ISPRS International Journal of Geo-Information

Taking location-based service (LBS) as the research scenario and aiming at the limitation of visualizing LBS points of interest (POI) in conventional web maps, this article proposes a visualization method of LBS-POI based on tag cloud, which is called “LBS tag cloud”. In this method, the user location is taken as the layout center, and the name of the POI is converted into a text tag and then placed around the center. The tags’ size, color, and placement location are calculated based on other attributes of the POI. The calculation of placement location is at the core of the LBS tag cloud. Firstly, the tag’s initial placement position and layout priority are calculated based on polar coordinates, and the tags are placed in the initial placement position in the order of layout priority. Then, based on the force-directed model, a repulsive force is applied to the tag from the layout center to make it move to a position without overlapping with other tags. During the move, the quadtree partition of the text glyph is used to optimize the detection of overlaps between tags. Taking scenic spots as an example, the experimental results show that the LBS tag cloud can present the attributes and distribution of POIs completely and intuitively and can effectively represent the relationship between the POIs and user location, which is a new visualization form suitable for spatial cognition. Full article

The growing proliferation of geographic information presents a substantial challenge to the traditional framework of a geographic information analysis and service. The dynamic integration and representation of geographic knowledge, such as triples, with spatio-temporal information play a crucial role in constructing a comprehensive spatio-temporal knowledge graph and facilitating the effective utilization of spatio-temporal big data for knowledge-driven service applications. The existing knowledge graph (or geographic knowledge graph) takes spatio-temporal as the attribute of entity, ignoring the role of spatio-temporal information for accurate retrieval of entity objects and adaptive expression of entity objects. This study approaches the correlation between geographic knowledge and spatio-temporal information as a text classification problem, with the aim of addressing the challenge of establishing meaningful connections among spatio-temporal data using advanced deep learning techniques. Specifically, we leverage Wikipedia as a valuable data source for collecting and filtering geographic texts. The Open Information Extraction (OpenIE) tool is employed to extract triples from each sentence, followed by manual annotation of the sentences’ spatio-temporal relevance. This process leads to the formation of quadruples (time relevance/space relevance) or quintuples (spatio-temporal relevance). Subsequently, a comprehensive spatio-temporal classification dataset is constructed for experiment verification. Ten prominent deep learning text classification models are then utilized to conduct experiments covering various aspects of time, space, and spatio-temporal relationships. The experimental results demonstrate that the Bidirectional Encoder Representations from Transformer-Region-based Convolutional Neural Network (BERT-RCNN) model exhibits the highest performance among the evaluated models. Overall, this study establishes a foundation for future knowledge extraction endeavors. Full article

Architectural heritage refers to buildings, complexes, and sites with historical, cultural, artistic, technological, and geographical values, including ancient buildings, historical buildings, places of interest, dwellings, and industrial sites. China’s 20th-Century Architectural Heritage List is a state-level list that includes architecture of historical, cultural, technological, and artistic value in China in the 20th century. It is the carrier of the past century and the monument to witnessing the change in human knowledge, culture, technology, and even art. This list is from China, a country with a vast land area, a densely populated population, and numerous architectural relics. This study used ArcGIS to analyze 597 cases in 6 batches in China’s 20th-Century Architectural Heritage List. Its spatial structure was studied by calculating the nearest neighbor index, Gini coefficient, imbalance index, and kernel density. The results showed that the distribution of the Chinese modern architectural heritage resources is cohesive and uneven in China. Next, the geographical detector model was used to analyze its influencing factors from the perspective of 12 factors. This study found that the spatial distribution of this type of resource was condensed. The provincial level showed a distribution pattern of seven centers with one core and multiple scattered points. Its distribution in 34 administrative regions is extremely uneven, with 57.29% being located in North and East China. It also focused on analyzing five influencing factors, namely, topography, regional status, culture and education, social and economic development level, and external contact. Exploring its spatial structure and influencing factors will not only enable a comprehensive understanding of the development context and current situation of 20th-century architectural heritage, but also provide a reference for its protection and sustainable use. Full article

