ISPRS Int. J. Geo-Inf., Volume 11, Issue 3 (March 2022) – 60 articles

Applying spatial clustering algorithms on large-scale spatial interactive dataset to find urban hot/cold spots is a new idea to assist urban management. However, the research usually focuses on the dataset with spatio-temporal proximity, rather than remote dataset. This article proposes a spatial hot/cold spot detection method for human communication by auto-correlating the PageRank values of the spatial interaction networks constructed by records. Milan was selected as the study area, and the spatial interaction records reflected by telephone calls, the land-use dataset, and the POI dataset were used as experimental data. The results showed that the proposed method can be applied to long-distance spatial interactive recording data, and the hot/cold spot were clearly distinguished by the statistical distribution of the containing land-use dataset and the POI dataset. These differences were consistent with the actual situation in the study area, indicating the accuracy of the proposed method for detecting hot/cold areas. Full article

In order to improve the effect of path planning in emergencies, the missing position imputation and velocity restoration in vehicle trajectory provide data support for emergency path planning and analysis. At present, there are many methods to fill in the missing trajectory information, but they basically restore the missing trajectory after analyzing a large number of datasets. However, the trajectory reduction method with few training sets needs to be further explored. For this purpose, a novel trajectory data cube model (TDC) is designed to store time, position, and velocity information hierarchically in the trajectory data. Based on this model, three trajectory Hierarchical Trace-Back algorithms HTB-p, HTB-v, and HTB-KF are proposed in this paper. Finally, experiments verify that conduct in a different number of sample sets, it has a satisfactory performance on information restoration of individual points of the trajectory and information restoration of trajectory segments. Full article

Green space areas are one of the key factors in people’s livelihoods. Their number and size have a significant impact on both the environment and people’s quality of life, including their health. Accordingly, government agencies often rely on information relating to green space areas when devising suitable plans and mandating necessary regulations. At present, obtaining information on green space areas using conventional ground surveys faces a number of limitations. This approach not only requires a lengthy period, but also tremendous human and financial resources. Given such restrictions, the status of a green space is not always up to date. Although software applications, especially those based on geographical information systems and remote sensing, have increasingly been applied to these tasks, the capability to use crowdsourcing data and produce real-time reports is lacking. This is partly because the quantity of data required has, to date, prohibited effective verification by human operators. To address this issue, this paper proposes a novel geospatial platform for green space area management by means of GIS and artificial intelligence. In the proposed system, all user-submitted data are automatically verified by deep learning classification and analyses of the greenness areas on satellite imagery. The experimental results showed that the classification and analyses can identify green space areas at accuracies of 93.50% and 97.50%, respectively. To elucidate the merits of the proposed approach, web-based application software was implemented to demonstrate multimodal data management, cleansing, and reporting. This geospatial system was thus proven to be a viable tool for assisting governmental agencies to devise appropriate plans toward sustainable development goals. Full article

Multi-source data fusion can help to weaken the original data’s shortcomings while improving data accuracy. The experimental area in this research is Taiyuan City in Shanxi Province, China. Using SRTM1 DEM, ASTER GDEM V3, and AW3D30 DEM, the optimal resolution of the Fused DEM in the research area is determined by analyzing the topographic factor information entropy. Then the optimally weighted fusion coefficient of the DEM with root mean square error (RMSE) as the criterion under different slope classes is determined by traversal exploration and quantitatively evaluates the fusion effect. The results show that the optimal resolution of the Fused DEM is 40 m under the terrain feature constraint of Taiyuan city. The fused DEM decreases by 33.8%, 57.9%, and 11.5% for mean absolute error (MAE), 36.3%, 54.6%, and 1.4% for standard deviation (STD), and 32.8%, 54.2%, and 9.7% for root mean square error (RMSE) compared with SRTM1, ASTER GDEM V3, and AW3D30. The weighted average fusion of multiple intensities increased the accuracy of the original data. The reduced topographic factor errors, such as slope, profile curvature, and TPI, improved the Fused DEM’s topographic representation capacity. Furthermore, the results confirm the high accuracy of Fused DEM in complex mountainous regions. Full article

