Search

With the development of ecological civilization construction, urban planning and development in China have entered a phase in which optimizing and constructing ecological spaces is required. As a national livable city, Xuchang has experienced rapid economic development in recent years, leading to significant urban expansion that has impacted the layout of ecological space networks in the central urban area and its surroundings. Therefore, identifying and optimizing the spatial layout of ecological corridors in Xuchang City are crucial for ecological development and park city construction. This study utilizes multisource geospatial data to identify and extract ecological corridors in the central urban area of Xuchang City. Ecological resistance and gravity models are employed to identify and verify that the primary ecological corridor pattern in Xuchang City is situated in Weidu District, which is a central urban area. Finally, 11 main ecological corridors in the central urban area are delineated. In response to the identification of ecological corridors, this study integrates spatial analysis methods and text analysis methods to evaluate the characteristics of urban ecological corridors. The results indicate that Xudu Park extends outward, serving as the hub of the ecological network, and that West Lake Park and Luming Lake Park form the core of the urban park system. Finally, based on the spatial relationships, ecological benefits, and citizen experience of each ecological corridor and the green parks it traverses, strategies for optimizing the layout of urban ecological corridors are proposed. [ABSTRACT FROM AUTHOR]

Accurate, detailed, and long-term urban land use mapping is crucial for urban planning, environmental assessment, and health evaluation. Despite previous efforts, mapping essential urban land use categories (EULUCs) across multiple periods remains challenging, primarily due to the scarcity of enduring consistent socio-geographical data, such as the widely used Point of Interest (POI) data. Addressing this issue, this study presents an experimental method for mapping the time-series of EULUCs in Dalian city, China, utilizing Local Climate Zone (LCZ) data as a substitute for POI data. Leveraging multi-source geospatial big data and the random forest classifier, we delineate urban land use distributions at the parcel level for the years 2000, 2005, 2010, 2015, 2018, and 2020. The results demonstrate that the generated EULUC maps achieve promising classification performance, with an overall accuracy of 78% for Level 1 and 71% for Level 2 categories. Features derived from nighttime light data, LCZ, Sentinel-2 satellite imagery, and topographic data play leading roles in our land use classification process. The importance of LCZ data is second only to nighttime light data, achieving comparable classification accuracy to that when using POI data. Our subsequent correlation analysis reveals a significant correlation between POI and LCZ data (p = 0.4), which validates the rationale of the proposed framework. These findings offer valuable insights for long-term urban land use mapping, which can facilitate effective urban planning and resource management in the near future. [ABSTRACT FROM AUTHOR]

Despite great progress in enhancing the efficiency of public transport, one still cannot seamlessly incorporate structural characteristics into existing algorithms. Moreover, comprehensively exploring the structure of urban bus networks through a single-view modelling approach is limited. In this research, a multi-view graph learning algorithm (MvGL) is proposed to aggregate community information from multiple views of urban bus system. First, by developing a single-view graph encoder module, latent community relationships can be captured during learning node embeddings. Second, inspired by attention mechanism, a multi-view graph encoder module is designed to fuse node embeddings in different views, aims to perceive more community information of urban bus network comprehensively. Then, the community assignment can be updated by using a differentiable clustering layer. Finally, a well-defined objective function, which integrates node level, community level and graph level, can help improve the quality of community detection. Experimental results demonstrated that MvGL can effectively aggregate community information from different views and further improve the quality of community detection. This research contributes to the understanding the structural characteristics of public transport networks and facilitates their operational efficiency. [ABSTRACT FROM AUTHOR]

