Search

The COVID-19 pandemic has dramatically changed human daily life. To mitigate the pandemic’s impacts, different countries and regions implemented various policies to contain COVID-19 and residents showed diverse responses. These human responses in turn shaped the uneven spatial-temporal spread of COVID-19. Such human-pandemic interaction is complex, dynamic, and interconnected. Delineating the reciprocal effects between human society and pandemics is crucial for preparing for and managing future epidemics. Geospatial big data acquired through mobile applications and sensor networks have facilitated near-real-time tracking and assessment of human responses to the pandemic, enabling a surge in researching human-pandemic interactions. However, these investigations involve inconsistent data sources, human activity indicators, relationship detection models, and analysis methods, leading to a fragmented understanding of human-pandemic dynamics. To assess the current state of human-pandemic interactions research using geospatial big data, we conducted a synthesis study based on 67 selected publications between 25 March 2020, and 9 January 2023. We extracted information from each article across six categories, i.e. publication details, research context, research area and time, data, methodological framework, and results and conclusions. Results reveal that the influence of stay-at-home policies on mobility decrease varied regionally, showing limited effectiveness in Europe compared to the US. The positive correlations between human mobility and COVID-19 case rates evolved through time and were highest in the initial outbreak in 2020. Public awareness generally peaked prior to the peaks in COVID-19 cases, with varying intervals of 0 to 19.8 days observed across different countries. This study summarizes the research characteristics of selected articles and highlights the need for future research to spatially and temporally model the long-term, bidirectional causal relationships within human-pandemic systems to inform evidence-based, hyperlocal pandemic mitigation strategies.

Dynamic imaging of optical remote sensing satellites refers to the active acquisition of images while the satellite is maneuvering at a high angular velocity, which significantly enhances the efficiency and application value of remote sensing imagery. However, due to the influence of rapid maneuvering, the random error of star sensors significantly increases, resulting in a decrease in the geometric positioning accuracy of dynamic imaging remote sensing images. This paper proposes a dynamic fusion method for multisource attitude measurement data based on the noise adaptive estimation and bidirectional filter to achieve high-precision attitude determination and geometric positioning in dynamic imaging. Based on the measurement error model of star sensors, the weights of the star sensor and gyroscope are adaptively adjusted in multisource data fusion to reduce the impact of star sensor measurement errors on the gyroscope. Moreover, a bidirectional fusion filter that includes a low-velocity maneuvering stage is proposed to realize the optimal estimation of the satellite attitude parameter. The simulation data and onboard data of the Luojia3-01 (LJ3–01) satellite were tested to verify the effectiveness of the proposed method. The geometric positioning accuracy of the staring images of LJ3–01 improved from 10.048 m to 7.538 m. The registration accuracy of the sequential images improved from 3.568 pixels to 1.179 pixels. The proposed method can significantly improve the attitude determination accuracy and the geometric positioning accuracy of LJ3–01 satellite staring images. Moreover, for simulation data with various angular velocities, the attitude determination accuracies of the proposed method are better than 0.93”. The experimental results show that the proposed method can achieve high-precision attitude determination in dynamic imaging, reaching the accuracy in the traditional passive imaging.

Reservoir characterization is a vital task within the oil and gas industry, with the identification of lithofacies in subsurface formations being a fundamental aspect of this process. However, lithofacies identification in complex geological environments with high dimensions, such as the Lower Indus Basin in Pakistan, poses a notable challenge, especially when dealing with limited data. To address this issue, we propose four common data-driven machine learning approaches: multi-resolution graph-based clustering (MRGC), artificial neural networks (ANN), K-nearest neighbors (KNN), and self-organizing map (SOM). We utilized these proposed approaches to assess their performance in scenarios with varying core sample availability, specifically evaluating their effectiveness in identifying lithofacies within the Lower Goru formation of the middle Indus Basin. The study reveals that in scenarios with a limited number of core samples, MRGC is the preferred choice, while KNN or MRGC is more suitable for larger datasets. The results demonstrate the superior performance of MRGC and KNN in lithofacies identification within the specified geological environment, with SOM following closely behind, and ANN exhibiting comparatively lower efficacy. The accurate identification of lithofacies from the selected model is complemented by the application of the truncated Gaussian simulation method for facies modeling. Comparative results confirm the excellent agreement between the model identification of lithofacies from well logs and electro-facies obtained from the truncated Gaussian simulation electro-facies volume. This study highlights the crucial role of selecting the right machine learning approach for precise lithofacies identification and modeling in complex geological environments. The comparative analysis provides practitioners in the petroleum industry with insights into the strengths and limitations of each method, enhancing existing knowledge. In conclusion, this research emphasizes the significance of comprehensive research and method selection for advancing lithofacies identification in diverse formations or study areas, ultimately benefiting the broader field of subsurface characterization in the petroleum industry.

Challenges related to data integration and interoperability were raised recently under the auspice of the Urban Digital Twin (UDT). This new paradigm shows its potential to address current city challenges. However, to maximize its outcomes at the city scale, we should tackle the fundamental issues related to data integration. Indeed, various Digital Twin (DT) frameworks are developed in practice. Their implementations led to the identification of three main levels of data integration. The first level involves the extension of the data model to handle new information. The second level supports data by default, and the data needs to be transformed to meet the model requirements. The third level performs the integration at the front-end level with the help of system architectures. The aim of this work is to analyze, illustrate, and guide the effectiveness of different data integration approaches. This exploratory review unpacks the levels of integration according to the corresponding UDT lifecycle phases (i.e., creation, use, and update phases). It highlights the challenges and potentialities of data integration levels and offers the DT designer conceptual guidelines related to data integration. Furthermore, current and theoretical data integration scenarios are extracted and investigated, considering several types and sources of data. This research provides a comprehensive analytical framework for data integration within UDTs, where some of the current operational UDT are examined based on the various integration levels of life cycle data. While the state-of-the-art identifies data integration as a major challenge for the full implementation of UDT, it is not explored in depth, and the integration is only addressed from a case study-specific perspective, according to the data availability and the UDT requirement. Hence, this framework provides a generic and urban application-independent overview of the different levels of data integration based on the UDT lifecycle inspired by the Spatial Data Infrastructure lifecycle. This article provides first conceptual insights of data integration levels to build, use, and update UDT. However, from a practical perspective, the list of UDT initiatives used to illustrate the work is not exhaustive, and future initiatives should be documented. Furthermore, the current emphasis is on the creation and use phases of the lifecycle, which lacks a concrete illustration of the update phase. Indeed, it limits the practicability of the data integration levels in the maintenance phase.

The Central Plains Urban Agglomeration (CPUA) is a link of economic development to connect the eastern part and western part in China. Current research on urban agglomeration integration mainly uses urban properties’ data. This paper conducts an evaluation method for urban agglomeration integration based on multivariate big data. This method mainly applies eigenvector centrality to assess the integrated situation of the CPUA from four dimensions (internet connection, industrial economy, public service and coordinated governance). The data of this research mainly includes cell phone signaling data, Baidu index, industrial investment data and statistical data for planning. The main innovations and contributions of this research is that (i) on the theoretical aspect, this research proposed an index indicator evaluation system for integration of urban agglomerations based on Analytic Hierarchy Process (AHP) and expert rating. It contributes for the further development of regional integration and other related theories; (ii) on the practical aspect, this study, taking the CPUA as example, presents an assessment approach that uses multivariate big data to measure the current integrated situation of urban agglomeration. This method provides decision-making support for the development of urban agglomeration integration.