Human activities are one of the main causes of lake-water pollution and eutrophication. The study of human pressure around lakes is of importance to understand its effects on the lakes natural resources. Social media data is a valuable space–time-resolved information source to detect human dynamics. In this study, user-generated geodata, namely users’ location records provided by the Facebook Data for Good program, are used to assess population patterns and infer the magnitude of anthropic pressure in the areas surrounding the Insubric lakes (Maggiore, Como and Lugano) between Northern Italy and Southern Switzerland. Patterns were investigated across different lakes’ neighbouring areas as well as seasons, days of the week, and day hours in the study period May 2020–August 2021. Two indicators were conceived, computed and mapped to assess the space–time distribution of users around lakes and infer the anthropic pressure. The highest pressure was found around lakes Maggiore and Como coastal areas during weekends in summer (up to +14% average users presence than weekdays in winter), suggesting tourism is the primary accountable reason for the pressure. Contrarily, around lake Lugano, the population dynamic is mostly affected by commuters or weekly workers, where the maximum pressure occurs during weekdays in all seasons (+6.6% average users presence than weekends). Results provide valuable input to further analyses connected, for example, to the correlation between human activities and lake-water quality and/or prediction models for anthropic pressure and tourism fluxes on lakes that are foreseen for the future development of this work. Full article

Crowd anomaly detection is a practical and challenging problem to computer vision and VideoGIS due to abnormal events’ rare and diverse nature. Consequently, traditional methods rely on low-level reconstruction in a single image space, easily affected by unimportant pixels or sudden variations. In addition, real-time detection for crowd anomaly detection is challenging, and localization of anomalies requires other supervision. We present a new detection approach to learn spatiotemporal features with the spatial constraints of a still dynamic image. First, a lightweight spatiotemporal autoencoder has been proposed, capable of real-time image reconstruction. Second, we offer a dynamic network to obtain a compact representation of video frames in motion, reducing false-positive anomaly alerts by spatial constraints. In addition, we adopt the perturbation visual interpretation method for anomaly visualization and localization to improve the credibility of the results. In experiments, our results provide competitive performance across various scenarios. Besides, our approach can process 52.9–63.4 fps in anomaly detection, making it practical for crowd anomaly detection in video surveillance. Full article

Land surface temperature (LST) is one of the crucial factors that is important in various fields, including the study of climate change and the urban heat island (UHI) phenomenon. The existing LST was acquired using satellite imagery, but with the development of unmanned aerial vehicles (UAV) and thermal infrared (TIR) cameras, it has become possible to acquire LST with a spatial resolution of cm. The accuracy evaluation of the existing TIR camera for UAV was conducted by shooting vertically. However, in the case of a TIR camera, the temperature value may change because the emissivity varies depending on the viewing angle. Therefore, it is necessary to evaluate the accuracy of the TIR camera according to each angle. In this study, images were simultaneously acquired at 2–min intervals for each of the three research sites by TIR camera angles (70°, 80°, 90°). Then, the temperature difference by land cover was evaluated with respect to the LST obtained by laser thermometer and the LST obtained using UAV and TIR. As a result, the image taken at 80° showed the smallest difference compared with the value obtained with a laser thermometer, and the 70° image showed a large difference of 1–6 °C. In addition, in the case of the impervious surface, there was a large temperature difference by angle, and in the case of the water-permeable surface, there was no temperature difference by angle. Through this, 80° is best when acquiring TIR data, and if it is impossible to take images at 80°, it is considered good to acquire TIR images between 80° and 90°. To obtain more accurate LST, correction studies considering the external environment, camera attitude, and shooting height are needed in future studies. Full article

Task allocation is a critical issue of spatial crowdsourcing. Although the batching strategy performs better than the real-time matching mode, it still has the following two drawbacks: (1) Because the granularity of the batch size set obtained by batching is too coarse, it will result in poor matching accuracy. However, roughly designing the batch size for all possible delays will result in a large computational overhead. (2) Ignoring non-stationary factors will lead to a change in optimal batch size that cannot be found as soon as possible. Therefore, this paper proposes a fine-grained, batching-based task allocation algorithm (FGBTA), considering non-stationary setting. In the batch method, the algorithm first uses variable step size to allow for fine-grained exploration within the predicted value given by the multi-armed bandit (MAB) algorithm and uses the results of pseudo-matching to calculate the batch utility. Then, the batch size with higher utility is selected, and the exact maximum weight matching algorithm is used to obtain the allocation result within the batch. In order to cope with the non-stationary changes, we use the sliding window (SW) method to retain the latest batch utility and discard the historical information that is too far away, so as to finally achieve refined batching and adapt to temporal changes. In addition, we also take into account the benefits of requesters, workers, and the platform. Experiments on real data and synthetic data show that this method can accomplish the task assignment of spatial crowdsourcing effectively and can adapt to the non-stationary setting as soon as possible. This paper mainly focuses on the spatial crowdsourcing task of ride-hailing. Full article