The spatial accessibility of urban parks is an important indicator of the livability level of cities. In this paper, we propose a comprehensive multimodal two-step floating catchment area (CM2SFCA) method which integrates supply capacity, the selection probability of individuals, and variable catchment sizes into the traditional multimodel 2SFCA method. This method is used to measure park accessibility in Wuhan, China. The results show that the spatial distribution of park accessibility under the proposed method is variant. High accessibility areas are clustered near the Third Ring Road with strong supply capacity parks, and low accessibility areas are distributed in the western and southern regions. Compared with the single-model accessibility (bicycling, driving, and public transit) method, we found that the multimodal spatial accessibility, combining the characteristics of three single transportations, can provide a more realistic evaluation. We also explore the spatial relationship between park accessibility and population density by bivariate local Moran’s I statistic and find that the Low Ai-High Pi area is located in the center of the study area, and the Low Ai-Low Pi area is located at the edge of the study area, with a relatively discrete distribution of parks and weak supply capacity. These findings may provide some insights for urban planners to formulate effective policies and strategies to ease the spatial inequity of urban parks. Full article

Building type prediction is a critical task for urban planning and population estimation. The growing availability of multi-source data presents rich semantic information for building type prediction. However, existing residential building prediction methods have problems with feature extraction and fusion from multi-type data and multi-level interactions between features. To overcome these limitations, we propose a deep learning approach that takes both the internal and external characteristics of buildings into consideration for residential building prediction. The internal features are the shape characteristics of buildings, and the external features include location features and semantic features. The location features include the proximity of the buildings to the nearest road and areas of interest (AOI), and the semantic features are mainly threefold: spatial co-location patterns of points of interest (POI), nighttime light, and land use information of the buildings. A deep learning model, DeepFM, with multi-type features embedded, was deployed to train and predict building types. Comparative and ablation experiments using OpenStreetMap and the nighttime light dataset were carried out. The results showed that our model had significantly higher classification performance compared with other models, and the F1 score of our model was 0.9444. It testified that the external semantic features of the building significantly enhanced the predicted performance. Moreover, our model showed good performance in the transfer learning between different regions. This research not only significantly enhances the accuracy of residential building identification but also offers valuable insights and ideas for related studies. Full article

Explainable Artificial Intelligence (XAI) has the potential to open up black-box machine learning models. XAI can be used to optimize machine learning models, to search for scientific findings, or to improve the understandability of the AI system for the end users. Geospatial XAI refers to AI systems that apply XAI techniques to geospatial data. Geospatial data are associated with geographical locations or areas and can be displayed on maps. This paper provides an overview of the state-of-the-art in the field of geospatial XAI. A structured literature review is used to present and discuss the findings on the main objectives, the implemented machine learning models, and the used XAI techniques. The results show that research has focused either on using XAI in geospatial use cases to improve model quality or on scientific discovery. Geospatial XAI has been used less for improving understandability for end users. The used techniques to communicate the AI analysis results or AI findings to users show that there is still a gap between the used XAI technique and the appropriate visualization method in the case of geospatial data. Full article

Remote sensing is valuable for estimating aboveground biomass (AGB) stocks. However, its application in agricultural and pasture areas is limited compared with forest areas. This study quantifies AGB in agriculture–pasture mosaics within Brazil’s Campo Maior Complex (CMC). The methodology employs remote sensing cloud processing and utilizes an estimator to incorporate vegetation indices. The results reveal significant changes in biomass values among land use and land cover classes over the past ten years, with notable variations observed in forest plantation, pasture, sugar cane, and soybean areas. The estimated AGB values range from 0 to 20 Mg.ha⁻¹ (minimum), 53 to 419 Mg.ha⁻¹ (maximum), and 19 to 57 Mg.ha⁻¹ (mean). In Forest formation areas, AGB values range from approximately 0 to 278 Mg.ha⁻¹, with an average annual value of 56.44 Mg.ha⁻¹. This study provides valuable insights for rural landowners and government officials in managing the semiarid territory and environment. It aids in decision making regarding agricultural management, irrigation and fertilization practices, agricultural productivity, land use and land cover changes, biodiversity loss, soil degradation, conservation strategies, the identification of priority areas for environmental restoration, and the optimization of resource utilization. Full article

