous Surfaces

High-frequency aerosol observation from new-generation geostationary meteorological satellite is capable to capture and monitor the spatiotemporal dynamic variation of aerosols, which is of vital significance to environmental research and climate studies. Due to the diversity and complexity of land cover, it is a challenge to retrieve aerosol properties with high accuracy over land especially over heterogeneous land surfaces. In this study, a Geometry-Discrete Minimum Reflectance Aerosol Retrieval Algorithm (GeoMRA) has been proposed to retrieve 10-min high temporal resolution aerosol optical depth (AOD) datasets for geostationary Himawari-8 AHI sensor, aiming at providing universal bidirectional reflectance distribution function (BRDF) descriptions for different land surfaces with different heterogeneous extent. The AOD retrievals from GeoMRA demonstrate good consistency against the ground-based AERONET measurements in the East Asia from 2015 to 2020, with a correlation coefficient (R) of 0.883 and approximately 65.6% of matchups falling within the expected error envelope of ±(0.05 + 15%). Intercomparison between the GeoMRA retrieved AOD and other operational AOD products shows that the GeoMRA AOD retrievals, which generally possess similar spatial distribution and accuracy as MODIS AOD products, have better performances than the Japan Aerospace Exploration Agency (JAXA) AOD products by providing more accurate AOD retrievals with higher spatial coverage. Moreover, the AOD bias analyses further demonstrate the robustness of GeoMRA algorithm, and an extreme haze event shows that the continuous GeoMRA AOD images illustrate smoother temporal variations than JAXA AOD products, demonstrating its efficacy and reliability in capturing the process of haze transport and monitoring the continuous spatiotemporal variation of aerosol. The above results suggest the considerable accuracy of GeoMRA algorithm for scientific application requirement, and demonstrate the robustness of proposed BRDF scheme in describing heterogeneous surfaces with diverse reflectance distribution.

A Robust Movement Quantification Algorithm of Hyperactivity Detection for ADHD Children Based on 3D Depth Images.

Attention deficit hyperactivity disorder (ADHD) is one of the most common childhood mental disorders. Hyperactivity is a typical symptom of ADHD in children. Clinicians diagnose this symptom by evaluating the children's activities based on subjective rating scales and clinical experience. In this work, an objective system is proposed to quantify the movements of children with ADHD automatically. This system presents a new movement detection and quantification method based on depth images. A novel salient object extraction method is proposed to segment body regions. In movement detection, we explore a new local search algorithm to detect any potential motions of children based on three newly designed evaluation metrics. In the movement quantification, two parameters are investigated to quantify the participation degree and the displacements of each body part in the movements. This system is tested by a depth dataset of children with ADHD. The movement detection results of this dataset mainly range from 91.0% to 95.0%. The movement quantification results of children are consistent with the clinical observations. The public MSR Action 3D dataset is tested to validate the performance of this system.

Towards Monocular Neural Facial Depth Estimation: Past, Present, and Future

This article contains all of the information needed to conduct a study on monocular facial depth estimation problems. A brief literature review and applications on facial depth map research were offered first, followed by a comprehensive evaluation of publicly available facial depth datasets and widely used loss functions. The key properties and characteristics of each facial depth map dataset are described and evaluated. Furthermore, facial depth maps loss functions are briefly discussed, which will make it easier to train neural facial depth models on a variety of datasets for both short- and long-range depth maps. The network’s design and components are essential, but its effectiveness is largely determined by how it is trained, which necessitates a large dataset and a suitable loss function. Implementation details of how neural depth networks work and their corresponding evaluation matrices are presented and explained. In addition, an SoA neural model for facial depth estimation is proposed, along with a detailed comparison evaluation and, where feasible, direct comparison of facial depth estimation methods to serve as a foundation for a proposed model that is utilized. The model employed shows better performance compared with current state-of-the-art methods when tested across four datasets. The new loss function used in the proposed method helps the network to learn the facial regions resulting in an accurate depth prediction. The network is trained on synthetic human facial depth datasets whereas for validation purposes real as well as synthetic facial images are used. The results prove that the trained network outperforms current state-of-the-art networks performances, thus setting up a new baseline method for facial depth estimations.