Rocky desertification is one of the most critical ecological and environmental problems in areas underlain by carbonate rocks globally. Land cover and land use in the region affects large-scale ecosystem processes on a global scale, and many Earth system models rely on accurate land cover information. Therefore, it is important to evaluate current global land cover products and to understand the differences between them, and the findings of these studies can provide guidance to different researchers when using or making land cover products. Whereas there are many studies on the assessment of coarser resolution land cover products, there are few studies on the assessment of higher resolution land cover products (10 m). In order to provide guidance for users of 10 m data, this paper uses the rock deserted southwest region of China as the experimental area. We analyzed the consistency and accuracy of the FROM-GLC, ESA WorldCover 10 and ESRI products using spatial pattern consistency, absolute accuracy assessment of three validation samples, and analyzed their intrinsic relationships among classification systems, classification methods, and validation samples. The results show that (1) the overall accuracy of the FROM-GLC product is the highest, ranging from 49.47 to 62.42%; followed by the overall accuracy of the ESA product, ranging from 45.13 to 64.50%; and the overall accuracy of the ESRI product is the lowest, between 39.03 and 61.94%. (2) The consistency between FROM-GLC and ESA is higher than the consistency between other products, with an area correlation coefficient of 0.94. Analysis of the spatial consistency of the three products shows that the proportion of perfectly consistent areas is low at 44.89%, mainly in areas with low surface heterogeneity and more homogeneous cover types. (3) Across the study area, the main land cover types such as forest and water bodies were the most consistent across the three product species, while the grassland, shrubland, and bareland were lower. All products showed high accuracy in homogeneous areas, with local accuracy varied in other areas, especially at high altitudes in the central and western regions. Therefore, land cover users cannot use these products directly when conducting relevant studies in rocky desertification areas, as their use may introduce serious errors. Full article

Fraud crime against seniors has become a serious social problem both at home and abroad. While most of the relevant research focuses on non-contact fraud against seniors, a few studies attend to contact fraud targeted at seniors. By constructing a theoretical framework of “environment–activity–fraud victimization” based on the integration of multiple theories, this study conducts a multilevel logit analysis of contact-fraud victimization among urban seniors in the downtown area of Guangzhou at the individual and neighborhood levels. The results show that contact-fraud victimization among urban seniors is influenced by individual-level factors and neighborhood-level factors, and that individual-level factors play a more significant role. More specifically, seniors with higher education levels and lower levels of self-control are more likely to experience contact-fraud victimization, while seniors who are older and healthier, and have higher household income are significantly less likely to experience contact-fraud victimization. Further, higher levels of collective efficacy and better living environments in the neighborhood significantly reduce the probability of contact-fraud victimization among urban seniors, while the percentage of the migrant population, the percentage of the aging population, and developed traffic environments significantly increase the probability of seniors experiencing contact fraud. This study confirms the feasibility of examining contact-fraud victimization among urban seniors based on the integration of theories, and enriches the research results of crime geography in terms of contact-fraud victimization among urban seniors. Full article

This research aims to protect Digital Elevation Model (DEM) data from piracy or counterfeiting. An invisible watermark inserted into the data, which will not considerably change the data value, is necessary. The proposed method involves the use of the two-dimensional discrete cosine transform (2D DCT), a combination of 2D DCT and discrete wavelet transform (DWT), and two-dimensional discrete Fourier transform (2D DFT) in the frequency domain. The data used include a National DEM file downloaded from the geoportal of the Geospatial Information Agency (Badan Informasi Geospasial—BIG). Three files represent mountainous, lowland/urban, and coastal areas. An “attack” is also conducted on the watermarked DEM by cropping. The results indicate that the watermarked DEM is well recognized. The watermark can be read 100% for 2D DCT, while that for 2D DFT can be read 90.50%. The distortion value of the elevation data under the DCT technique demonstrates the smallest maximum value of 0.1 m compared with 4.5 and 1.1 m for 2D DFT and 2D DCT–DWT. Meanwhile, the height difference (Max Delta), the peak signal-to-noise ratio, and the root mean squared error (RMSE) are highest in mountainous, lowland, and coastal areas, respectively. Overall, the 2D DCT is also superior to the 2D DFT and the2D DCT–DWT. Although only one can recognize the nine watermarks inserted on each sheet, DEMs attacked by the cropping process can still be identified. However, this finding can sufficiently confirm that DEMs belong to BIG. Full article