In the processing of Precise Point Positioning (PPP) data, the receiver clock is approached with nearly infinite uncertainty, rendering it difficult to fulfill the requirements of high-precision time frequency applications. Therefore, a receiver clock model is essential. In this study, we first analyze the “over-constraint” problem in the existing clock model and subsequently propose a new clock model, called the Adaptive Clock Constraint (ACC) model, which relies on a sliding window to update covariance and frequency characteristics parameters in real-time. To verify the robustness of the ACC model, three experiments were conducted, and the results show that the ACC model not only is suitable for different types of atomic clock stations but also has superior frequency stability and time transfer precision in contrast to the BIPM PPP, the IGS products and White Noise (WN) model results. Using the optical fiber results as a time reference, the STD of the time difference between the ACC model and optical fiber results is 0.13 ns and the frequency stability is 1.28 × 10−16 on average for one week, representing improvements of more than 10% and 15% compared with the BIPM PPP results.

Research vessels are typically equipped with multiple receivers for positioning and attitude measurement; however, there is no data interaction or model fusion to implement the Precise Point Positioning (PPP) for these receivers. Therefore, a Constrained PPP (CPPP) is established by using the baseline length and tropospheric constraints of two receivers to improve the vessel’s remote marine positioning performance. Based on two integrated Real-Time Kinematic (RTK) receivers, marine experiments are conducted at a distance of 300–600 km from land. Compared to the ground environment, the Root Mean Square error (RMS) of the multipath and the STandard Deviation (STD) of the carrier-to-noise ratio in the marine environment are increased by 2.87 and 2.6 times, respectively. The length constraints reduce the RMS of positioning in the East, North, and Up (ENU) directions by about 0.053 (67%), 0.020 (34%), and 0.054 m (34%), respectively, and also rapidly recover positioning after interruptions, achieving positioning with errors in the ENU-directions of 10, 15, and 20 cm, respectively, within 3 minutes. When the baseline length and tropospheric constraints are combined, with or without the addition of the Zenith Wet Delay bias (dZWD), the average STD can be reduced by about 0.060 m (43%) and the accuracy of the up-positioning can be significantly improved. The correlation of dZWD to the up-positioning deviation of du=−2.161*dZWD is obtained by simulation. Since the acquisition of dZWD depends on the PPP accuracy, it is recommended that dZWD be set to compensate for unmodeled receiver errors when the STD of the up-positioning is superior to 0.06 m.

Understanding the sentiments of social media posts can help health authorities respond to disease outbreaks, through a proxy measure of fear, confidence, and community compliance. Sentiment analysis identifies a pattern of emotion through the written word and assigns a positive, neutral, or negative value to it. As of February 2023, there were 677.7 million confirmed cases of coronavirus disease (COVID-19) and more than 6.7 million confirmed deaths. In this paper, around 170,000 COVID-19-related tweets were collected between September 2020 and January 2021 in the contiguous United States. Data preprocessing and exploratory investigation were completed for analysis of the collected dataset. Further, a novel and unified architecture called attention-based one-dimensional convolution with bidirectional long short-term memory layers (CNN-BiLSTM-ATT) is proposed to classify people’s sentiments as positive, neutral, and negative based on COVID-19-related tweets. In the CNN-BiLSTM-ATT model, the CNN layer can extract the low-level semantic features from textual data, and the BiLSTM layer can extract both the previous and future contextual representations. The attention module can improve the information focus from the outputted layer of the BiLSTM. The proposed method can extract both the local phrase representations and the global feature of sentences. Numerical experiments were conducted on COVID-19-related tweets using the proposed method and other baseline models to compare their performances. Our experimental results demonstrate that the CNN-BiLSTM-ATT model achieves an average accuracy of 95.16% and a macro-average F1-score of 95.12%, which outperforms the baseline models.

Tropospheric delay influences high-precision navigation positioning and precipitable water vapor retrieval with the Global Navigation Satellite System (GNSS). Existing Zenith Tropospheric Delay (ZTD) models often struggle to accurately capture the non-linear variations in tropospheric delay. Therefore, this study employs the coupled Particle Swarm Optimization (PSO) algorithm with the Genetic Algorithm Back Propagation (GABP) neural network, combined with ERA5 reanalysis meteorological data, to develop an optimized model (PSO-GABP) for ZTD in the Chinese mainland. Nevertheless, ZTD data at the target point are obtained through four different methods: the integration method, model method, and GPT3 models at varying resolutions (EZTD_P, EZTD_S, GPT3_1, and GPT3_5). The analysis reveals the following: (1) The Root Mean Square (RMS) errors of the ZTD values obtained through these different methods are 1.86 cm, 3.42 cm, 3.99 cm, and 4.09 cm, respectively, when verified against GNSS_ZTD data from 2016. The optimized model yields ZTD values with the RMS error of 0.98 cm, 1.96 cm, 2.34 cm, and 2.36 cm, representing improvements of 47.3%, 42.7%, 41.4%, and 42.3% compared to the pre-optimization results. These improvements are significant; (2) The predictive capability of the constructed ZTD model is evaluated using GNSS_ZTD data from 2019 as a reference. The PSO_EZTD_P model demonstrates excellent accuracy and practicality in the Chinese mainland. As a result, the tropospheric delay optimization model based on the PSO-GABP neural network can provide valuable references for real-time GNSS navigation positioning and precipitable water vapor detection in the Chinese mainland.

As the elderly population rises, the growth rate of age-related diseases such as Alzheimer’s disease and cognitive impairments increases. Wandering is one of the first and the most progressive and challenging behaviors; that manifest with certain patterns in the mobility behavior of the patients in the early stages of the disease. Timely diagnosis of wandering can prevent irreparable damages, including the risk of losing the patient, severe physical injuries caused by accidents, and even death. So far, numerous studies have focused on the development of wandering detection algorithms. Most of these mainly rely on two approaches of extracting features from patients’ trajectory history and estimating the path complexity. Motion signal processing methods have rarely been used in this area. An important consideration for these patients is the instability in their movement behaviors, which has received limited attention in previous research, leading to less compatibility of models with this feature. Therefore, this paper proposes an algorithm based on motion signal processing using the Short-time Fourier transform (STFT). This algorithm detects wandering patterns only by using the patient’s trajectory data and changes in their zero and non-zero frequency components. The efficiency of the proposed algorithm has been evaluated using the Geolife open-source dataset, considering the macro-average of metrics such as accuracy, precision, specificity, recall, and F-score, achieving respective values of 96.38%, 94.89%, 96.36%, 96.36%, and 95.58%. The results have validated the proposed algorithm’s strong performance in diagnosing wandering behavior, which, on one hand, helps prevent adverse consequences and, on the other hand, aids in the diagnosis and predicting the progression of the disease to severe Alzheimer’s stage.

Remote sensing images often need to be merged into a larger mosaic image to support analysis on large areas in many applications. However, the performance of the mosaic imagery may be severely restricted if there are many areas with cloud coverage or if these images used for merging have a long-time span. Therefore, this paper proposes a method of image selection for full coverage image (i.e. a mosaic image with no cloud-contaminated pixels) generation. Specifically, a novel High-Frequency-Aware (HFA)-Net based on Swin-Transformer for region quality grading is presented to provide a data basis for image selection. Spatiotemporal constraints are presented to optimize the image selection. In the temporal dimension, the shortest-time-span constraint shortens the time span of the selected images, obviously improving the timeliness of the image selection results (i.e. with a shorter time span). In the spatial dimension, a spatial continuity constraint is proposed to select data with better quality and larger area, thus improving the radiometric continuity of the results. Experiments on the GF-1 images indicate that the proposed method reduces the averages by 76.1% and 38.7% in terms of the shortest time span compared to the Improved Coverage-oriented Retrieval algorithm (MICR) and Retrieval Method based on Grid Compensation (RMGC) methods, respectively. Moreover, the proposed method also reduces the residual cloud amount by an average of 91.2%, 89.8%, and 83.4% when compared to the MICR, RMGC, and Pixel-based Time-series Synthesis Method (PTSM) methods, respectively.