The cyberspace map, as one of the important tools for describing cyberspace, provides a visual representation of the dynamic and elusive nature of cyberspace. It has become a research hotspot in multiple disciplinary fields. Compared with traditional maps, cyberspace maps lack the guidance of cartography theory and have not yet formed a unified understanding. Clarifying the concept of the cyberspace map and developing a conceptual model of it could enhance people’s unified understanding of cyberspace. Drawing from the perspective of cartography, this paper analyzes the current situation of cyberspace map research, first discussing the characteristics and definition of the cyberspace map and then proposing the conceptual model of a cyberspace map. This model elaborates on the types of map elements and their specific composition, the strength of their element–space association, the mapping of relationships between elements, element symbolization, and map expression. Then, based on the model proposed in this paper, typical maps are compared and analyzed, and design suggestions are provided. Finally, the entire article is summarized. This paper aims to adapt the development trend of cartography to the ternary space, clarify the basic concept of the cyberspace map, promote the development of cyberspace mapping theory, and lay the foundation for future research. Full article

Next Point-of-Interest (POI) recommendation has shown great value for both users and providers in location-based services. Existing methods mainly rely on partial information in users’ check-in sequences, and are brittle to users with few interactions. Moreover, they ignore the impact of multi-dimensional auxiliary information such as user check-in frequency, POI category on user preferences modeling and the impact of dynamic changes in user preferences over different time periods on recommendation performance. To address the above limitations, we propose a novel method for next POI recommendation by modeling long and short term user preferences with multi-dimensional auxiliary information. In particular, the proposed model includes a static LSTM module to capture users’ multi-dimensional long term static preferences and a dynamic meta-learning module to capture users’ multi-dimensional dynamic preferences. Furthermore, we incorporate a POI category filter into our model to comprehensively simulate users’ preferences. Experimental results on two real-world datasets demonstrate that our model outperforms the state-of-the-art baseline methods in two commonly used evaluation metrics. Full article

The accurate assessment of proper value in complex and increasingly high-rise urban environments is a significant challenge. Previous research has identified property value as a composite of indoor elements, such as volume and height, and 3D simulations of the outdoor environment, including variables such as view, noise, and pollution. These simulations have been preliminary performed in taxation context; however, there has been no work addressing the simulation of property valuation. In this paper, we propose an IFC-CityGML data integration approach for property valuation and develop a workflow based on IFC-CityGML 3.0 to simulate and model 3D property variables at the Level of Information Need. We evaluate this approach by testing it for two indoor variables, indoor daylight and property unit cost. Our proposed approach aims to improve the accuracy of property valuation by integrating data from indoor and outdoor environments and providing a standardized and efficient workflow for property valuation modeling using IFC and CityGML. Our approach represents a solid base for future works toward a 3D property valuation extension. Full article

The availability of spatial and spatiotemporal big data is increasing rapidly. Spatially and temporally high resolved data are especially gathered via the Internet of Things. This data can often be accessed as data streams that push new data tuples continuously and make the data available in real time. Such real-time spatiotemporal data have great potential for new analysis approaches based on modern data processing technologies. The ability to retrieve spatial big data in real time, as well as process it in real time, demands new analysis methodologies that catch up with the instantaneous and continuous character of today’s spatiotemporal data. In this work, we present an evaluation of a high-frequent dynamic spatiotemporal autocorrelation approach. This approach allows for geostatistical analysis of streaming spatiotemporal data in real time and can provide insights into spatiotemporal processes while they are still ongoing. To evaluate this new approach, it was applied to mobility data from New York City. The results show that a high-frequent dynamic spatiotemporal autocorrelation approach provides comparable and meaningful results. In this way, high-frequent geostatistical analyses in real time can become an addition to retrospective analyses based on historical data. Full article