Earth Observation (EO) spectral indices have been an important tool for quantifying and monitoring forest biomass. Nevertheless, the selection of the bands and their combination is often realized based on preceding studies or generic assumptions. The current study investigates the relationship between satellite spectral information and the Above Ground Biomass (AGB) of a major private forest on the island of Java, Indonesia. Biomass-related traits from a total of 1517 trees were sampled in situ and their AGB were estimated from species-specific allometric models. In parallel, the exhaustive band combinations of the Ratio Spectral Index (RSI) were derived from near-concurrently acquired Sentinel-1 and Sentinel-2 images. By applying scenarios based on the entire dataset, the prevalence and monodominance of acacia, mahogany, and teak tree species were investigated. The best-performing index for the entire dataset yielded R² = 0.70 (R² = 0.78 when considering only monodominant plots). An application of eight traditional vegetation indices provided, at best, R² = 0.65 for EVI, which is considerably lower compared to the RSI best combination. We suggest that an investigation of the complete band combinations as a proxy of retrieving biophysical parameters may provide more accurate results than the blind application of popular spectral indices and that this would take advantage of the amplified information obtained from modern satellite systems. Full article

Predicting where the next large-scale wildfire event will occur can help fire management agencies better prepare for taking preventive actions and improving suppression efficiency. Wildfire simulations can be useful in estimating the spread and behavior of potential future fires by several available algorithms. The uncertainty of ignition location and weather data influencing fire propagation requires a stochastic approach integrated with fire simulations. In addition, scarcity of required spatial data in different fire-prone European regions limits the creation of fire simulation outputs. In this study we provide a framework for processing and creating spatial layers and descriptive data from open-access international and national databases for use in Monte Carlo fire simulations with the Minimum Travel Time fire spread algorithm, targeted to assess cross-boundary wildfire propagation and community exposure for a large-scale case study area (Macedonia, Greece). We simulated over 300,000 fires, each independently modelled with constant weather conditions from a randomly chosen simulation scenario derived from historical weather data. Simulations generated fire perimeters and raster estimates of annual burn probability and conditional flame length. Results were used to estimate community exposure by intersecting simulated fire perimeters with community polygons. We found potential ignitions can grow large enough to reach communities across 27% of the study area and identified the top-50 most exposed communities and the sources of their exposure. The proposed framework can guide efforts in European regions to prioritize fuel management activities in order to reduce wildfire risk. Full article

Soil erosion worldwide is an intense, poorly controlled process. In many respects, this is a consequence of the lack of up-to-date high-resolution erosion maps. All over the world, the problem of insufficient information is solved in different ways, mainly on a point-by-point basis, within local areas. Extrapolation of the results obtained locally to a more extensive territory produces inevitable uncertainties and errors. For the anthropogenic-developed part of Russia, this problem is especially urgent because the assessment of the intensity of erosion processes, even with the use of erosion models, does not reach the necessary scale due to the lack of all the required global large-scale remote sensing data and the complexity of considering regional features of erosion processes over such vast areas. This study aims to propose a new methodology for large-scale automated mapping of rill erosion networks based on Sentinel-2 data. A LinkNet deep neural network with a DenseNet encoder was used to solve the problem of automated rill erosion mapping. The recognition results for the study area of more than 345,000 sq. km were summarized to a grid of 3037 basins and analyzed to assess the relationship with the main natural-anthropogenic factors. Generalized additive models (GAM) were used to model the dependency of rill erosion density to explore complex relationships. A complex nonlinear relationship between erosion processes and topographic, meteorological, geomorphological, and anthropogenic factors was shown. Full article