The visibility of retail frontages is critical for earning profits from spontaneous traffic visits to retail shops located along a street. The urban tree canopy plays a crucial role in enhancing the street-side environment, yet more is not always better when considering the placement of retail shops behind trees with big canopies. Related evidence in the literature is rarely provided, and an unclear relationship has been reported to exist between the number of shops for a specific retail type and the quantified ratio of the canopy shade in a street view. In this study, both big data crawling and deep learning were employed to unravel this relationship for retail shops in Changchun, Northeast China. The entire study area was divided into 6037 grid cells with a side length of ~0.6 km, wherein the number of shops of five retail types (food and beverage, shopping, life services, entertainment, and hotel) were quantified by computer counting their points of interest (POIs). The canopy shade was evaluated using the green view index (GVI) quantified through the ratio of canopy pixels divided by all the pixels in a street view image obtained through an online map API. A neighboring road network was categorized into four classes: class I road density mainly reduced the number of retail shops, and the road densities of classes III and IV accounted for more retail shops. The relationship between the number of retail shops and the GVI could be fitted with positive skewness curves for class II roads, where the critical peak of the GVI was estimated to be about 3.27%. The optimization scheme indicated that more retail shops should be placed along class I and II roads. In conclusion, more retail shops for food and beverage, shopping, and life services should be placed in the landscape neighboring big canopies. [ABSTRACT FROM AUTHOR]

Recommendation systems research is a subfield of information retrieval, as these systems recommend appropriate items to users during their visits. Appropriate recommendation results will help users save time searching while increasing productivity at work, travel, or shopping. The problem becomes more difficult when the items are geographical locations on the ground, as they are associated with a wealth of contextual information, such as geographical location, opening time, and sequence of related locations. Furthermore, on social networking platforms that allow users to check in or express interest when visiting a specific location, their friends receive this signal by spreading the word on that online social network. Consideration should be given to relationship data extracted from online social networking platforms, as well as their impact on the geolocation recommendation process. In this study, we compare the similarity of geographic locations based on their distance on the ground and their correlation with users who have checked in at those locations. When calculating feature embeddings for users and locations, social relationships are also considered as attention signals. The similarity value between location and correlation between users will be exploited in the overall architecture of the recommendation model, which will employ graph convolution networks to generate recommendations with high precision and recall. The proposed model is implemented and executed on popular datasets, then compared to baseline models to assess its overall effectiveness. [ABSTRACT FROM AUTHOR]

In this paper, we consider a wireless sensor network consisting of an unmanned aerial vehicle (UAV) acting as a sink node and a number of sensor nodes scattered uncertainly on the ground. In the network, the UAV flies to a spatial point called point of interest and hovers to collect environmental data from neighboring sensor nodes. Then, the UAV proceeds to the next point of interest. The UAV must gather data from all the sensor nodes. On the other hand, a shorter round-trip air route of the UAV is more preferred since a battery-operated UAV needs regular recharging. To satisfy the requirement and to adhere to the recommendation as well, especially in the situation where only vague locational information about sensor nodes is available, we propose a scheme that follows three steps. First, it covers the sensor field of the wireless sensor network with three categories of hexagonal tessellations. Secondly, it establishes a point of interest at the centroid of each tile. Thirdly, it constructs an air route of the UAV, which visits every point of interest along a Hamiltonian cycle on the induced graph. Next, we develop a closed-form expression for the exact flight distance attained by the proposed scheme. For comparative evaluation, we discover some optimal schemes that minimize the flight distance by completely inspecting all patterns and corroborating the property of Hamiltonicity. The flight distance along the air route constructed by the proposed scheme is found to be only slightly longer than the flight distance yielded by an optimal scheme. Furthermore, the proposed scheme is proven to be practically valid when a common multicopter is employed as the sink node. [ABSTRACT FROM AUTHOR]

Transitional streets serve as intermediary spaces between the Central Business Districts (CBDs) and surrounding residential areas, offering diverse functions and activities within urban interiors. However, a practical methodology for accurately classifying these streets has been lacking, due primarily to transitional areas' spatial constraints and functional complexities. This study leverages Point of Interest (PoI) data from 2023 to develop an innovative methodological framework that addresses these challenges. This framework analyses transitional streets' functional distribution and typology, employing PoI frequency density and functional type ratios to identify and classify functional zones. It generally delineates eight main types of transitional streets in the CBD of Chongqing, a prototypical hillside city. Utilising advanced data technology from internet maps, this research pioneers new approaches for identifying and analysing the functionality of transitional streets. The findings underscore the effectiveness of PoI data in precisely recognising the functional types of transitional streets, thereby providing a robust theoretical and practical foundation for the in-depth study of transitional streets. Moreover, the results enhance urban spatial planning in hillside cities of China, effectively demonstrating the advantages of PoI data in defining street typology compared to traditional methods. This approach provides a more detailed understanding of urban functional dynamics by allowing for a more nuanced data analysis of street functions. [ABSTRACT FROM AUTHOR]