Information on Land Use and Land Cover Map (LULCM) is essential for environment and socioeconomic applications. Such maps are generally derived from Multispectral Remote Sensing Images (MRSI) via classification. The classification process can be described as information flow from images to maps through a trained classifier. Characterizing the information flow is essential for understanding the classification mechanism, providing solutions that address such theoretical issues as “what is the maximum number of classes that can be classified from a given MRSI?” and “how much information gain can be obtained?” Consequently, two interesting questions naturally arise, i.e. (i) How can we characterize the information flow? and (ii) What is the mathematical form of the information flow? To answer these two questions, this study first hypothesizes that thermodynamic entropy is the appropriate measure of information for both MRSI and LULCM. This hypothesis is then supported by kinetic-theory-based experiments. Thereafter, upon such an entropy, a generalized Jarzynski equation is formulated to mathematically model the information flow, which contains such parameters as thermodynamic entropy of MRSI, thermodynamic entropy of LULCM, weighted F1-score (classification accuracy), and total number of classes. This generalized Jarzynski equation has been successfully validated by hypothesis-driven experiments where 694 Sentinel-2 images are classified into 10 classes by four classical classifiers. This study provides a way for linking thermodynamic laws and concepts to the characterization and understanding of information flow in land cover classification, opening a new door for constructing domain knowledge.

During the development of service-based software systems, Geospatial Service (GS) replacement is often performed, which requires the discovery of functionally similar services in service registries to replace failed services. Compared to real-time similarity computations, direct extraction of similar services from constructed similarity relationships can yield higher replacement efficiency. However, missing and inconsistent service-registry information impedes accurate similarity relationship construction. Here, we propose a Graph Neural Network (GNN)-based model for GS Similarity Relationship construction considering service descriptions and tags, which is named GSSR-GNN. As the sparsity of the service similarity relationship graph constructed based on labeled samples limits the information propagation ability, a graph augmentation method for similarity relationship construction among second-order neighbors is proposed. Considering the differences in the semantic-information feature distributions, such as the service descriptions and tags, a feed-forward neural network-based fusion method is designed to embed them into the same vector space. Pre-trained Bidirectional Encoder Representations from Transformers (BERT) and WordNet models are introduced to enhance the service-representation expressiveness. When an enhanced service representation is input to the GNN, the similarity is calculated and the service similarity relationship is obtained. Experimental results show that the proposed model constructs service similarity relationships with high precision, thus improving the service replacement efficiency and reducing the computational cost of service registry during service replacement.

In dendroclimatology, tree ring chronology is ordinarily established to reveal the fluctuation law of climate change on the interannual, interdecadal, and centennial scales. However, since traditional dendrochronology can only use one variable (tree ring width) to reflect environmentally related information, this causes the richer information recorded in the tree rings to be discarded. In this study, we examined the potential of hyperspectral chronological indices (shortened as “hyperspectral index/indices”) with samples collected in Shennongjia woodland in central China. The correlation analysis of the tree ring series on different samples indicated that hyperspectral indices outperform the traditional width index in chronology statistics including Signal-to-noise Ratio (SNR) and Expressed Population Signal (EPS). The reliability test shows that hyperspectral chronologies have more periods reaching the threshold of EPS or Subsample Signal Strength (SSS) > 0.85, which means that hyperspectral chronologies provide more reliable periods for accurate climate reconstruction. Based on this, chronologies built by the three dendroclimatic indices were used to reconstruct the average temperature changes in Shennongjia over the last 103 years. The reconstruction results indicate that in our study area, the traditional width index model failed the split-sample calibration test and exhibited a low reconstruction accuracy, while the hyperspectral index model has a higher explained variance of 46.4% (p

Pattern recognition is critical to map data handling and their applications. This study presents a model that combines the Shape Context (SC) descriptor and Graph Convolutional Neural Network (GCNN) to classify the patterns of interchanges, which are indispensable parts of urban road networks. In the SC-GCNN model, an interchange is modeled as a graph, wherein nodes and edges represent the interchange segments and their connections, respectively. Then, a novel SC descriptor is implemented to describe the contextual information of each interchange segment and serve as descriptive features of graph nodes. Finally, a GCNN is designed by combining graph convolution and pooling operations to process the constructed graphs and classify the interchange patterns. The SC-GCNN model was validated using interchange samples obtained from the road networks of 15 cities downloaded from OpenStreetMap. The classification accuracy was 87.06%, which was higher than that of the image-based AlexNet, GoogLeNet, and Random Forest models.

Cartographic sounding selection is a constraint-based bathymetric generalization process for identifying navigationally relevant soundings for nautical chart display. Electronic Navigational Charts (ENCs) are the premier maritime navigation medium and are produced according to international standards and distributed around the world. Cartographic generalization for ENCs is a major bottleneck in the chart creation and update process, where high volumes of data collected from constantly changing seafloor topographies require tedious examination. Moreover, these data are provided by multiple sources from various collection platforms at different levels of quality, further complicating the generalization process. Therefore, in this work, a comprehensive sounding selection algorithm is presented that focuses on safe navigation, leveraging both the Digital Surface Model (DSM) of multi-source bathymetry and the cartographic portrayal of the ENC. A taxonomy and hierarchy of soundings found on ENCs are defined and methods to identify these soundings are employed. Furthermore, the significant impact of depth contour generalization on sounding selection distribution is explored. Incorporating additional ENC bathymetric features (rocks, wrecks, and obstructions) affecting sounding distribution, calculating metrics from current chart products, and introducing procedures to correct cartographic constraint violations ensures a shoal-bias and mariner-readable output. This results in a selection that is near navigationally ready and complementary to the specific waterways of the area, contributing to the complete automation of the ENC creation and update process for safer maritime navigation.

The rich feature information contained in the diverse remote sensing data has also exhibited growing potential in the field of image classification. However, the processing of multi-feature data still grapples with the challenges posed by the “curse of dimensionality” and the high computational costs. This paper proposes a remote sensing feature parameter selection method. This method is based on the Gini index of a Random Forest (RF) classifier and employs a 10% threshold decision to identify the optimal combination of remote sensing feature parameters. First, spectral features, texture features, temperature features, elevation features, and principal component features are selected to create a stack of remote sensing images. Second, multiple sets of decision trees are established to cross-validate the contributions of various feature parameters. The feature rankings are determined based on the normalized mean of feature importance. Subsequently, a threshold isset to filter out remote sensing feature parameters that meet the criteria. Finally, an iterative parameter optimization process is carried out to obtain the optimal combination of remote sensing feature parameters. The Landsat 8 image covering Hangzhou Bay in eastern China and the Sentinel-2 remote sensing image of Yancheng Nature Reserve in Jiangsu, China were selected for experiments. The results show that the feature parameters of the remote sensing image screened by the method in this paper are representative, and the proposed method demonstrates strong adaptability and generalization performance in complex environments. The study has important guiding significance for regional spatial planning and sustainable development.

Accurate and efficient ship detection is crucial for ocean monitoring and management, especially in reefs and deep-sea, where fishing and illegal activities threaten sustainability of ecosystems. Obtaining the size of ships in reefs and deep-sea helps to identify ship types and to assess the impact of ships on marine ecosystems quantitatively. Ship detections were mainly applied at coast or river of the inland region using high spatial resolution remote sensing data due to its rich details and frequent coverage. However, the ships located in reefs and deep-sea regions were rarely studied because of price, and availability of high spatial resolution remote sensing data. Global covered medium-high resolution (10–30 m) remote sensing data (such as Sentinel-2) makes it possible to obtain the spatial-temporal distribution of ships, especially small ships. This study developed a deep learning ship detection algorithm – an enhanced Rotated-Ship Detector (RShipDet) to detect ships in reefs and deep-sea regions. RShipDet was applied to Nansha Islands based on two medium-high resolution ship detection datasets (Sentinel2-Ship and SDGSAT-Ship). These two datasets include various backgrounds of reefs and deep-sea, and complex scenarios such as cloud cover and parallel ships, adapting RShipDet to ship detection under complex circumstances in reefs and deep-sea. The results showed that: (1) Small gains: gains of 3.3% and 8.7% Average-Precision (AP) compared to Rotation-equivariant Detector (ReDet) and Faster-RCNN on Sentinel2-Ship dataset; (2) Strong generalization capabilities: 77.4% AP on SDGSAT-Ship dataset; (3) Better performance under complex conditions: RShipDet obtained more accurate ship detection results over regions with cloud cover, islands and reefs, deep-sea, and ports compared to other classical detectors. Our algorithm could be applied for better management of ocean resources and activities in reefs and deep-sea.

