Competition among tourism enterprises is an ineluctable component of sustainable tourism growth, requiring comprehensive studies to understand its dynamic and develop appropriate strategies. The literature employs text mining or statistical analyses to identify correlations between tourism areas as competitive relationships. However, this approach may not be fully applicable, due to the sparsity of crucial coexistence phenomena, and may fail to investigate fine-grained attractions' competition inside destination using large-scale geospatial data. To overcome the limitations, this study proposes a knowledge-driven competitive intelligence framework for tourism management, utilizing knowledge graph (KG) construction and inference technologies. First, multi-mode heterogeneous tourism data are integrated into a unified KG, including tourist check-in, online text, and basic geographic information. Second, the spatial-dependent GNN-based model absorbing abundant spatial semantic knowledge from tourism-oriented KG can enhance the performance of competition reasoning. Third, with multiple analyses via symbolic queries on KG, a comprehensive panorama of competition situations can be revealed.
旅游企业之间的竞争是旅游业可持续增长不可避免的组成部分，需要进行全面研究以了解其动态并制定适当的战略。文献采用文本挖掘或统计分析的方法来确定旅游领域之间的相关竞争关系。然而，由于关键共存现象的稀缺性，这种方法可能并不完全适用，也可能无法利用大规模地理空间数据研究目的地内部细粒度的景点竞争关系。为了克服上述局限性，本研究利用知识图谱（KG）构建和推理技术，提出了一种知识驱动的旅游管理竞争情报框架。首先，将多模式异构旅游数据整合到统一的知识图谱中，包括游客签到、在线文本和基础地理信息。其次，基于空间依赖的 GNN 模型从面向旅游的知识图谱中吸收了丰富的空间语义知识，从而提高了竞争推理的性能。其三，通过符号查询对 KG 进行多重分析，可以揭示全面的竞争情况全景。
{"title":"Knowledge-driven spatial competitive intelligence for tourism","authors":"Jialiang Gao, Peng Peng, Feng Lu, Shu Wang, Xiaowei Xie, Christophe Claramunt","doi":"10.1111/tgis.13145","DOIUrl":"https://doi.org/10.1111/tgis.13145","url":null,"abstract":"Competition among tourism enterprises is an ineluctable component of sustainable tourism growth, requiring comprehensive studies to understand its dynamic and develop appropriate strategies. The literature employs text mining or statistical analyses to identify correlations between tourism areas as competitive relationships. However, this approach may not be fully applicable, due to the sparsity of crucial coexistence phenomena, and may fail to investigate fine-grained attractions' competition inside destination using large-scale geospatial data. To overcome the limitations, this study proposes a knowledge-driven competitive intelligence framework for tourism management, utilizing knowledge graph (KG) construction and inference technologies. First, multi-mode heterogeneous tourism data are integrated into a unified KG, including tourist check-in, online text, and basic geographic information. Second, the spatial-dependent GNN-based model absorbing abundant spatial semantic knowledge from tourism-oriented KG can enhance the performance of competition reasoning. Third, with multiple analyses via symbolic queries on KG, a comprehensive panorama of competition situations can be revealed.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139981253","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Zhong Wang, Kai Cao, Yu Lung Marcus Chiu, Qiushi Feng
Primary healthcare plays a pivotal role in enhancing health conditions. In Singapore, such services are predominantly manifested through the implementation of the Community Health Assistance Scheme (CHAS). CHAS is an initiative aimed at providing fundamental preventive and therapeutic services, especially for those seniors and low-income adults with chronic diseases. In spite of considerable efforts in policy and research in this domain, there is a dearth of studies focusing on the spatial optimization of these primary healthcare services. In this study, an innovative multi-objective medical service facility siting model has been developed based on coarse-grained parallel genetic algorithm to address the intricate challenges associated with the optimization of locations for CHAS clinics. The proposed optimization model aims to simultaneously maximize accessibility, minimize inequity, and minimize the number of clinics. The successful application of this model in the siting of CHAS clinics in Singapore demonstrates its effectiveness in enhancing residents' access to healthcare services. Apart from its novel academic contributions to the field of spatial optimization of primary healthcare facilities in general, we have also discussed the inherent limitations and identified certain aspects as the future directions of this research.