Sentiment analysis is one of the promising approaches for developing a point of interest (POI) recommendation system. It uses natural language processing techniques that deploy expert insights from user-generated content such as reviews and feedback. By applying sentiment polarities (positive, negative, or neutral) associated with each POI, the recommendation system can suggest the most suitable POIs for specific users. The proposed study combines two models for POI recommendation. The first model uses bidirectional long short-term memory (BiLSTM) to predict sentiments and is trained on an election dataset. It is observed that the proposed model outperforms existing models in terms of accuracy (99.52%), precision (99.53%), recall (99.51%), and F1-score (99.52%). Then, this model is used on the Foursquare dataset to predict the class labels. Following this, user and POI embeddings are generated. The next model recommends the top POIs and corresponding coordinates to the user using the LSTM model. Filtered user interest and locations are used to recommend POIs from the Foursquare dataset. The results of our proposed model for the POI recommendation system using sentiment analysis are compared to several state-of-the-art approaches and are found quite affirmative regarding recall (48.5%) and precision (85%). The proposed system can be used for trip advice, group recommendations, and interesting place recommendations to specific users. [ABSTRACT FROM AUTHOR]

Copyright of Tourism Tribune / Lvyou Xuekan is the property of Tourism Institute of Beijing Union University and its content may not be copied or emailed to multiple sites or posted to a listserv without the copyright holder's express written permission. However, users may print, download, or email articles for individual use. This abstract may be abridged. No warranty is given about the accuracy of the copy. Users should refer to the original published version of the material for the full abstract. (Copyright applies to all Abstracts.)

Vehicular fog computing (VFC), as the extension of the mobile cloud, has been widely investigated. However, in most existing VFC works, the scenario with point-of-interests (PoIs) is rarely considered, which can lead to underutilization of vehicle computing resources and overloading of the computing load for roadside units (RSUs). Therefore, this paper focuses on improving the quality of services for PoI-based VFC by utilizing the computation capabilities of vehicles to assist the RSU. An NP-hard problem is formulated to maximize the number of tasks completed within the duration of delay constraints. To solve the problem, a delay-aware task offloading algorithm, named Delay-Aware Task Offloading (DTO), is proposed. DTO preferentially operates on tasks with tighter delay constraints. To minimize the completion delay for each offloaded task, DTO selects the set of service vehicles to perform tasks. Moreover, a vehicle-resource-aware task offloading algorithm, named Vehicle-Resources-Aware Task Offloading (VRTO), is proposed to maximize the number of tasks completed within the duration of delay constraints by efficiently utilizing the available resource of the vehicle. Specifically, VRTO allocates the data to each service vehicle according to the service configuration of vehicles and the delay constraints of tasks. Finally, extensive experiments are carried out to evaluate the effectiveness of the proposed algorithms. The performance is successfully improved by more than 30% compared with the baselines in terms of the number of completed tasks. [ABSTRACT FROM AUTHOR]

Augmented reality (AR) technology has emerged as a promising solution that can potentially reduce head-down time and increase situational awareness during navigation operations. It is also useful for remote operation centers where video feeds from remote ships can be "augmented" with data and information. In this article, we introduce a user interface design concept that supports ship navigation by showing data about points of interest in AR. This approach enables users to view and interact with relevant data in the maritime environment by bridging the gap between digital information and real-world features. The proposed concept can provide operational data from various maritime systems, such as radar, GPS, AIS, or camera systems, empowering users with a wealth of information about their surroundings. Developed through an iterative user-centered design process, it was built as an extension to the OpenBridge design system, an open-source platform facilitating consistent design in maritime workplaces. Furthermore, we use this concept to propose a design framework that paves the way for establishing new standards for AR user interface design in the maritime domain. [ABSTRACT FROM AUTHOR]