Accurate and complete road network extraction plays a critical role in urban planning, street navigation, and emergency response. At present, narrow roads are a main feature in most public road datasets. However, the continuity and boundary completeness of the extraction results for these narrow roads are relatively poor, due to their varied shapes, uneven spatial distribution, and the presence of various interfering elements. To address these issues, this study introduces a novel network, the Self-weighted Global Context Road Extraction Network (SWGE-Net), which integrates a dilate block and an improved coordinate attention mechanism to effectively capture the complex details and spatial information of narrow roads. Furthermore, most public road training datasets often lack labels for very narrow roads, this omission leads to poor extraction results for these roads in test datasets. In order to further improve the extraction capability for unlabeled, extremely narrow roads, this study introduces another network called the Multi-scale Information Fusion Road Extraction Network (MSIF-Net), which uses the same encoders as SWGE-Net and has a special module for merging information at different scales. This module, with a dilate block and pyramid pooling-based decoder, makes the network better at recognizing and combining features of different sizes. Experimental results indicate that SWGE-Net outperforms the baseline network with road IoU scores of 71.57% and 60.67% on the DeepGlobe and CHN6-CUG road datasets, respectively an improvement of 18.51% and 5.40%. Meanwhile, MSIF-Net not only exceeds the baseline in road IoU scores for both datasets, but also achieves the best performance in extracting unlabeled, extremely narrow roads in qualitative experiments.

High-quality Geographic Knowledge Graphs (GeoKGs) are highly anticipated for their potential to provide reliable semantic support in geographical knowledge reasoning, training Geographic Large Language Models (Geo-LLMs), enabling geographical recommendation, and facilitating various geospatial knowledge-driven tasks. However, there is a lack of a standardized quality assessment methodology and clearly defined evaluative indicators in the field of GeoKGs research. This research uses the Preferred Reporting Items for Systematic Reviews and Meta-Analyses (PRISMA) methodology to conduct a systematic review of literature and standards in the field of GeoKG in an effort to fill the gap. First, using the lifecycle theory as a guide, we outline and propose five groups including twenty assessment criteria and their accompanying calculation techniques for evaluating GeoKG quality. Then, expanding on this foundation, we present a streamlined evaluation scheme for GeoKGs that relies on just seven key measures, discussing their applicability, utility, and weight scheme in greater detail. After applying the GeoKG quality framework, we stated three key tasks emerge as priorities: the creation of specialized assessment tools, the formation of worldwide standards, and the building of large-scale, high-quality GeoKGs. We believe this thorough and systematic GeoKG quality assessment technique will help construct high-quality GeoKGs and promote GeoKGs as an engine for geo-intelligence applications including Geospatial Artificial Intelligence (GeoAI) systems, Sustainable Development Goals (SDGs) analyzers, and Virtual Geographic Environments (VGEs) models.

Hyperspectral datasets captured by airborne are one of the important data sources in the field of hyperspectral image fusion. However, the limited number of data samples often hinders the optimal performance of deep learning-based methods on these datasets. Domain adaptation is expected to alleviate the issue of data scarcity. However, there are two issues that need to be addressed in applying domain adaptation to hyperspectral image fusion, which are the heterogeneity and spatial degradation diversity of hyperspectral data. In this paper, we propose a domain adaptation hyperspectral image fusion network based on spatial-spectral domain separation. The model, constructed with three-dimensional convolutional layers, effectively addresses the challenge of hyperspectral data heterogeneity. Compared with 2D convolution, 3D convolution is able to consider both spatial and spectral dimensions and extract spatial-spectral features efficiently. Based on this, we design a domain-separation architecture to extract domain-invariant and domain-private features in the spatial-spectral domain. The architecture achieves domain adaptation by extracting domain-invariant features from both datasets to obtain the prior knowledge in the source dataset and apply it to the target dataset. Additionally, the spatial degradation of different datasets varies due to distinct shooting conditions during the acquisition. Therefore, the fusion algorithms should be robust to various degradation scenarios. To tackle this challenge, we design the Observation Module to predict degradation information and the Degradation Information Modulation Module to apply it to the input, thereby enhancing the network’s robustness. Experiments on various datasets demonstrate that our method is qualitatively and quantitatively superior to state-of-the-art methods.

To enhance the adaptability and application capability of the cloud detection model in different remote sensing satellite domains, unsupervised domain adaptation methods are employed to improve the model’s robustness and transferability. However, conducting fully unlabeled training in the target domain to be adapted may impose difficulty on further improving the accuracy. It is more practical to obtain a few labeled target data for domain adaptation. Additionally, the detection of complex cloud scenes remains a persistent challenge. To address these issues, an Active Domain Adaptation network for Cloud detection (ADAC) is proposed in this paper. This network employs active learning to select a small number of representative samples for annotation, facilitating the transfer of a source domain-trained model to the target domain. Moreover, a novel Generator (G) designed for cloud segmentation is developed, where G utilizes a progressive learning strategy by dividing the network into two stages to learn gradient information, guiding cloud boundary segmentation and enabling the distinction between cloud-like objects and clouds. Furthermore, G integrates Transformer and Convolutional Neural Network to address the issues of misclassifying thin clouds. The proposed method is validated on Landsat 8 and GF-2 datasets, representing the source and target domains, respectively. The experimental results demonstrate ADAC achieved a 4% improvement in the overall accuracy with only 5% labeled training samples in the target domain, achieving the effective adaptation performance in the GF-2 domain.

Augmented Reality (AR) offers new opportunities for Citizen Science (CS) projects regarding data visualization, data collection, and training of participants. Since limited research on the usage of AR in CS projects exists, an online survey is conducted in this study by reaching out to CS project managers to determine the extent of its current use. The survey can identify areas where CS project managers themselves see the greatest potential for AR in their projects and reasons that exist against the use of AR. A total of 53 CS project managers participated in the survey and shared their opinions and concerns. Of all participating CS projects, only three are currently using AR. However, 27 CS projects indicated that AR could be beneficial for their project. Especially projects with a geographic focus, in which participants are involved in the process of collecting spatial data, expressed this opinion. Particularly in the areas “data visualization” and “attraction/motivation of participants” the projects identified potential for AR. Arguments against the use of AR named by 23 CS projects include remote study areas, financial considerations, and the lack of a practical use case. This study shows initial trends regarding the use of AR in CS projects and highlights specific use cases for the application of AR.

The increasing availability of ubiquitous sensor data on the built environment holds great potential for a new generation of travel and mobility research. Bluetooth technology, for example, is already vastly used in vehicular transportation management solutions and services. Current studies discuss the potential of this emerging technology for pedestrian mobility research, but it has yet to be examined in a large urban setting. One of the main problems is detecting pedestrians from Bluetooth records since their behavior and movement patterns share similarities with other urban transportation modes. This study aims to accurately detect pedestrians using a network of 65 Bluetooth detectors located in Tel-Aviv, Israel, which record on average over 60,000 unique daily Bluetooth Media-Access-Control addresses. We propose a detection methodology that includes system calibration, effective travel time calculation, and classification by velocity that takes into consideration the probability of vehicular traffic jams. An evaluation of the proposed methodology presents a promising pedestrian detection accuracy rate of 89%. We showcase the results of pedestrian traffic analysis, together with a discussion on the data analysis challenges and limitations. To the best of our knowledge, this work is the first to analyze pedestrian records detection from a Bluetooth network employed in a dynamic urban environment setting.