{"title":"Spatial multi-objective optimization of primary healthcare facilities: A case study in Singapore","authors":"Zhong Wang, Kai Cao, Yu Lung Marcus Chiu, Qiushi Feng","doi":"10.1111/tgis.13147","DOIUrl":"https://doi.org/10.1111/tgis.13147","url":null,"abstract":"Primary healthcare plays a pivotal role in enhancing health conditions. In Singapore, such services are predominantly manifested through the implementation of the Community Health Assistance Scheme (CHAS). CHAS is an initiative aimed at providing fundamental preventive and therapeutic services, especially for those seniors and low-income adults with chronic diseases. In spite of considerable efforts in policy and research in this domain, there is a dearth of studies focusing on the spatial optimization of these primary healthcare services. In this study, an innovative multi-objective medical service facility siting model has been developed based on coarse-grained parallel genetic algorithm to address the intricate challenges associated with the optimization of locations for CHAS clinics. The proposed optimization model aims to simultaneously maximize accessibility, minimize inequity, and minimize the number of clinics. The successful application of this model in the siting of CHAS clinics in Singapore demonstrates its effectiveness in enhancing residents' access to healthcare services. Apart from its novel academic contributions to the field of spatial optimization of primary healthcare facilities in general, we have also discussed the inherent limitations and identified certain aspects as the future directions of this research.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-02-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139981268","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
As one of the classic tasks in information retrieval, the core of image retrieval is to identify the images sharing similar features with a query image, aiming to enable users to find the required information from a large number of images conveniently. Street view image retrieval, in particular, finds extensive applications in many fields, such as improvements to navigation and mapping services, formulation of urban development planning scheme, and analysis of historical evolution of buildings. However, the intricate foreground and background details in street view images, coupled with a lack of attribute annotations, render it among the most challenging issues in practical applications. Current image retrieval research mainly uses the visual model that is completely dependent on the image visual features, and the multimodal learning model that necessitates additional data sources (e.g., annotated text). Yet, creating annotated datasets is expensive, and street view images, which contain a large amount of scene texts themselves, are often unannotated. Therefore, this paper proposes a deep unsupervised learning algorithm that combines visual and text features from image data for improving the accuracy of street view image retrieval. Specifically, we employ text detection algorithms to identify scene text, utilize the Pyramidal Histogram of Characters encoding predictor model to extract text information from images, deploy deep convolutional neural networks for visual feature extraction, and incorporate a contrastive learning module for image retrieval. Upon testing across three street view image datasets, the results demonstrate that our model holds certain advantages over the state‐of‐the‐art multimodal models pre‐trained on extensive datasets, characterized by fewer parameters and lower floating point operations. Code and data are available at https://github.com/nwuSY/svtRetrieval.
{"title":"Multimodal learning with only image data: A deep unsupervised model for street view image retrieval by fusing visual and scene text features of images","authors":"Shangyou Wu, Wenhao Yu, Yifan Zhang, Mengqiu Huang","doi":"10.1111/tgis.13146","DOIUrl":"https://doi.org/10.1111/tgis.13146","url":null,"abstract":"As one of the classic tasks in information retrieval, the core of image retrieval is to identify the images sharing similar features with a query image, aiming to enable users to find the required information from a large number of images conveniently. Street view image retrieval, in particular, finds extensive applications in many fields, such as improvements to navigation and mapping services, formulation of urban development planning scheme, and analysis of historical evolution of buildings. However, the intricate foreground and background details in street view images, coupled with a lack of attribute annotations, render it among the most challenging issues in practical applications. Current image retrieval research mainly uses the visual model that is completely dependent on the image visual features, and the multimodal learning model that necessitates additional data sources (e.g., annotated text). Yet, creating annotated datasets is expensive, and street view images, which contain a large amount of scene texts themselves, are often unannotated. Therefore, this paper proposes a deep unsupervised learning algorithm that combines visual and text features from image data for improving the accuracy of street view image retrieval. Specifically, we employ text detection algorithms to identify scene text, utilize the Pyramidal Histogram of Characters encoding predictor model to extract text information from images, deploy deep convolutional neural networks for visual feature extraction, and incorporate a contrastive learning module for image retrieval. Upon testing across three street view image datasets, the results demonstrate that our model holds certain advantages over the state‐of‐the‐art multimodal models pre‐trained on extensive datasets, characterized by fewer parameters and lower floating point operations. Code and data are available at <jats:ext-link xmlns:xlink=\"http://www.w3.org/1999/xlink\" xlink:href=\"https://github.com/nwuSY/svtRetrieval\">https://github.com/nwuSY/svtRetrieval</jats:ext-link>.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139948560","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Fenli Jia, Jian Yang, Linfang Ding, Guangxia Wang, Guomin Song