Bidirectional Multiscale Refinement Network for Crisp Edge Detection

With the development of deep convolution neural networks (CNNs), contour detection has made great progress. Some contour detectors based on CNNs have better performance than human beings on standard benchmarks. However, it is easier for CNNs to learn the similar features of adjacent pixels, and the number of background pixels and edge pixels in the input training sample is highly imbalanced. Therefore, the prediction edge by the edge detector based on CNNs is thick and requires post-processing to obtain crisp edges. Accordingly, we introduce a novel parallel attention model and a novel loss function that combines cross-entropy and dice loss through the use of adaptive coefficients, and propose a novel bidirectional multiscale refinement network (BMRN) that stacks multiple refinement modules in order to achieve richer feature representation. The experimental results show that our method has better performance than the state-of-the-art on BSDS500 (ODS F-score of 0.828), NYUDv2 depth datasets (ODS F-score of 0.778) and Multi-Cue dataset (ODS F-score 0.905(0.002)).

Depth Map Recovery Based on a Unified Depth Boundary Distortion Model.

Depth maps acquired by either physical sensors or learning methods are often seriously distorted due to boundary distortion problems, including missing, fake, and misaligned boundaries (compared with RGB images). An RGB-guided depth map recovery method is proposed in this paper to recover true boundaries in seriously distorted depth maps. Therefore, a unified model is first developed to observe all these kinds of distorted boundaries in depth maps. Observing distorted boundaries is equivalent to identifying erroneous regions in distorted depth maps, because depth boundaries are essentially formed by contiguous regions with different intensities. Then, erroneous regions are identified by separately extracting local structures of RGB image and depth map with Gaussian kernels and comparing their similarity on the basis of the SSIM index. A depth map recovery method is then proposed on the basis of the unified model. This method recovers true depth boundaries by iteratively identifying and correcting erroneous regions in recovered depth map based on the unified model and a weighted median filter. Because RGB image generally includes additional textural contents compared with depth maps, texture-copy artifacts problem is further addressed in the proposed method by restricting the model works around depth boundaries in each iteration. Extensive experiments are conducted on five RGB-depth datasets including depth map recovery, depth super-resolution, depth estimation enhancement, and depth completion enhancement. The results demonstrate that the proposed method considerably improves both the quantitative and visual qualities of recovered depth maps in comparison with fifteen competitive methods. Most object boundaries in recovered depth maps are corrected accurately, and kept sharply and well aligned with the ones in RGB images.

Evaluation of snow depth and snow cover represented by multiple datasets over the Tianshan Mountains: Remote sensing, reanalysis, and simulation

AbstractMountain snowpacks play important roles in water resource and ecological system. However, existing snow depth products show great uncertainties across the Tianshan Mountains, Central Asia. This study evaluated and compared four snow depth datasets over the Tianshan Mountains, including snow depth datasets from ERA5, ERA5‐Land, passive microwave, as well as a dynamically downscaled simulation by Weather Research and Forecasting (WRF) model. The snow depth was evaluated against in situ observations while the snow cover extent was evaluated by interactive multisensor snow and ice mapping system (IMS) snow cover. Furthermore, the snow‐related metrics, such as annual mean snow depth and snow cover days, were compared among the four datasets. The results showed that the spatial patterns of snow‐related metrics were relatively consistent among datasets, although discrepancies existed in magnitude. Additionally, the temporal variations in snow‐related metrics depended on the dataset employed. The simulated snow depth from WRF got the lowest bias in daily snow depth value against the in situ observations (mean bias = 0.12 cm, root mean square error = 2.08 cm), additionally, it had the best performance in classifying correct snow grids compared with IMS (probability of detection = 0.766). It also outperformed in annual mean snow depth and snow cover days by 47.2 and 13.3% compared with ERA5‐Land snow depth. This study highlights the confidence in characterizing both the spatial pattern and temporal variations of snow depth products based on WRF model simulation.