There is a growing interest in leveraging LiDAR-generated forest Aboveground Biomass (LG-AGB) data as a reference to retrieve AGB from satellite observations. However, the biases arising from the upscaling process and the impact of the sampling strategy on model accuracy still need to be resolved. In this study, we first corrected the bias arising from upscaling the LG-AGB map to match the spatial resolution of Landsat observations. Subsequently, the stratified random sampling method was used to select training samples from the corrected LG-AGB map (cLG-AGB) for the Random Forest (RF) regression model. The RF model features were extracted from the Landsat observations and auxiliary data. The impact of strata numbers on model accuracy was explored during the sampling process. Finally, independent validation was conducted using in situ measurements. The results indicated that: (1) about 68% of the biases can be corrected in the up-scale transformation; (2) compared to no stratification, a three-strata model achieved a 6.5% improvement in AGB estimation accuracy while requiring a 37.8% reduction in sample size; (3) the black locust forest had a low saturation point at 60.52 ± 4.46 Mg/ha AGB and 72.4% AGB values were underestimated and the remaining were overestimated. In summary, our study provides a framework to harmonize near-surface LiDAR and satellite data for AGB estimation in plantation forest ecosystems with small patch sizes and fragmented distribution.

Leaving no one behind is a worldwide goal, but it is difficult to make policy to address this issue because we do not have a thorough knowledge of where poverty exists and in what forms due to lack of data, particularly in developing countries. Household interview surveys are the common way to collect such information, but conducting large-scale surveys frequently is difficult from the perspective of cost and time. Here, we show a novel method for estimating income levels of individual building in urban and peri-urban rural areas. The combination of high-resolution satellite imagery and household interview survey data obtained by visiting households on the ground makes it possible to estimate income levels at a detailed scale for the first time. These data are often handled in different academic disciplines and are rarely used in combination. Using the results, we can determine the number and location of poor people at the local scale. We can also identify areas with particularly high concentrations of poor people. This information enables planning and policy making for more effective poverty reduction and disaster prevention measures tailored to local conditions. Thus, the results of this study will help developing countries to achieve sustainable development.

The Precise Point Positioning-Real Time Kinematic (PPP-RTK) technique, which provides centimeter-level positioning with instantaneous ambiguity resolution, is considered as a potential tool for intelligent vehicle applications. However, its performance is restricted under complex urban conditions owing to intermittent signal interruptions and poor satellite geometries. Thus, a tightly coupled Multi-Frequency (MF) PPP-RTK/INS (Inertial Navigation System) model was developed with the objective of providing a stable and reliable positioning for the urban vehicle. In this model, the augmentation of INS information, third-frequency observations, precise atmospheric corrections, the fixed Extra-Wide Lane (EWL), and Wide-Lane (WL) ambiguities can be used to enhance the positioning performance of PPP-RTK. We designed urban vehicle experiments under different scenarios to validate the proposed method. The results show that PPP-RTK can be significantly improved for urban vehicle positioning by fusing the MF and INS. In urban areas, the solution availability with a horizontal positioning error within 10 cm was 96.1% for MFPPP-RTK/INS with a fixing percentage of 90.9%. Compared with the dual-frequency PPP-RTK solutions, the fixing percentage and solution availability in the MFPPP-RTK/INS was improved by 9.5% and 8.8%, respectively. Moreover, MFPPP-RTK/INS provides continuous and stable positioning and fast ambiguity recovery in GNSS-challenged environments. The MFPPP-RTK/INS could achieve a fast ambiguity re-fixing within 1 s after continuously crossing obstacles, whereas PPP-RTK could achieve the same in 10 s.

Artificial Intelligence (AI) Machine Learning (ML) technologies, particularly Deep Learning (DL), have demonstrated significant potential in the interpretation of Remote Sensing (RS) imagery, covering tasks such as scene classification, object detection, land-cover/land-use classification, change detection, and multi-view stereo reconstruction. Large-scale training samples are essential for ML/DL models to achieve optimal performance. However, the current organization of training samples is ad-hoc and vendor-specific, lacking an integrated approach that can effectively manage training samples from different vendors to meet the demands of various RS AI tasks. This article proposes a solution to address these challenges by designing and implementing LuoJiaSET, a large-scale training sample database system for intelligent interpretation of RS imagery. LuoJiaSET accommodates over five million training samples, providing support for cross-dataset queries and serving as a comprehensive training data store for RS AI model training and calibration. It overcomes challenges related to label semantic categories, structural heterogeneity in label representation, and interoperable data access.

BeiDou navigation satellite system with global coverage (BDS-3) has been fully operational since July 2020, currently providing the positioning, navigation and timing service together with regional BDS-2. In addition to the legacy signals of B1I and B3I, the BDS-3 also transmits several new signals such as BIC, B2a and B2b, which brings new opportunities for rapid ambiguity resolution (AR) of BDS precise point positioning (PPP). In this contribution, a multi-frequency (MF) rapid PPP-AR method with regional network augmentation was proposed. Firstly, BDS five-frequency observations were introduced into uncombined double-differenced models to retrieve regional augmentation corrections at the server. Thereafter, a cascade PPP-AR strategy using extra-wide-lane, wide-lane and narrow-lane ambiguity was employed at the user. Once ambiguities were fixed to integers, the phase correction accuracy could reach about 3 cm on average overall BDS frequencies in the network with inter-station distances of 100–200 km. Subsequently, the statistical results of seven-day simulated kinematic experiments showed that over 99% of epochs on average realized PPP-AR. Correspondingly, the positioning accuracy of the MF fixed solution reached 1.8, 1.9, 4.7 cm in the east, north and up components, respectively, improving by 5–15% compared with the dual-frequency scheme. Moreover, several vehicle-borne experiments under different urban scenarios were also conducted. Under an open-sky or a relatively open highway scene, the BDS-MF scheme similarly exhibited good performance, and over 98% of epochs achieved rapid PPP-AR with a positioning accuracy better than 3 cm. More encouragingly, for this BDS-challenged experiment with an average satellite number of 8.6, although only 72.06% of epochs were available due to serious signal blockages caused by overpass, tunnels or tall buildings, the horizontal positioning accuracy could still remain 7 cm on average.

As the number of high-density buildings has increased, the management of property with complex condominium ownership has become an ongoing challenge in property registration and management. The three-dimensional (3D) modeling of condominium ownership has emerged as an effective means of meeting this challenge and has attracted great attention from fields such as geographical information science, urban planning and management, and property administration. Much progress has been made in building 3D models of condominium ownership; however, existing studies are all on a case-by-case basis and have left some critical issues unsolved, such as vague ownership boundaries, spatial rights without physical counterparts, and the unfixed spatial extent. The purpose of this study is to construct a 3D building ownership model with multiple levels of detail in the context of Chinese law to overcome the defects of 3D models above. This 3D model is presented in a case study of China by subdividing ownership boundaries based on clarifying the internal structure of condominium ownership, embedding the apportionment mechanism, and integrating the semantics, attributes, and geometry associated with the physical and legal entity of the condominium. The proposed 3D model is implemented by extending Building Information Modeling (BIM) based on the Industry Foundation Classes (IFC) and inheriting legal information from Land Administration Domain Model (LADM). In this study, examples of condominium ownership from three real legal dispute cases in China are analyzed and tested. The study clearly demonstrates that the proposed model can provide a better cognitive understanding of the legal space of property by rendering unambiguous ownership boundaries and presenting the spatial internal structure of ownership, which offers solid technical support for dealing with property registration and many legal dispute cases about condominium ownership.