Frequent and granular population data are essential for decision making. Further-more, for progress monitoring towards achieving the sustainable development goals (SDGs), data availability at global scales as well as at different disaggregated levels is required. The high population coverage of mobile cellular signals has been accelerating the generation of large-scale spatiotemporal data such as call detail record (CDR) data. This has enabled resource-scarce countries to collect digital footprints at scales and resolutions that would otherwise be impossible to achieve solely through traditional surveys. However, using such data requires multiple processes, algorithms, and considerable effort. This paper proposes a big data-analysis pipeline built exclusively on an open-source framework with our spatial enhancement library and a proposed open-source mobility analysis package called Mobipack. Mobipack consists of useful modules for mobility analysis, including data anonymization, origin–destination extraction, trip extraction, zone analysis, route interpolation, and a set of mobility indicators. Several implemented use cases are presented to demonstrate the advantages and usefulness of the proposed system. In addition, we explain how a large-scale data platform that requires efficient resource allocation can be con-structed for managing data as well as how it can be used and maintained in a sustainable manner. The platform can further help to enhance the capacity of CDR data analysis, which usually requires a specific skill set and is time-consuming to implement from scratch. The proposed system is suited for baseline processing and the effective handling of CDR data; thus, it allows for improved support and on-time preparation. Full article

This article describes an original methodology for integrating global SIR-like epidemic models with spatial interaction models, which enables the forecasting of COVID-19 dynamics in Poland through time and space. Mobility level, estimated by the regional population density and distances among inhabitants, was the determining variable in the spatial interaction model. The spatiotemporal diffusion model, which allows the temporal prediction of case counts and the possibility of determining their spatial distribution, made it possible to forecast the dynamics of the COVID-19 pandemic at a regional level in Poland. This model was used to predict incidence in 380 counties in Poland, which represents a much more detailed modeling than NUTS 3 according to the widely used geocoding standard Nomenclature of Territorial Units for Statistics. The research covered the entire territory of Poland in seven weeks of early 2021, just before the start of vaccination in Poland. The results were verified using official epidemiological data collected by sanitary and epidemiological stations. As the conducted analyses show, the application of the approach proposed in the article, integrating epidemiological models with spatial interaction models, especially unconstrained gravity models and destination (attraction) constrained models, leads to obtaining almost 90% of the coefficient of determination, which reflects the quality of the model’s fit with the spatiotemporal distribution of the validation data. Full article

Taxi demand forecasting plays an important role in ride-hailing services. Accurate taxi demand forecasting can assist taxi companies in pre-allocating taxis, improving vehicle utilization, reducing waiting time, and alleviating traffic congestion. It is a challenging task due to the highly non-linear and complicated spatial-temporal patterns of the taxi data. Most of the existing taxi demand forecasting methods lack the ability to capture the dynamic spatial-temporal dependencies among regions. They either fail to consider the limitations of Graph Neural Networks or do not efficiently capture the long-term temporal dependencies. In this paper, we propose a Spatial-Temporal Diffusion Convolutional Network (ST-DCN) for taxi demand forecasting. The dynamic spatial dependencies are efficiently captured through a two-phase graph diffusion convolutional network where the attention mechanism is introduced. Moreover, a novel temporal convolution module is designed to learn various ranges of temporal dependencies, including recent, daily, and weekly periods. Inside the module, convolution layers are stacked to handle very long sequences. Experimental results on two large-scale real-world taxi datasets from New York City (NYC) and Chengdu demonstrate that our method significantly outperforms seven state-of-the-art baseline methods. Full article

To achieve Sustainable Development Goal 7 (SDG7), it is essential to detect the spatiotemporal patterns of electricity consumption, particularly the spatiotemporal heterogeneity of consumers. This is also crucial for rational energy planning and management. However, studies investigating heterogeneous users are lacking. Moreover, existing works focuses on mathematic models to identify and predict electricity consumption. Additionally, owing to the complex non-linear interrelationships, interactive visualizations are more effective in detecting patterns. Therefore, by combining geospatial dashboard knowledge and interactive visualization technology, a Smart Electricity dashboard (SmartEle) was designed and developed to interactively visualize big electrical data and interrelated factors. A university campus as the study area. The SmartEle system addressed three challenges. First, it permitted user group-oriented monitoring of electricity consumption patterns, which has seldom been considered in existing studies. Second, a visualization-driven data mining model was proposed, and an interactive visualization dashboard was designed to facilitate the perception of electricity usage patterns at different granularities and from different perspectives. Finally, to deal with the non-linear features of electricity consumption, the ATT-LSTM machine learning model to support multivariate collaborative predicting was proposed to improve the accuracy of short-term electricity consumption predictions. The results demonstrated that the SmartEle system is usable for electricity planning and management. Full article