Vogtareuth Rehab Depth Datasets: Benchmark for Marker-less Posture Estimation in Rehabilitation.

Posture estimation using a single depth camera has become a useful tool for analyzing movements in rehabilitation. Recent advances in posture estimation in computer vision research have been possible due to the availability of large-scale pose datasets. However, the complex postures involved in rehabilitation exercises are not represented in the existing benchmark depth datasets. To address this limitation, we propose two rehabilitation-specific pose datasets containing depth images and 2D pose information of patients, both adult and children, performing rehab exercises. We use a state-of-the-art marker-less posture estimation model which is trained on a non-rehab benchmark dataset. We evaluate it on our rehab datasets, and observe that the performance degrades significantly from non-rehab to rehab, highlighting the need for these datasets. We show that our dataset can be used to train pose models to detect rehab-specific complex postures. The datasets will be released for the benefit of the research community.

Single Image Haze Removal Based on transmission map estimation using Encoder-Decoder based deep learning architecture

Haze removal is an essential requirement in autonomous vehicle applications for identifying different objects on the road. Most of the available techniques are based on different constraints/priors. The important parameters required for recovering the ground truth from hazy image are transmission map and air light. In this paper, we proposed a learning-based Encoder-Decoder deep learning architecture for transmission map estimation. Based on the assumption that at least twenty percent of the outdoor image includes with sky region and hence airlight is calculated as average of the twenty percent brightest pixels of the image. These two parameters namely transmission map and airlight were applied in atmospheric scattering model for ground truth image recovery. In Encoder-Decoder architecture, Max pooling layer, dropout layer was used for feature learning and efficient generalization respectively. The proposed architecture was trained on different datasets like NYU Depth data set, FRIDA and RESIDE Dataset for better generalization on unseen data. Experimental results shows that the proposed method has shown better performance compared to the existing state of the art methods.

An insight to the cryospheric level in Mars: Case study from the Thaumasia Minor

The presence of a subsurface Martian cryosphere has been widely acknowledged. Rampart craters and outflow channels are thought to be the prominent geomorphic signatures in support of the presence of this cryospheric layer. Valley networks, on the other hand, are thought to be the signatures of precipitation, seasonal meltwater flow due to glacial melting and/or groundwater sapping. A rampart crater essentially has an asymmetric lobate-shaped ejecta blanket around it. In the present study area within Thaumasia Minor, situated near the equatorial region of Mars, rampart craters are present while outflow channels are absent. Therefore, the rampart craters are the only windows to locate the existence and extent of the cryospheric level in the area. It has been observed that these rampart craters remained unaffected by surface fluvial activities. Rampart Craters, both Single Layered Ejecta craters (SLE) and Multiple Layered Ejecta craters (MLE) present in Thaumasia Minor were identified, mapped and dated. Excavation depths were calculated (with respect to the areoid) for all craters of varied ages. The excavation depth data sets were used to draw statistical surfaces for MLE craters and SLE craters. It was concluded from the comparative analysis of the excavation depths (between the MLE and SLE craters situated in the relatively higher altitudes within TM) at different time intervals, the base of the Martian cryosphere was at greater depths prior to ~2Ga than it was around 0.5Ga in the study area. This suggests that within the study area the Martian cryosphere did evolve with time and our study of the excavation depths of the craters suggests that the cryosphere must have thinned out as time progressed.