According to General Relativity Theory (GRT), by comparing the frequencies between two precise clocks at two different stations, the gravity potential (geopotential) difference between the two stations can be determined due to the gravity frequency shift effect. Here, we conduct a clock-transportation experiment for measuring geopotential differences based on frequency comparisons via satellite links between two remote hydrogen atomic clocks. Based on the net frequency shift between the two clocks in two different periods, the geopotential difference between stations of the Beijing 203 Institute Laboratory (BIL) and Luojiashan Time-frequency Station (LTS) is determined. Comparisons show that the experimental result deviated from the reference of Earth gravity model EGM2008 result by (38.5[Formula: see text]45.9) m in Orthometric Height (OH). The results are consistent with the frequency stabilities of the hydrogen clocks (at the level of [Formula: see text]) used in the experiment. With the rapid development of time and frequency science and technology, the approach discussed in this study for measuring the geopotential is prospective and thus, could have broad applications.

An accurate Modulation Transfer Function (MTF) is essential for Synthetic Aperture Radar (SAR) wave spectra retrieval. This study aimed to investigate the performance of a quad-polarized wave retrieval algorithm based on fully polarimetric SAR image data using the improved tilt MTF and considering the influence of wind speed. The tilt MTF is the key factor in the wave retrieval scheme from quad-polarized (Vertical–Vertical (VV), Horizontal–Horizontal (HH), Vertical–Horizontal (VH), and Horizontal–Vertical (HV)) SAR images. In this study, the waves were inverted from more than 1300 Gaofen-3 (GF-3) images acquired in quad-polarization strip mode with a spatial resolution of 16 m and a swath coverage of 50 km. The winds were retrieved using the Geophysical Model Function (GMF) C-band SAR model for Gaofen-3 (CSARMOD-GF), which is suitable for re-calibrated GF-3 images in VV-polarization. The comparison of the wind speed yielded a Root Mean Square Error (RMSE) of 1.73 m/s and a Correlation Coefficient (COR) of 0.94. The validation of the Significant Wave Height (SWH) simulated using the Waves Nearshore (SWAN) model against Haiyang-2B (HY-2B) altimeter data yielded an RMSE of 0.56 m and a COR of 0.87. The results reveal that the SAR-derived wind and SWAN-simulated SWH are suitable for analysis of SAR wave retrieval. The full polarimetric technique was applied to the collected images, and the statistical analysis yielded a RMSE of 0.51 m, a COR of 0.75, and a Scatter Index (SI) of 0.44 compared with the SWHs retrieved using the simulations from the SWAN model. The non-polarized contribution in the Normalized Radar Cross Section (NRCS; unit: dB) caused by wave breaking [Formula: see text] was calculated using a theoretical approach that employs the VV-polarized calibrated NRCS [Formula: see text] and HH-polarized calibrated NRCS. The effect of wave breaking on the SAR retrieval waves was studied. The bias (SAR-derived minus SWAN-simulated SWH) increased as the ([Formula: see text]/[Formula: see text]) ratio (>0.4) increased, and the accuracy improved when the ratio was less than 0.4. This behavior is reasonable since the wave breaking inevitably affects the tilt modulation. Therefore, wave breaking should be considered in SAR wave retrieval using the approach proposed in this paper under extreme sea states, such as typhoons and hurricanes.

Precise classification of Light Detection and Ranging (LiDAR) point cloud is a fundamental process in various applications, such as land cover mapping, forestry management, and autonomous driving. Due to the lack of spectral information, the existing research on single wavelength LiDAR classification is limited. Spectral information from images could address this limitation, but data fusion suffers from varying illumination conditions and the registration problem. A novel multispectral LiDAR successfully obtains spatial and spectral information as a brand-new data type, namely, multispectral point cloud, thereby improving classification performance. However, spatial and spectral information of multispectral LiDAR has been processed separately in previous studies, thereby possibly limiting the classification performance of multispectral LiDAR. To explore the potential of this new data type, the current spatial–spectral classification framework for multispectral LiDAR that includes four steps: (1) neighborhood selection, (2) feature extraction and selection, (3) classification, and (4) label smoothing. Three novel highlights were proposed in this spatial – spectral classification framework. (1) We improved the popular eigen entropy-based neighborhood selection by spectral angle match to extract a more precise neighborhood. (2) We evaluated the importance of geometric and spectral features to compare their contributions and selected the most important features to reduce feature redundancy. (3) We conducted spatial label smoothing by a conditional random field, accounting for the spatial and spectral information of the neighborhood points. The proposed method demonstrated by a multispectral LiDAR with three channels: 466 nm (blue), 527 nm (green), and 628 nm (red). Experimental results demonstrate the effectiveness of the proposed spatial – spectral classification framework. Moreover, this research takes advantages of the complementation of spatial and spectral information, which could benefit more precise neighborhood selection, more effective features, and satisfactory refinement of classification result. Finally, this study could serve as an inspiration for future efficient spatial–spectral process for multispectral point cloud.

Satellite Interferometric Synthetic Aperture Radar (InSAR) is widely used for topographic, geological and natural resource investigations. However, most of the existing InSAR studies of ground deformation are based on relatively short periods and single sensors. This paper introduces a new multi-sensor InSAR time series data fusion method for time-overlapping and time-interval datasets, to address cases when partial overlaps and/or temporal gaps exist. A new Power Exponential Knothe Model (PEKM) fits and fuses overlaps in the deformation curves, while a Long Short-Term Memory (LSTM) neural network predicts and fuses any temporal gaps in the series. Taking the city of Wuhan (China) as experiment area, COSMO-SkyMed (2011–2015), TerraSAR-X (2015–2019) and Sentinel-1 (2019–2021) SAR datasets were fused to map long-term surface deformation over the last decade. An independent 2011–2020 InSAR time series analysis based on 230 COSMO-SkyMed scenes was also used as reference for comparison. The correlation coefficient between the results of the fusion algorithm and the reference data is 0.87 in the time overlapping region and 0.97 in the time-interval dataset. The correlation coefficient of the overall results is 0.78, which fully demonstrates that the algorithm proposed in our paper achieves a similar trend as the reference deformation curve. The experimental results are consistent with existing studies of surface deformation at Wuhan, demonstrating the accuracy of the proposed new fusion method to provide robust time series for the analysis of long-term land subsidence mechanisms.

Poplar (PopulusL.) is one of the most widely distributed tree species planted in the plains of China and plays an important role in wood products and ecological services. Accurate estimation of poplar Growing Stock Volume (GSV) is crucial for better understanding the ecological functions and economic values in plain regions. However, the striped distribution feature of poplar forests in plain regions makes traditional grid-based GSV modeling methods highly uncertain. This research took Lixin County and Yongqiao District as case studies to examine the advantages of using object-based GSV modeling approach over the traditional grid-based approaches for poplar GSV estimation. The canopy height variables and density variables were extracted from airborne LIDAR-derived Canopy Height Model (CHM) data through different grid sizes and segmentation unit for constructing the poplar GSV estimation models using the linear regression. The results indicate that (1) Significantly linear relationships exist between GSV and height percentile variables; (2) The estimation accuracy in Lixin can be effectively improved by incorporating the CHM density variables into height variables, with the coefficient of determination (R2) increasing from 0.46 to 0.71 and Root Mean Square Error (RMSE) decreasing from 20.23 to 14.94 m3/ha when a grid-based approach was implemented at grid size of 26 m by 26 m (plot size). However, CHM density variables have no effect on estimation modeling in Yongqiao district. The patch sizes and shapes considerably affect the selection of modeling variables and accuracy of modeling prediction; (3) The object-based mapping approach outperforms the grid-based approach in solving the mixed plot problem. This is especially valuable in the study areas with striped forest distribution. This study shows that differences in poplar stand structure affect the selection of modeling variables and GSV modeling performance, and an object-based modeling approach is recommended for GSV estimation in the plain areas.