A collaborative open-source IT infrastructure is designed and implemented to optimize the process of geological field data collection, integration, validation, and sharing. Firstly, field data collection is carried out by multiple users using free and open-source GIS-based tools for mobile devices according to a predefined database structure; then, data integration is automatically performed in a central server, where the collected geological information is stored and validated; finally, data are shared over the Internet, providing users with up-to-date information. The IT infrastructure is currently being employed to accomplish surveys for the realization of the “Brescia” geological map within the New Geological Map of Italy, scale 1:50,000 (CARG Project). Users are only required to run the field data collection application on their mobile devices, add different geometric features to predefined thematic layers and fill in the dialogue forms with the required information to store the new structured and georeferenced data in the central database. The major advantage of the proposed IT infrastructure consists of guaranteeing the operational continuity between field surveys and the finalization of geological or geothematic maps leveraging field data collection tools that are operational both online and offline to ensure the overall system resilience. Full article

Nowadays, with the rise of sensor technology, the amount of spatial and temporal data is increasing day by day. Modeling data in a structured way and performing effective and efficient complex queries has become more essential than ever. Online analytical processing (OLAP), developed for this purpose, provides appropriate data structures and supports querying multidimensional numeric and alphanumeric data. However, uncertainty and fuzziness are inherent in the data in many complex database applications, especially in spatiotemporal database applications. Therefore, there is always a need to support flexible queries and analyses on uncertain and fuzzy data, due to the nature of the data in these complex spatiotemporal applications. FSOLAP is a new framework based on fuzzy logic technologies and spatial online analytical processing (SOLAP). In this study, we use crisp measures as input for this framework, apply fuzzy operations to obtain the membership functions and fuzzy classes, and then generate fuzzy association rules. Therefore, FSOLAP does not need to use predefined sets of fuzzy inputs. This paper presents the method used to model the FSOLAP and manage various types of complex and fuzzy spatiotemporal queries using the FSOLAP framework. In this context, we describe how to handle non-spatial and fuzzy spatial queries, as well as spatiotemporal fuzzy query types. Additionally, while FSOLAP primarily includes historical data and associated queries and analyses, we also describe how to handle predictive fuzzy spatiotemporal queries, which typically require an inference mechanism. Full article

With the widespread use of GPS equipment, a large amount of mobile location data is recorded, and urban hotspot areas extracted from GPS data can be applied to location-based services, such as tourist recommendations and point of interest positioning. It can also provide decision support for the analysis of population migration distribution and land use and planning. However, taxi GPS location data has a large amount of data and sparse points. How to avoid the influence of noise and efficiently detect hotspots in cities have become urgent problems to be solved. This paper proposes a clustering algorithm based on stay points and grid density. Firstly, a filtering pre-processing algorithm using stay points classification and stay points thresholds is proposed, so the influence of stop points is avoided. Then, the data space is divided into rectangular grid cells; each grid cell is determined to be a dense or non-dense grid according to the defined density threshold, and the cluster boundary points and noise points are judged in the non-dense grid cells to avoid normal sampling points being treated as noise. Finally, the associated dense grids are connected into clusters. The sampling points mapped to the grid cells are the elements in the clusters. Our method is more efficient than the DBSCAN algorithm because the grid cells are calculated. The superiority of the proposed algorithm in terms of clustering accuracy and time efficiency is verified in the real data set compared to traditional algorithms. Full article

In recent years, significant progress has been obtained in object detection using Convolutional Neural Networks (CNNs). However, owing to the particularity of Remote Sensing Images (RSIs), common object detection methods are not well suited for RSIs. Aiming at the difficulties in RSIs, this paper proposes an object detection method based on the Dense Feature Fusion Path Aggregation Network (DFF-PANet). Firstly, for better improving the detection performance of small and medium-sized instances, we propose Feature Reuse Module (FRM), which can integrate semantic and location information contained in feature maps; this module can reuse feature maps in the backbone to enhance the detection capability of small and medium-sized instances. After that, we design the DFF-PANet, which can help feature information extracted from the backbone to be fused more efficiently, and thus cope with the problem of external interference factors. We performed experiments on the Dataset of Object deTection in Aerial images (DOTA) dataset and the HRSC2016 dataset; the accuracy reached 71.5% mAP, which exceeds most object detectors of one-stage and two-stages at present. Meanwhile, the size of our model is only 9.2 M, which satisfies the requirement of being lightweight. The experimental results demonstrate that our method not only has better detection accuracy but also maintains high efficiency in RSIs. Full article