Assimilating Cloud Optical Depth for Applications to Extreme Weather Events

AbstractThis paper reports the assimilation of cloud optical depth datasets into a variational data assimilation system to improve cloud ice, cloud water, rain, snow, and graupel analysis in extreme weather events for improving forecasts. A cloud optical depth forward operator was developed and implemented in the Space and Time Multiscale Analysis System (STMAS), a multiscale three-dimensional variational analysis system. Using this improved analysis system, the NOAA GOES-15 DCOMP (Daytime Cloud Optical and Microphysical Properties) cloud optical depth products were assimilated to improve the microphysical states. For an eight-day period of extreme weather events in September 2013 in Colorado, the United States, the impact of the cloud optical depth assimilation on the analysis results and forecasts was evaluated. The DCOMP products improved the cloud ice and cloud water predictions significantly in convective and lower levels. The DCOMP products also reduced errors in temperature and relative humidity data at the top (250–150 hPa) and bottom (850–700 hPa) layers. With the cloud ice improvement at higher layers, the DCOMP products provided better forecasts of cloud liquid at low layers (900–700 hPa), temperature and wind at all layers, and relative humidity at middle and bottom layers. Furthermore, for this extreme weather event, both equitable threat score (ETS) and bias were improved throughout the 12 h period, with the most significant improvement observed in the first 3 h. This study will raise the expectation of cloud optical depth product assimilation in operational applications.

Modeling Snow Depth and Snow Water Equivalent Distribution and Variation Characteristics in the Irtysh River Basin, China

Accurate simulation of snow cover process is of great significance to the study of climate change and the water cycle. In our study, the China Meteorological Forcing Dataset (CMFD) and ERA-Interim were used as driving data to simulate the dynamic changes in snow depth and snow water equivalent (SWE) in the Irtysh River Basin from 2000 to 2018 using the Noah-MP land surface model, and the simulation results were compared with the gridded dataset of snow depth at Chinese meteorological stations (GDSD), the long-term series of daily snow depth dataset in China (LSD), and China’s daily snow depth and snow water equivalent products (CSS). Before the simulation, we compared the combinations of four parameterizations schemes of Noah-MP model at the Kuwei site. The results show that the rainfall and snowfall (SNF) scheme mainly affects the snow accumulation process, while the surface layer drag coefficient (SFC), snow/soil temperature time (STC), and snow surface albedo (ALB) schemes mainly affect the melting process. The effect of STC on the simulation results was much higher than the other three schemes; when STC uses a fully implicit scheme, the error of simulated snow depth and snow water equivalent is much greater than that of a semi-implicit scheme. At the basin scale, the accuracy of snow depth modeled by using CMFD and ERA-Interim is higher than LSD and CSS snow depth based on microwave remote sensing. In years with high snow cover, LSD and CSS snow depth data are seriously underestimated. According to the results of model simulation, it is concluded that the snow depth and snow water equivalent in the north of the basin are higher than those in the south. The average snow depth, snow water equivalent, snow days, and the start time of snow accumulation (STSA) in the basin did not change significantly during the study period, but the end time of snow melting was significantly advanced.

Systematic Comparison of the Performances of De Novo Genome Assemblers for Oxford Nanopore Technology Reads From Piroplasm.

BackgroundEmerging long reads sequencing technology has greatly changed the landscape of whole-genome sequencing, enabling scientists to contribute to decoding the genetic information of non-model species. The sequences generated by PacBio or Oxford Nanopore Technology (ONT) be assembled de novo before further analyses. Some genome de novo assemblers have been developed to assemble long reads generated by ONT. The performance of these assemblers has not been completely investigated. However, genome assembly is still a challenging task.Methods and ResultsWe systematically evaluated the performance of nine de novo assemblers for ONT on different coverage depth datasets. Several metrics were measured to determine the performance of these tools, including N50 length, sequence coverage, runtime, easy operation, accuracy of genome and genomic completeness in varying depths of coverage. Based on the results of our assessments, the performances of these tools are summarized as follows: 1) Coverage depth has a significant effect on genome quality; 2) The level of contiguity of the assembled genome varies dramatically among different de novo tools; 3) The correctness of an assembled genome is closely related to the completeness of the genome. More than 30× nanopore data can be assembled into a relatively complete genome, the quality of which is highly dependent on the polishing using next generation sequencing data.ConclusionConsidering the results of our investigation, the advantage and disadvantage of each tool are summarized and guidelines of selecting assembly tools are provided under specific conditions.