Sentiment analysis is one of the promising approaches for developing a point of interest (POI) recommendation system. It uses natural language processing techniques that deploy expert insights from user-generated content such as reviews and feedback. By applying sentiment polarities (positive, negative, or neutral) associated with each POI, the recommendation system can suggest the most suitable POIs for specific users. The proposed study combines two models for POI recommendation. The first model uses bidirectional long short-term memory (BiLSTM) to predict sentiments and is trained on an election dataset. It is observed that the proposed model outperforms existing models in terms of accuracy (99.52%), precision (99.53%), recall (99.51%), and F1-score (99.52%). Then, this model is used on the Foursquare dataset to predict the class labels. Following this, user and POI embeddings are generated. The next model recommends the top POIs and corresponding coordinates to the user using the LSTM model. Filtered user interest and locations are used to recommend POIs from the Foursquare dataset. The results of our proposed model for the POI recommendation system using sentiment analysis are compared to several state-of-the-art approaches and are found quite affirmative regarding recall (48.5%) and precision (85%). The proposed system can be used for trip advice, group recommendations, and interesting place recommendations to specific users.

The growth of the tourism industry has greatly boosted the Point-of-Interest (POI) recom- mendation tasks using Location-based Social Networks (LBSNs). The ever-evolving nature of user preferences poses a major problem. To address this, we propose a Long-Term Preference Mining (LTPM) approach that utilizes the Temporal Recency (TR) measure in the visits along with the location-aware recommendation based on Spatial Proximity (SP) to the user’s location. The temporal dynamics and changing preferences are exploited based on the modified Long Short-term Memory (LSTM) that utilizes the time decay. The spatial considerations are modeled in two aspects: geographical proximity based on enhanced representation learning using orthogonal mapping. Second, the Region-of-Interest (ROI) is based on spatial griding and metric learning to capture the spatial relationships between POIs to enhance the metric space representation. The final recommendations are based on a multi-head attention mechanism that allocates the weights to different features. The combination of three models, called, LTPM-TRSP approach captures the user-POI, POI-POI, and POI-time relationships by focusing on the informative representation of sequential and spatial data. The category-aware final recommendations based on comprehensive historical behavior and geographical context are quite efficacious. The experimentation on three real-world datasets, Gowalla, Foursquare, and Weeplaces, also suggests the potency compared to other state-of-the-art approaches.

With the development of ecological civilization construction, urban planning and development in China have entered a phase in which optimizing and constructing ecological spaces is required. As a national livable city, Xuchang has experienced rapid economic development in recent years, leading to significant urban expansion that has impacted the layout of ecological space networks in the central urban area and its surroundings. Therefore, identifying and optimizing the spatial layout of ecological corridors in Xuchang City are crucial for ecological development and park city construction. This study utilizes multisource geospatial data to identify and extract ecological corridors in the central urban area of Xuchang City. Ecological resistance and gravity models are employed to identify and verify that the primary ecological corridor pattern in Xuchang City is situated in Weidu District, which is a central urban area. Finally, 11 main ecological corridors in the central urban area are delineated. In response to the identification of ecological corridors, this study integrates spatial analysis methods and text analysis methods to evaluate the characteristics of urban ecological corridors. The results indicate that Xudu Park extends outward, serving as the hub of the ecological network, and that West Lake Park and Luming Lake Park form the core of the urban park system. Finally, based on the spatial relationships, ecological benefits, and citizen experience of each ecological corridor and the green parks it traverses, strategies for optimizing the layout of urban ecological corridors are proposed.