This paper proposes an approach of target tracking of a ground target for UAVs using Optimal Two-Stage Cubature Kalman Filter and Improved Coordinated Lateral Guidance Law. Firstly, the Optimal Two-Stage Cubature Kalman Filter (OTSCKF) is proposed to estimate the target motion. The OTSCKF combines two-stage filtering technology with CKF to improve the estimation accuracy. Secondly, to keep a constant distance between the UAV and the target, a new guidance law based on the lateral turning equation is proposed and its asymptotic stability is proven. On this basis, a distributed tracking algorithm is designed to balance the phase difference and achieve cooperation among multi-UAVs. Thirdly, numerical experiments are performed for the tracking problems of moving targets and the results verify the effectiveness of the proposed guidance algorithm. Full article

Spatial cluster detection is one of the focus areas of spatial analysis, whose objective is the identification of clusters from spatial distributions of point events aggregated in districts with small areas. Choi et al. (2018) formulated cluster detection as a parameter estimation problem to leverage the parameter selection capability of the sparse modeling method called the generalized fused lasso. Although this work is superior to conventional methods for detecting multiple clusters, its estimation results are limited to point estimates. This study therefore extended the above work as a Bayesian cluster detection method to describe the probabilistic variations of clustering results. The proposed method combines multiple sparsity-inducing priors and encourages sparse solutions induced by the generalized fused lasso. Evaluations were performed with simulated and real-world distributions of point events to demonstrate that the proposed method provides new information on the quantified reliabilities of clustering results at the district level while achieving comparable detection performances to that of the previous work. Full article

When surveying national reference points using a global positioning system (GPS), appropriate work regulations pertaining to the surveying time must be observed. However, such data can be modified easily, so identifying non-compliance with work regulations and forgeries is challenging. If such incidents occur in cadastral surveys, it may result in financial damages to stakeholders, such as citizens and the state. Therefore, it is necessary to improve the reliability by ensuring the integrity of the GPS positioning data and allowing anyone to track them. In this study, a prototype system was developed to record GPS data and the corrections generated during survey processes using the Ethereum blockchain network. Blockchain is a distributed ledger system that prevents the manipulation of uploaded data without the need for a centralized institution by allowing anyone to check the data. Unlike in the past, the proposed system improves the data integrity and reliability for the entire survey process through blockchain, thereby ensuring transparency of the checks using smart contract addresses. Full article

Predicting taxi-calling demands at the urban area level is vital to coordinate the supply–demand balance of the urban taxi system. Differing travel patterns, the impact of external data, and the expression of dynamic spatiotemporal demand dependence pose challenges to predicting demand. Here, a framework using residual attention graph convolutional long short-term memory networks (RAGCN-LSTMs) is proposed to predict taxi-calling demands. It consists of a spatial dependence (SD) extractor, which extracts SD features; an external dependence extractor, which extracts traffic environment-related features; a pattern dependence (PD) extractor, which extracts the PD of demands for different zones; and a temporal dependence extractor and predictor, which leverages the abovementioned features into an LSTM model to extract temporal dependence and predict demands. Experiments were conducted on taxi-calling records of Shanghai City. The results showed that the prediction accuracies of the RAGCN-LSTMs model were a mean absolute error of 0.8664, a root mean square error of 1.4965, and a symmetric mean absolute percentage error of 43.11%. It outperformed both classical time-series prediction methods and other deep learning models. Further, to illustrate the advantages of the proposed model, we investigated its predicting performance in various demand densities in multiple urban areas and proved its robustness and superiority. Full article