One of the major impacts of climate change in the agricultural sector relates to changes in the suitability of areas that are used for planting crops. Since peanut (Arachis hypogaea L.) is one of the most important sources of protein, an assessment of the potential shifts in peanut crop planting areas is critical. In this study, we evaluated the effects of climate change on the potential distribution of peanut crops in Australia. The current and potential future distributions of peanut crops were modeled using Species Distribution Models (SDMs) of CLIMatic indEX (CLIMEX). The future potential peanut crop distributions in Australia for 2030, 2050, 2070, and 2100 were modeled by employing CSIRO-Mk3.0 and MIROC-H Global Climate Models (GCMs) under SRES A2 climate change scenarios from CliMond 10’ database. The results indicated an increase in unsuitable areas for peanut cultivation in Australia throughout the projected years for the two GCMs. The CSIRO-Mk3.0 projection of unsuitable areas in 2100 was higher (i.e. 76% of the Australian continent) than the MIROC-H projection (i.e. 48% of the Australian continent). It was found that the projected increase in dry stress in the future could cause limitations in areas that are currently suitable for peanut crop cultivation. Looking into the future suitability of existing peanut cultivation areas, both GCMs agreed that some areas will become unsuitable, while they disagreed with the suitability of other areas. However, they agreed on the important point that only a small number of existing peanut cultivation areas would still be suitable in the future. Using CLIMEX, the present study has confirmed the effects of climate change on the shifts in areas suitable for peanut cultivation in the future, and thus may provide valuable information relevant to the long-term planning of peanut cultivation in Australia.

The use of virtual drilling technology can effectively accelerate the establishment process of 3D geological models and improve grid structure and visual performance. However, most existing virtual drilling prediction techniques mainly rely on traditional interpolation methods, which not only increase computational overhead but also lack sufficient automation. To address this problem, this study introduces an innovative virtual borehole prediction technology combined with a machine learning stacking strategy. This technology integrates Random Forest (RF), XGBoost, CatBoost, and LightGBM algorithms as basic models and improves prediction accuracy through stacked generalization technology. This study adopted a method of adding zero-thickness layers to unify stratigraphic sequences. The 3D position information of boreholes is used as model input, and the bottom height of boreholes at stratigraphic boundaries is used as the prediction target. Through a hierarchical training method using 85[Formula: see text] of borehole data for training and 15[Formula: see text] for verification, a regression prediction model for stratigraphic boundaries is established. The model is able to predict detailed stratigraphic sequences containing information on stratigraphic type and thickness to accurately simulate virtual boreholes. Research results show that the integrated model has excellent prediction performance, achieves efficient automated prediction, and provides a new solution for virtual drilling prediction.

The distribution of surface particulate matter (PM2.5) exhibits significant spatiotemporal patterns, especially with a spatial clustering effect. Therefore, resolving spatial characteristics is essential in the modeling process. This study proposes a space–time varying coefficients (STVC-LG) model by considering spatial effects from the perspective of eigenvector spatial filtering and incorporating spatial effects and temporal features into the LightGBM model to estimate ground PM2.5. A site-based cross-validation result of the estimated daily 1 km PM2.5 concentration in China from 2016 to 2020 shows that the proposed model offers high accuracy, an R2 of 0.88, and an RMSE of 12.21 μg/m3 (17% and 32% enhanced compared to the original LightGBM model). It uses a series of spatial eigenvectors to describe different spatial patterns. It then constructs spatial interaction terms by combining the eigenvectors and influencing variables, allowing the values of the variable to vary spatially with the eigenvectors. The obtained PM2.5, with a decreasing trend, had a clear distributional consistency with NO2 and SO2 according to the co-occurrence distribution maps, particularly in winter. In areas where high concentrations co-occur, both NO2 and SO2 concentrations are Granger-causing PM2.5 concentrations from a statistical perspective.

Both the physical features and social functions of urban green spaces (UGSs) are crucially important to the ecological and social benefits of urban residents. Increasing attention has been focused on exploring how UGS social functions affect the ecological and social benefits of urban residents, but the social functional classification of UGSs has rarely been studied, and related efficient classification methods are urgently needed. Thus, a novel methodological framework for accurately mapping UGS social functional zones was proposed by integrating remote sensing images, crowd-sourced geospatial data (i.e. point of interest data, the OpenStreetMap road network, and Baidu Map boundary), and a deep learning algorithm. A sequence of combination experiments and ablation experiments were designed for performance validation and for quantifying the contributions of individual crowd-sourced geospatial data to UGS social functional classification. The results showed that the proposed methodological framework can precisely and effectively map UGS social functional zones and that all kinds of crowd-sourced geospatial data contributed to improving the accuracy of UGS social functional classification. This study can assist planners and government departments in the rapid monitoring, effective management, and scientific planning of UGS social functional zones by providing accurate data sources and an effective mapping tool.

Forests are of vital importance in maintaining the balance of ecosystems, and accurate forest cover maps provide basic data for research. Existing forest cover products suffer from substantial discrepancies in forest definition, area estimation, statistical accuracy, and spatial consistency, complicating their use. This paper uses the Dempster-Shafer theory to create a precise forest cover map of China using forest datasets from 2020. The basic probability assignment (BPA) function calculation adopts a combination of global constraints and local adaptive approach. The experimental results reveal that the accuracy of the fused forest cover map (FFCM) is significantly higher than that of the reference maps, with 91.62% user accuracy, 91.61% producer accuracy, 91.61% F1 score, and 94.65% overall accuracy. The area of China’s forests in 2020 is estimated at 229.43 million ha. The higher-precision forest cover map provides reliable data for research and a reference for the use of existing products.

This article describes the forecasting system urbanAQF, which incorporates several developments to deal with the complexities of air pollution in cities, including the adaptation of high-resolution numerical weather prediction data to the urban canopy, the coupling with regional forecast data, and an interactive web service for public dissemination of urban air quality information. The system applies a unique bias correction algorithm that adjusts boundary conditions and traffic emissions to observations of the previous days. An evaluation of the air quality forecasts during 2021 for Hamburg, Germany, against a comprehensive dataset of the administrative monitoring network and meteorological data, demonstrated the system’s capability to describe space and time variations of NO2 and PM10. At traffic sites, the high number of missed alerts in relation to exceedance of the daily mean limit for NO2 indicates the need to improve the simulation of traffic emissions. The forecast of PM2.5 alerts was affected by the time lag of the automatic correction, leading to a low number of correct alerts. The overall performance for O3 was very good, despite frequent false alarms connected to the prediction of unstable atmospheric conditions. The urbanAQF system empowers policymakers to implement effective measures for improving air quality in cities.

ABSTRACTVirtual geographical scenes aim to naturally represent the real world and aid in comprehending geographic information. However, current virtual geographical scene modeling methods have problems detecting change information and low efficiency in dynamic modeling. Additionally, the modeling process lacks guidance from domain experts, resulting in poor modeling standardization. Therefore, this paper proposes a combined data-driven and knowledge-driven virtual geographical scene twin modeling method. We discuss the three-domain association geographical scene knowledge graph, change information detection network based on knowledge graph and deep learning, and knowledge-guided semantic modeling algorithms in detail. These methods enhance the ability of virtual geographical scenes to describe the changing real world. Furthermore, we select an urban bridge construction geographical scene with obvious change characteristics as a typical case, develop a prototype system, and conduct an experimental analysis. The results show that our method can fully and effectively utilize the geographical scene data and knowledge and improve the reusability of the knowledge. The average change detection accuracy in geographical scene information reaches 92.46%, and the dynamic modeling efficiency of virtual geographical twin scenes reaches 29.97 fps. Compared to other 3D modeling methods, the proposed method can represent the dynamic real world more timely, accurately, completely, and comprehensively.