Recommendation system always involves huge volumes of data, therefore it causes the scalability issues that do not only increase the processing time but also reduce the accuracy. In addition, the type of data used also greatly affects the result of the recommendations. In the recommendation system, there are two common types of data namely implicit (binary) rating and explicit (scalar) rating. Binary rating produces lower accuracy when it is not handled with the properly. Thus, optimized K-Means+ clustering and user-based collaborative filtering are proposed in this research. The K-Means clustering is optimized by selecting the K value using the Davies-Bouldin Index (DBI) method. The experimental result shows that the optimization of the K values produces better clustering than Elbow Method. The KMeans+ and User-Based Collaborative Filtering (UBCF) produce precision of 8.6% and f-measure of 7.2%, respectively. The proposed method was compared to DBSCAN algorithm with UBCF, and had better accuracy of 1% increase in precision value. This result proves that K-Means+ with UBCF can handle implicit feedback datasets and improve precision. [ABSTRACT FROM AUTHOR]

While understanding the dynamic urban network through the concept of regional centrality has provided various implications on the structure and hierarchy of cities, the macroscopic focus of previous studies has largely overlooked the small-scale physical and social urban entities in central places. Meanwhile, recent advances in real-time Point-of-Interest (POI) data have quickly replaced much of traditional urban facility data, emerging as a new representation of urban activities and demands. Therefore, this study proposes a method to identify the relationship between regional centrality and the distribution of POI facilities, particularly focused on the Seoul metropolitan area of South Korea. To this end, this study conducts a correlation analysis between regional centrality results derived from social network analysis and POI indices obtained from POI distribution analysis. The results indicate that a statistically significant relationship exists between regional centrality and the distribution of urban facilities, with a particularly strong correlation exhibited in specific POI categories. The results also demonstrate the effectiveness of the method in capturing disparities in the provision of facilities concerning growing commuting centers. The findings of the study provide pragmatic implications for prioritization and planning of facility development, as well as making informed decisions in real estate and facility investment. [ABSTRACT FROM AUTHOR]

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. [ABSTRACT FROM AUTHOR]

Nighttime light (NTL) data and points of interest (POI) data offer precise visual indications of the distributional characteristics of urban spatial structures. This study employed nighttime light data and point of interest data to investigate spatial distribution patterns in Changchun, a selected study area. The built-up area was extracted from the nighttime light data, while kernel density analysis was utilized to examine the distribution of point of interest data. The processing outcomes of both datasets were gridded with spatially resolved resolution. Afterward, the fishnet tool was employed to conduct two-factor integrated mapping and visual analysis, which helped identify shared or divergent spatial coupling relationships. The results indicated a high degree of consistency in the distribution of both NTL and POI across Changchun, with 84.58% of the coupling demonstrating a concordant pattern. The spatial analysis conducted in this study showed that the heterogeneities of the coupling relationship within each administrative borough expanded outward from the center of the borough. POI provided a more accurate depiction of the spatial distribution of urban built-up areas compared to NTL, leading to a more precise representation of spatial patterns of human activity intensity. Changchun has undergone zoning adjustments, resulting in the emergence of multiple urban centers in both the central city and the surrounding administrative districts. These urban centers are gradually merging into each other. The study found that the level of spatial coupling was much higher in the central area compared to the surrounding administrative districts. This has contributed to the formation of multiple urban centers and the gradual expansion of the urban built-up area beyond the main city, indicating a trend towards regional integration and development. This study provides a more detailed and accurate description of the current distribution of urbanization and spatial structural characteristics of Changchun by investigating the spatial coupling between POI and NTL. The findings contribute to a better understanding of the urban development patterns in the region and provide insights for future urban planning and management. [ABSTRACT FROM AUTHOR]

Traffic congestion and frequent traffic accidents have become the main problems affecting urban traffic. The effective location prediction of vehicle trajectory can help alleviate traffic congestion, reduce the occurrence of traffic accidents, and optimize the urban traffic system. Vehicle trajectory is closely related to the surrounding Point of Interest (POI). POI can be considered as the spatial feature and can be fused with trajectory points to improve prediction accuracy. A Local Dynamic Graph Spatiotemporal–Long Short-Term Memory (LDGST-LSTM) was proposed in this paper to extract and fuse the POI knowledge and realize next location prediction. POI semantic information was learned by constructing the traffic knowledge graph, and spatial and temporal features were extracted by combining the Graph Attention Network (GAT) and temporal attention mechanism. The effectiveness of LDGST-LSTM was verified on two datasets, including Chengdu taxi trajectory data in August 2014 and October 2018. The accuracy and robustness of the proposed model were significantly improved compared with the benchmark models. The effects of major components in the proposed model were also evaluated through an ablation experiment. Moreover, the weights of POI that influence location prediction were visualized to improve the interpretability of the proposed model. [ABSTRACT FROM AUTHOR]