The development of the HSR station area is the result of the combined effect of the three elements of transport, place, and industry. This study introduces the industrial dimension and constructs the node-place-industry model to empirically analyze the development potential of station areas along the Hunan section of the Beijing–Guangzhou and the Shanghai–Kunming high-speed railway lines. The results show that (1) the development of the three spatial elements of the station area is mostly out of sync, and the node value has the highest fit with the integrated potential value of the station area; (2) there is a significant correlation between the magnitude of the combined potential of the station area and the site location, station class and time of development; (3) according to the results of the cluster analysis, it was found that most of the stations were in a state of disequilibrium, and the main reason was that the functional value of the place did not match with the value of industrial aggregation. In particular, the introduction of the industry dimension extends the NP model and establishes a tessellated analytical framework for station type classification, providing an interesting assessment tool for the sustainable development of transport hub areas. Full article

This study focuses on the positional accuracy of Digital Elevation Models (DEMs) and 3D vector features by considering that both datasets can be used as a product to assess or as a reference. The main objective is to provide an alternative method to the traditional use of checkpoints by using check-surfaces in order to avoid identification issues. The methodology includes the determination of a set of polygons with a significant height in relation to the surrounding area (elevated or depressed) and those cells extracted from the DEM that match these elements. The check-surfaces are obtained after a triangulation of these polygons. The methodology uses procedures based on buffers to provide several results in the form of distribution functions of accuracies (2D, vertical and 3D). The trial has been carried out using a large set of data representing buildings obtained from official institutions. The results show consistent 2D, vertical and 3D accuracy values related to commonly used confidence levels. The application has demonstrated the viability of this approach for obtaining horizontal and vertical accuracies individually and jointly at any confidence level. In addition, the study includes the analysis of the results of specific zones, considering several characteristics. Full article

The comprehensive and accurate assessment of the indoor air quality (IAQ) in large spaces, such as offices or multipurpose facilities, is essential for IAQ management. It is widely recognized that various IAQ factors affect the well-being, health, and productivity of indoor occupants. In indoor environments, it is important to assess the IAQ in places where it is difficult to install sensors due to space constraints. Spatial interpolation is a technique that uses sample values of known points to predict the values of other unknown points. Unlike in outdoor environments, spatial interpolation is difficult in large indoor spaces due to various constraints, such as being separated into rooms by walls or having facilities such as air conditioners or heaters installed. Therefore, it is necessary to identify independent or related regions in indoor spaces and to utilize them for spatial interpolation. In this paper, we propose a spatial interpolation technique that groups points with similar characteristics in indoor spaces and utilizes the characteristics of these groups for spatial interpolation. We integrated the IAQ data collected from multiple locations within an office space and subsequently conducted a comparative experiment to assess the accuracy of our proposed method in comparison to commonly used approaches, such as inverse distance weighting (IDW), kriging, natural neighbor interpolation, and the radial basis function (RBF). Additionally, we performed experiments using the publicly available Intel Lab dataset. The experimental results demonstrate that our proposed scheme outperformed the existing methods. The experimental results show that the proposed method was able to obtain better predictions by reflecting the characteristics of regions with similar characteristics within the indoor space. Full article

Traffic prediction plays a significant part in creating intelligent cities such as traffic management, urban computing, and public safety. Nevertheless, the complex spatio-temporal linkages and dynamically shifting patterns make it somewhat challenging. Existing mainstream traffic prediction approaches heavily rely on graph convolutional networks and sequence prediction methods to extract complicated spatio-temporal patterns statically. However, they neglect to account for dynamic underlying correlations and thus fail to produce satisfactory prediction results. Therefore, we propose a novel Self-Adaptive Spatio-Temporal Graph Convolutional Network (SASTGCN) for traffic prediction. A self-adaptive calibrator, a spatio-temporal feature extractor, and a predictor comprise the bulk of the framework. To extract the distribution bias of the input in the self-adaptive calibrator, we employ a self-supervisor made of an encoder–decoder structure. The concatenation of the bias and the original characteristics are provided as input to the spatio-temporal feature extractor, which leverages a transformer and graph convolution structures to learn the spatio-temporal pattern, and then applies a predictor to produce the final prediction. Extensive trials on two public traffic prediction datasets (METR-LA and PEMS-BAY) demonstrate that SASTGCN surpasses the most recent techniques in several metrics. Full article