Application of Topological Data Analysis to Multi-Resolution Matching of Aerosol Optical Depth Maps

Topological data analysis (TDA) combines concepts from algebraic topology, machine learning, statistics, and data science which allow us to study data in terms of their latent shape properties. Despite the use of TDA in a broad range of applications, from neuroscience to power systems to finance, the utility of TDA in Earth science applications is yet untapped. The current study aims to offer a new approach for analyzing multi-resolution Earth science datasets using the concept of data shape and associated intrinsic topological data characteristics. In particular, we develop a new topological approach to quantitatively compare two maps of geophysical variables at different spatial resolutions. We illustrate the proposed methodology by applying TDA to aerosol optical depth (AOD) datasets from the Goddard Earth Observing System, Version 5 (GEOS-5) model over the Middle East. Our results show that, contrary to the existing approaches, TDA allows for systematic and reliable comparison of spatial patterns from different observational and model datasets without regridding the datasets into common grids.

Spatial characterization of dust emission prone arid regions using feature extraction and predictive algorithms

Aeolian dust emission is a serious environmental hazard in central Iran. We attempted to map the dust emission prone (DEP) areas in this region of Iran using the most accurate model among the random forest (RF), conditional RF (CRF), parallel RF (PRF), and extremely randomized trees (ERT) models. These models were evaluated using the Taylor diagram, Nash Sutcliffe coefficient, and Kling–Gupta efficiency. The generated map of DEP areas was also validated based on an aerosols optical depth (AOD) dataset. The Shapely values were used to determine the contribution of factors controlling dust events in DEP areas. The high performance and reliability of the ERT model for mapping DEP territories were confirmed by both error assessment statistics and reclassified AOD map. Using the ERT-generated map, five dust generation susceptibility classes including very low (20.16%), low (19.99%), moderate (19.82%), high (24.11%), and very high (15.92%) were identified in the study region. Drought severity, solar radiation, soil moisture, geology, soil sand content, bulk density, vegetation cover, land use, and slope were detected as the key features controlling dust emissions in central Iran. These results are useful for developing programs to reduce dust emissions hazards in DEP areas, particularly in central Iran.

Comprehensive bathymetry and intertidal topography of the Amazon estuary

Abstract. The characterization of estuarine hydrodynamics primarily depends on knowledge of the bathymetry and topography. Here, we present the first comprehensive, high-resolution dataset of the topography and bathymetry of the Amazon River estuary, the world's largest estuary. Our product is based on an innovative approach combining spaceborne remote sensing data, an extensive and processed river depth dataset, and auxiliary data. Our goal with this mapping is to promote the database usage in studies that require this information, such as hydrodynamic modeling or geomorphological assessments. Our twofold approach considered 500 000 sounding points digitized from 19 nautical charts for bathymetry estimation, in conjunction with a state-of-the-art topographic dataset based on remote sensing, encompassing intertidal flats, riverbanks, and adjacent floodplains. Finally, our estimate can be accessed in a unified 30 m resolution regular grid referenced to the Earth Gravitational Model 2008 (EGM08), complemented both landward and seaward by land (Multi-Error-Removed Improved-Terrain digital elevation model, MERIT DEM) and ocean (General Bathymetric Chart of the Oceans version 2020, GEBCO_2020) topographic data. Extensive validation against independent and spatially distributed data, from an airborne lidar survey, from ICESat-2 altimetric satellite data, and from various in situ surveys, shows a typical vertical accuracy of 7.2 m (riverbed) and 1.2 m (non-vegetated intertidal floodplains). The dataset is available at https://doi.org/10.17632/3g6b5ynrdb.2 (Fassoni-Andrade et al., 2021).