The visibility of retail frontages is critical for earning profits from spontaneous traffic visits to retail shops located along a street. The urban tree canopy plays a crucial role in enhancing the street-side environment, yet more is not always better when considering the placement of retail shops behind trees with big canopies. Related evidence in the literature is rarely provided, and an unclear relationship has been reported to exist between the number of shops for a specific retail type and the quantified ratio of the canopy shade in a street view. In this study, both big data crawling and deep learning were employed to unravel this relationship for retail shops in Changchun, Northeast China. The entire study area was divided into 6037 grid cells with a side length of ~0.6 km, wherein the number of shops of five retail types (food and beverage, shopping, life services, entertainment, and hotel) were quantified by computer counting their points of interest (POIs). The canopy shade was evaluated using the green view index (GVI) quantified through the ratio of canopy pixels divided by all the pixels in a street view image obtained through an online map API. A neighboring road network was categorized into four classes: class I road density mainly reduced the number of retail shops, and the road densities of classes III and IV accounted for more retail shops. The relationship between the number of retail shops and the GVI could be fitted with positive skewness curves for class II roads, where the critical peak of the GVI was estimated to be about 3.27%. The optimization scheme indicated that more retail shops should be placed along class I and II roads. In conclusion, more retail shops for food and beverage, shopping, and life services should be placed in the landscape neighboring big canopies.

In this paper, we consider a wireless sensor network consisting of an unmanned aerial vehicle (UAV) acting as a sink node and a number of sensor nodes scattered uncertainly on the ground. In the network, the UAV flies to a spatial point called point of interest and hovers to collect environmental data from neighboring sensor nodes. Then, the UAV proceeds to the next point of interest. The UAV must gather data from all the sensor nodes. On the other hand, a shorter round-trip air route of the UAV is more preferred since a battery-operated UAV needs regular recharging. To satisfy the requirement and to adhere to the recommendation as well, especially in the situation where only vague locational information about sensor nodes is available, we propose a scheme that follows three steps. First, it covers the sensor field of the wireless sensor network with three categories of hexagonal tessellations. Secondly, it establishes a point of interest at the centroid of each tile. Thirdly, it constructs an air route of the UAV, which visits every point of interest along a Hamiltonian cycle on the induced graph. Next, we develop a closed-form expression for the exact flight distance attained by the proposed scheme. For comparative evaluation, we discover some optimal schemes that minimize the flight distance by completely inspecting all patterns and corroborating the property of Hamiltonicity. The flight distance along the air route constructed by the proposed scheme is found to be only slightly longer than the flight distance yielded by an optimal scheme. Furthermore, the proposed scheme is proven to be practically valid when a common multicopter is employed as the sink node.

Augmented reality (AR) technology has emerged as a promising solution that can potentially reduce head-down time and increase situational awareness during navigation operations. It is also useful for remote operation centers where video feeds from remote ships can be “augmented” with data and information. In this article, we introduce a user interface design concept that supports ship navigation by showing data about points of interest in AR. This approach enables users to view and interact with relevant data in the maritime environment by bridging the gap between digital information and real-world features. The proposed concept can provide operational data from various maritime systems, such as radar, GPS, AIS, or camera systems, empowering users with a wealth of information about their surroundings. Developed through an iterative user-centered design process, it was built as an extension to the OpenBridge design system, an open-source platform facilitating consistent design in maritime workplaces. Furthermore, we use this concept to propose a design framework that paves the way for establishing new standards for AR user interface design in the maritime domain.