Time geography considers that the probability of moving objects distributed in an accessible transportation network is not always uniform, and therefore the probability density function applied to quantitative time geography analysis needs to consider the actual network constraints. Existing methods construct a kernel density function under network constraints based on the principle of least effort and consider that each point of the shortest path between anchor points has the same density value. This, however, ignores the attenuation effect with the distance to the anchor point according to the first law of geography. For this reason, this article studies the kernel function framework based on the unity of the principle of least effort and the first law of geography, and it establishes a mechanism for fusing the extended traditional model with the attenuation model with the distance to the anchor point, thereby forming a kernel density function of time geography under network constraints that can approximate the theoretical prototype of the Brownian bridge and providing a theoretical basis for reducing the uncertainty of the density estimation of the transportation network space. Finally, the empirical comparison with taxi trajectory data shows that the proposed model is effective. Full article

Waterway traffic monitoring is an important content in waterway traffic management. Taking into account that the number of monitored water areas is growing and that waterway traffic management capabilities are insufficient in the current situation in China, this paper investigates the location optimization of the vessel traffic service (VTS) radar station. During the research process, radar attenuation and environmental occlusion, as well as variable coverage radius and multiple covering are all considered. In terms of the radar attenuation phenomenon in the propagation process and obstacles such as mountains and islands in the real world, judgment and evaluation methods in a three-dimensional space are proposed. Moreover, a bi-objective mathematical model is then developed, as well as a modified adaptive strategy particle swarm optimization algorithm. Finally, a numerical example and a case are given to verify the effectiveness of the proposed methods, model, and algorithm. The results show the methods, model, and algorithm proposed in this paper can solve the model efficiently and provide a method to optimize the VTS radar station location in practice. Full article

The reliance on native MODIS-16 PET potential evapotranspiration (PET) in scarce-data-driven areas is growing in support among ecohydrological studies, yet information about its performance is limited or unknown as validation studies are mostly concentrated in developed countries. This study aimed to assess its performance at the monthly level using four ground measurements in a tropical watershed system with complex topography, applying a machine learning artificial neural network (ANN) to improve the estimates, and using the ANN-adjusted MODIS-16 PET to characterize the spatio-temporal patterns of PET in the Brantas watershed, as well as to understand the monthly patterns of water deficiency in areas under eight different vegetation covers. The results showed that the native MODIS-16 PET experienced overestimation with an RMSE of 37–66 mm/month and NRSME of up to 33%. The performance decreased in drier periods. The ANN-based adjustment using only one variable showed improved estimates with a reduction of RSME to only 14 mm and lower than 10% NRMSE. Sari-temporal patterns of PET in the Brantas watershed showed that the PET characteristics were not uniform. The southern part of the Brantas watershed has areas with relatively lower PET that are, thus, more prone to water deficiency. Complex topography and climate gradients within the watershed apparently became the multi-controllers of PET variations. The difference in vegetation cover also influenced the magnitudes of water deficiency. Full article

Point-based networks have been widely used in the semantic segmentation of point clouds owing to the powerful 3D convolution neural network (CNN) baseline. Most of the current methods resort to intermediate regular representations for reorganizing the structure of point clouds for 3D CNN networks, but they may neglect the inherent contextual information. In our work, we focus on capturing discriminative features with the interactive attention mechanism and propose a novel method consisting of the regional simplified dual attention network and global graph convolution network. Firstly, we cluster homogeneous points into superpoints and construct a superpoint graph to effectively reduce the computation complexity and greatly maintain spatial topological relations among superpoints. Secondly, we integrate cross-position attention and cross-channel attention into a single head attention module and design a novel interactive attention gating (IAG)-based multilayer perceptron (MLP) network (IAG–MLP), which is utilized for the expansion of the receptive field and augmentation of discriminative features in local embeddings. Afterwards, the combination of stacked IAG–MLP blocks and the global graph convolution network, called IAGC, is proposed to learn high-dimensional local features in superpoints and progressively update these local embeddings with the recurrent neural network (RNN) network. Our proposed framework is evaluated on three indoor open benchmarks, and the 6-fold cross-validation results of the S3DIS dataset show that the local IAG–MLP network brings about 1% and 6.1% improvement in overall accuracy (OA) and mean class intersection-over-union (mIoU), respectively, compared with the PointNet local network. Furthermore, our IAGC network outperforms other CNN-based approaches in the ScanNet V2 dataset by at least 7.9% in mIoU. The experimental results indicate that the proposed method can better capture contextual information and achieve competitive overall performance in the semantic segmentation task. Full article