Historical maps represent a unique and irreplaceable source of information about the history of a country, be it large (historical) regions, individual geomorphological units or specifically defined sites. Using a methodologically correct, critical historical analysis, old maps provide both the horizontal and vertical analysis of a landscape and its transformation in different time periods. These maps represent some of the oldest, but relatively easily accessible, historical pictorial documents (plausibly) depicting historical landscapes. This study provides the methodology for processing and georeferencing old mine maps with the possibility of their further use for the purposes of mining tourism. The 1696 Marsigli mine map has been chosen for the case study in question. It depicts a cross-section of the copper mines in Smolník and shows in detail the process of cementation water mining. Through an analysis and a detailed study, two-dimensional parts of a georeferenced historical map have been plotted in Google Earth’s three-dimensional space. Full article

Using a people-centered approach to new urbanization, China has committed to building high-quality living environments through improving urban livability and promoting a stronger sense of belonging among residents. Retail stores serve as one of the most immediate and accessible destinations for residents’ consumption, and their spatial configuration has a direct impact on residents’ satisfaction and happiness in their daily lives. In this context, for the present study we selected the central urban area of Lanzhou City as the case study area. Based on POI data and using the daily life circle as the basic unit, we applied methods such as kernel density analysis, hotspot analysis, and the Shannon–Weaver index to analyze spatial distribution patterns of the retail industry. Furthermore, we applied Geodetector to analyze the impacts of four factors that are closely related to the retail industry: economic level, convenience level, market demand, and location. The conclusions are as follows: In the central urban area of Lanzhou, the retail industry exhibits a belt distribution pattern along the Yellow River. The density of distribution gradually decreases from the city center toward the outskirts, forming four prominent agglomeration centers. Overall, within the central urban area of Lanzhou, the spatial distribution of the retail industry at the scale of daily living circles shows that only a small proportion of the industry demonstrates noticeable clustering effects. In terms of spatial patterns, the retail industry at the scale of the daily living circles demonstrates similar characteristics in terms of diversity and agglomeration distribution. It exhibits a decreasing trend from the urban core toward the peripheral areas. The agglomeration distribution pattern of the retail industry in the central urban area of Lanzhou is considerably influenced by market demand, economic level, convenience, and location. The spatial distribution of the retail industry in the central urban area is primarily influenced by economic factors and convenience, while market demand plays a major role and location has a relatively minimal impact. Full article

With rapid urbanization, urban functional zones have become important for rational government and resource allocation. Points of interest (POIs), as informative and open-access data, have been widely used in studies of urban functions. However, most existing studies have failed to address unevenly or sparsely distributed POIs. In addition, the spatial adjacency of analysis units has been ignored. Therefore, we propose a new method for identifying urban functional zones based on POI density and marginalized graph autoencoder (MGAE). First, kernel density analysis was utilized to obtain the POI density and spread the effects of POIs to the surroundings, which enhanced the data from unevenly or sparsely distributed POIs considering the barrier effects of main roads and rivers. Second, MGAE performed feature extraction in view of the spatial adjacency to integrate features from the POIs of the surrounding units. Finally, the k-means algorithm was used to cluster units into zones, and semantic recognition was applied to identify the function category of each zone. A case study of Changzhou indicates that this method achieved an overall accuracy of 90.33% with a kappa coefficient of 0.88, which constitutes considerable improvement over that of conventional methods and can improve the performance of urban function identification. Full article

Accurate land use and land cover (LULC) mapping is essential for scientific and decision-making purposes. The objective of this paper was to map LULC classes in the northern region of Mozambique between 2011 and 2020 based on Landsat time series processed by the Random Forest classifier in the Google Earth Engine platform. The feature selection method was used to reduce redundant data. The final maps comprised five LULC classes (non-vegetated areas, built-up areas, croplands, open evergreen and deciduous forests, and dense vegetation) with an overall accuracy ranging from 80.5% to 88.7%. LULC change detection between 2011 and 2020 revealed that non-vegetated areas had increased by 0.7%, built-up by 2.0%, and dense vegetation by 1.3%. On the other hand, open evergreen and deciduous forests had decreased by 4.1% and croplands by 0.01%. The approach used in this paper improves the current systematic mapping approach in Mozambique by minimizing the methodological gaps and reducing the temporal amplitude, thus supporting regional territorial development policies. Full article