Traffic congestion and frequent traffic accidents have become the main problems affecting urban traffic. The effective location prediction of vehicle trajectory can help alleviate traffic congestion, reduce the occurrence of traffic accidents, and optimize the urban traffic system. Vehicle trajectory is closely related to the surrounding Point of Interest (POI). POI can be considered as the spatial feature and can be fused with trajectory points to improve prediction accuracy. A Local Dynamic Graph Spatiotemporal–Long Short-Term Memory (LDGST-LSTM) was proposed in this paper to extract and fuse the POI knowledge and realize next location prediction. POI semantic information was learned by constructing the traffic knowledge graph, and spatial and temporal features were extracted by combining the Graph Attention Network (GAT) and temporal attention mechanism. The effectiveness of LDGST-LSTM was verified on two datasets, including Chengdu taxi trajectory data in August 2014 and October 2018. The accuracy and robustness of the proposed model were significantly improved compared with the benchmark models. The effects of major components in the proposed model were also evaluated through an ablation experiment. Moreover, the weights of POI that influence location prediction were visualized to improve the interpretability of the proposed model.

The impact of the Coronavirus Disease 2019 (COVID-19) pandemic on microplastic (MP) occurrence in aquatic environments deserves an in-depth study. In this study, the occurrence of MPs and environmental flux of plastics before (2019) and during (2020 and 2021) the pandemic were comparatively investigated in various aquatic compartments in the Taihu Lake Basin in China. The field-based investigations from 2019 to 2021 for Taihu Lake have shown that, at the onset of the outbreak, the MP abundance declined at a rate of 62.3 %, but gradually recovered to the pre-pandemic level. However, the amount of plastics being released into aquatic environments showed a declining trend in 2020 and 2021 compared to those in 2019, with decrease rates of 13.7 % and 15.8 %, respectively. Characterization analysis of MP particles and source apportionment framework implied that while the contributions of tire abrasion and domestic waste to MP occurrence were depleted owing to the reduction in human activity during the pandemic, weathering and fragmentation of retained plastics contributed to the recovery of stored MPs. This study provides insights into the anthropogenic influences on MP occurrence, and supports policymakers in managing and controlling plastic contamination in large freshwater systems in the "new normal" phase. [Display omitted] • Microplastic abundance in Taihu Lake decreased then recovered during the pandemic. • Calculated plastic flux in Taihu Lake Basin declined during the pandemic. • COVID-19 waste contributed insignificantly to plastic flux in Taihu Lake Basin. • Plastic aging contributed to increase of microplastic abundance in the pandemic. • Aquaculture makes an important contribution to microplastics in Taihu Lake Basin. [ABSTRACT FROM AUTHOR]

• A method for quickly identifying individual buildings' function at large scale. • Verifying the effectiveness of built environment by migration experiments. • Successfully identifying the functions of 39 million buildings in China. As crucial geographical components shaping urban landscapes, defining the functions of buildings plays one of the pivotal roles in planning urban development and facilitating socio-economic human activities. Existing studies in large-scale mapping mainly ignore the environment around buildings, leading to insufficient meeting the demands of large-scale building-level mapping in certain disciplines. To abridge this gap, this article calculates the geometric characteristics of building footprint, the distances from buildings to adjacent objects, and the kernel densities of Point-of-Interest (POIs) to identify building main functions in three Chinese urban agglomerations (Beijing-Tianjin-Hebei Urban Agglomeration, Yangtze River Delta Urban Agglomeration, and Pearl River Delta Urban Agglomeration). Leveraging XGBoost, our models attained accuracies of 0.936, 0.934, and 0.940 in the three urban agglomerations, accompanied by kappa coefficients of 0.883, 0.868, and 0.891 respectively, suggesting their capability of identifying building functions in large-scale mapping. Furthermore, the conducted experiments on varying feature combinations and transferability highlight the significance of the built environment in enhancing classification accuracy. Additionally, the analysis of the classification results of buildings in the three urban agglomerations shows harmonized development strategies for Yangtze River Delta Urban Agglomeration and Pearl River Delta Urban Agglomeration, while cities within the Beijing-Tianjin-Hebei Urban Agglomeration do not show the same development strategies. All results demonstrate the feasibility of employing multi-source accessible data to efficiently categorize building functions over large areas in a cost-effective manner. This methodology can be replicated in China and even on a larger scale to offer insights into complex urban spaces and to help urban planners provide policy support such as old city renovations and new city planning. [ABSTRACT FROM AUTHOR]