ABSTRACTThe Medium Resolution Spectral Image (MERSI) is a MODIS-like sensor aboard Fengyun-3 satellite. The first version of MERSI aerosol algorithm has been developed based on MODIS dark target (DT) algorithm, with modified models for estimating surface reflectance and an adjusted inland water masking method to release haze aerosols. This study applies MERSI DT algorithm to the global observations from the upgraded MERSI sensor (MERSI-II) on Fengyun-3D. And then, the Aerosol Optical Depth (AOD) results from the year of 2019–2020 are validated against the Aerosol Robotic Network (AERONET) data. In addition, analyses of the spatial distribution and error characteristics of MODIS and MERSI-II retrievals are presented. The overall validation demonstrates that MERSI-II retrievals perform well globally, with a correlation coefficient of 0.877 and 67.1% of matchups within the Expected Error envelope of ± (0.05 + 0.2τ), which are close to the statistic metrics of MODIS products. In addition, MERSI-II and MODIS AODs exhibit similar error trends and error dependence. Moreover, the similar global distribution characteristics of the two AODs are revealed in the retrieval performance at site and regional scales, as well as in the analysis of monthly averages. These findings indicate the success of the ported MERSI algorithm.

ABSTRACTAmidst rapid global urbanization, comprehending urban area growth (UAG) dynamics is vital for urban planning and sustainability. Despite ample urban development research, the historical developmental patterns of UAG remain underexplored. Long-term UAG exhibits an initial acceleration followed by deceleration, thus, using 200-years UAG data from the U.S., we meticulously compare the S-shaped curve (Logistics and Gompertz models) with other time-series models, and unveil insights into UAG's intricacies by examining how S-shaped models perform across different urban stages. Notably, the Logistics model emerges as the more accurate modeling tool, boasting an RMSE of 0.019, which surpasses the Gompertz model's 0.032. Moreover, the parameters of the S-curve explicitly describe the fundamental properties of UAG, and we unveil the remarkable stability of the maximum growth rate in the S-shaped model through a thorough parameter analysis, which underscores its role as a reliable and universally applicable assessment tool for UAG. Fundamentally, this meticulously analytical research delves deep into the complexities of the UAG curve, robustly confirming the S-shaped trend as the ‘realistic’ consequence of UAG over time. Importantly, this enduring S-shaped trend remains consistent across historical and contemporary contexts. These findings significantly advance our understanding of UAG dynamics for informed urban planning and development.

ABSTRACTSpaceborne photon-counting light detection and ranging (LiDAR) have been extensively applied in shallow-water bathymetry. The density of underwater topographic photons (UTP) varies and is discontinuous due to sunlight noise, beam intensity, and seabed reflectivity, which differ from the land photon distribution due to the attenuation of water. Therefore, a general method for extracting and grading UTP is still lacking. We propose an active contour method combined with a variable convolution kernel method to calculate the photon range by considering the energy contributions of adjacent photons. Adaptive parameters under different observation conditions were determined to obtain the optimal convolution kernel using a kernel ridge regression model. This implies that the number of photons contained in the buffer zone was largest after the extracted UTP was fitted to a curve. Quantitative and qualitative verifications proved that the method performed well under different conditions. The photons obtained by the energy functional and the curve obtained by the fitting method were then used to grade the photons. Finally, an online developed UTP dataset and extraction framework were proposed to provide an applicable method for current and subsequent spaceborne photon-counting LiDAR.

ABSTRACTAccurately predicting the geometric structure of a building's roof as a vectorized representation from a raster image is a challenging task in building reconstruction. In this paper, we propose an efficient and precise parsing method called Roof-Former, based on a vision Transformer. Our method involves three steps: (1) Image encoder and edge node initialization, (2) Image feature fusion with an enhanced segmentation refinement branch, and (3) Edge filtering and structural reasoning. Our method outperforms previous works on the vectorizing world building dataset and the Enschede dataset, with vertex and edge heat map F1-scores increasing from [Formula: see text], [Formula: see text] to [Formula: see text], [Formula: see text], and from [Formula: see text], [Formula: see text] to [Formula: see text], [Formula: see text], respectively. Furthermore, our method demonstrates superior performance compared to the current state-of-the-art based on qualitative evaluations, indicating its effectiveness in extracting global image information while maintaining the consistency and topological validity of the roof structure.

Connectivity enhancement of ecological networks is an efficient and advantageous spatial planning strategy, and it is a hot research topic to analyze ecological networks based on complex systems theory and perform model optimization. As a typical geographic network, the evolution process of ecological network, such as node and edge growth, will be subject to geospatial constraints, and the current research lacks optimization models that take the geospatial constraints into account. This study focused on urban ecological network connectivity and the distribution of nodes as well as structural fractures where the connectivity of the ecological network was hindered were analyzed. Then it introduced a local world network model to optimize network connectivity and designed a network growth mechanism with limited added nodes and optimal connections. An ecological network optimization model considering geospatial constraints was constructed, and the network closeness index was used to fit the objective function curve to select optimization schemes. This study used Shenzhen, China as a case study, and the results indicated that the initial ecological network was significantly fractured by urban construction. In the optimization scenario, the network evolution reached its optimal state at the simulation step size of t = 26. At this point, the closeness index of the optimized network was increased by 15%. The optimization model constructed in this paper emphasizes the importance of functional restoration of existing network nodes, and the results of the study can provide support for ecospatial layout optimization and management.

High-resolution digital elevation models (DEMs) of the lunar surface are crucial for lunar exploration missions and scientific research. The emergence of advanced technologies, such as Shape-from-Shading (SfS), has enabled the generation of pixel-wise high-resolution DEMs from monocular images of the lunar surface. However, SfS encounters significant challenges in locations with limited illumination, such as the lunar south pole, where the surface is largely covered by shadows. Therefore, this paper presents a novel shadow-constrained SfS approach for pixel-wise 3D surface reconstruction at the lunar south pole. The proposed approach uses multiple high-resolution images captured under different illumination conditions and an existing low-resolution DEM as the inputs and generates a high-resolution DEM with the same resolution as that of the input image through hierarchical SfS processing incorporating shadow constraints. Experiments were conducted using actual images collected by the Lunar Reconnaissance Orbiter (LRO) Narrow Angle Camera (NAC) at the lunar south pole. Comparisons with respect to photogrammetric DEMs generated from stereo NAC images show that the DEMs generated using the proposed approach exhibit the smallest root mean square error (RMSE). Moreover, shaded relief images rendered from the DEMs generated using the proposed approach demonstrate the highest similarity to the actual NAC images. Detailed profile comparisons further validate the effectiveness of the shadow constraint in optimizing 3D reconstruction in regions in proximity to shadows and within shadowed regions. The proposed shadow-constrained SfS approach can be used to generate high-resolution DEMs to support future missions to explore the lunar south pole, with applications including landing site evaluation and route planning for lunar probes or astronauts.

Building use identification is crucial in urban planning and management. Current identification methods often rely on a single data source and neglect spatial proximity. In this paper, we propose a stepwise urban building use identification framework that integrates remote sensing and social sensing data with spatial constraints based on the association of buildings with Point of Interest (POI), Area of Interest (AOI) and remote sensing data. First, the study data are preprocessed using geometric correction and POI and AOI reclassification. Then, we identify buildings with the quantitative-density index of the POIs as well as the spatial relationships between the AOIs and the buildings. Next, we generate Traffic Analysis Zones (TAZs) from road network data and utilize the similarity in physical features of buildings from remote sensing data to identify building use within spatial constraints. Finally, POI kernel density estimation is used to determine the semantic features of the buildings, and the similarity of the features between the buildings is utilized to identify the remaining buildings. The specificity of our proposed framework lies not only in the combination of multiple source data at the building-level but also in the introduction of the spatial relationships of AOIs and spatial constraints. Shenyang is selected as an example. The proposed framework identifies buildings as commercial, residential, industrial, public service and scenic spots. The accuracy assessment indicates that the proposed framework performs well, with an Overall Accuracy (OA) of 87.1% and a kappa coefficient (kappa) of 73.4%. The results of the comparison experiments show that the consideration of spatial constraints and the integration of multiple data sources help to improve the accuracy of building use identification. The proposed framework provides a new tool for better identification of urban building use, and the generated data are suitable for in-depth analyses such as building-level urban heat islands.