To reduce traffic congestion, air pollution, and lost revenue due to wasted driving around looking for parking spaces, effective parking management has become a crucial issue in urban areas. Previous studies have shown that parking demand is related to the location of parking spaces/lots, parking fees, time spent looking for spaces, and various driver and environmental characteristics. However, there have been more studies of on-street rather than off-street parking. Also, the spatio-temporal variance between variables and turnover rate (such as the hours of operation for various types of Points of Interest (POIs) as well as the causes of bias estimators has been largely overlooked. To solve the above problems, the Geographical and Temporal Weighted Regression (GTWR) model was utilized in this study to predict the hourly parking turnover rate in off-street parking lots. The flexible coefficient setting of this model can be used to capture the spatial and temporal variance. In addition to this model, the Geographically Weighted Regression (GWR) and the Ordinary Least Squares (OLS) models were used as a basis for comparison. The study included 346 public off-street parking lots in Taipei and 10 types of nearby POIs. The study period was for 24 h on August 31, 2021. Due to the dissimilar trend of the turnover rate, the researchers separated all parking lots into three groups for regression analysis: those that experience a daytime decrease, remain stable, and those with an increase during the day. Our results show the following: (1) For the types of parking lots that experienced increases and decreases, the GTWR model performed best for the prediction of hourly turnover rate, while all models performed similarly for the prediction of the stable type parking lot. (2) With regard to related factors (the type 1 parking lot for example), parking lots in areas with more traditional markets, MRT stations, and with fewer schools, supermarkets, hotel bus stops, and lower parking fees tended to have higher turnover rates. (3) Incorporating a more precise POI dataset (the number and types of POIs as well as their business hours) and applying a suitable spatial temporal model improved the parking demand model's performance. However, the GTWR model's limitations may hamper its performance, especially with regard to analysis of the time-stable parking lots or variables. Future studies might include other datasets, such as nearby private parking lots or holiday data to improve the model fit. [ABSTRACT FROM AUTHOR]

Accurate qualitative and quantitative information on the characteristics of traffic noise exposure in densely populated urban areas is an important prerequisite for reasonable traffic noise control. The primary objective of this study is the development and application of a traffic noise exposure evaluation method based on points of interest (POIs). First, an automatic query arithmetic is used to acquire geospatial information, POIs data, building and network information from the webmap. Second, the attribute matrix of preprocessed POIs for the population is constructed. And the population distribution is obtained by principal component analysis (PCA) of POIs and Gaussian decomposition of demographic data. Then, the modified traffic noise line-source model is applied to calculate the noise distribution considering attenuation among buildings based on measured traffic flow parameters. Finally, with the help of the proposed noise evaluation indicators, and considering the noise function requirements (NFRs, which can be divided into four classes according to different area land-use types), traffic noise evaluation is realized. The proposed method is applied to a typical region with four NFR classes. It is concluded that the characteristics of traffic noise exposure are affected by traffic conditions, buildings, NFR classes and population distribution. And the crowds exposed to noise present aggregation effects, which are usually centered around specific buildings. In addition, POI types which people actives related suffer more serious noise exposure, and exposure is overestimated at low requirement regions without considering crowd distribution of the setting scenario. [Display omitted] • Principal component analysis distributes population based on Interest Points (POIs). • Traffic, buildings, Function Regions and population comprehensively affects noise exposure. • POI types which people actives related, suffer more serious noise exposure. • Exposure is overestimated at low requirement regions without considering crowd distribution. • Noise exposure presents aggregation effects, and centered on specific buildings. [ABSTRACT FROM AUTHOR]