Map images with various themes and cartographic representations have become ubiquitous on the Internet. Such ubiquitously and openly accessible data, named ubiquitous map images in this study, are a potential resource for many geographic information applications such as cartographic design. However, there is a semantic gap between the simple physical form and the complex connotation of ubiquitous map images, which hinders their further applications. To mitigate such barrier, this article develops an ontology‐based semantic description model for ubiquitous map images. First, we discuss the design concerns and principles of the semantic description model of ubiquitous map images. Second, three semantic layers of the semantic description model are proposed, that is, image semantic description layer, cognitive tool layer, and information source layer, and detailed semantic description items are defined for each layer. Furthermore, a formalized semantic description model for ubiquitous map images is developed using ontology construction tools, which lays the foundation for automated and fine‐grained reasoning with the information embedded in map images. We construct a small test dataset consisting of weather maps, and use three types of constraints, namely “time‐topic,” “region‐topic,” and “map auxiliary elements” for the semantic retrieval experiments. The experiments show that the proposed semantic ontology model can enable complex semantic retrieval of ubiquitous map images. Finally, the scalability of the model is discussed from three perspectives: the depth of description, the combination with intelligent methods, and the integration with other open knowledge bases. The proposed model provides a semantic label system for applying data‐driven approaches to decode ubiquitous map images, which also paves the path to the development of cartographic theory in the era of information and communications technologies.
{"title":"An ontology‐based semantic description model of ubiquitous map images","authors":"Fenli Jia, Jian Yang, Linfang Ding, Guangxia Wang, Guomin Song","doi":"10.1111/tgis.13144","DOIUrl":"https://doi.org/10.1111/tgis.13144","url":null,"abstract":"Map images with various themes and cartographic representations have become ubiquitous on the Internet. Such ubiquitously and openly accessible data, named ubiquitous map images in this study, are a potential resource for many geographic information applications such as cartographic design. However, there is a semantic gap between the simple physical form and the complex connotation of ubiquitous map images, which hinders their further applications. To mitigate such barrier, this article develops an ontology‐based semantic description model for ubiquitous map images. First, we discuss the design concerns and principles of the semantic description model of ubiquitous map images. Second, three semantic layers of the semantic description model are proposed, that is, image semantic description layer, cognitive tool layer, and information source layer, and detailed semantic description items are defined for each layer. Furthermore, a formalized semantic description model for ubiquitous map images is developed using ontology construction tools, which lays the foundation for automated and fine‐grained reasoning with the information embedded in map images. We construct a small test dataset consisting of weather maps, and use three types of constraints, namely “time‐topic,” “region‐topic,” and “map auxiliary elements” for the semantic retrieval experiments. The experiments show that the proposed semantic ontology model can enable complex semantic retrieval of ubiquitous map images. Finally, the scalability of the model is discussed from three perspectives: the depth of description, the combination with intelligent methods, and the integration with other open knowledge bases. The proposed model provides a semantic label system for applying data‐driven approaches to decode ubiquitous map images, which also paves the path to the development of cartographic theory in the era of information and communications technologies.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139948399","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Youjun Tu, Zihan Shu, Wenjun Wu, Zongyi He, Junli Li
With accelerating globalization, the complexity of the global grain trade network structure is increasing. Traditional network analysis approaches have certain limitations in capturing these dynamic changes and hidden topological structures in data. Based on global import and export trade data for rice, wheat, and corn from 1988 to 2022, this study has proposed a novel method for the topological clustering of temporal multilayer networks based on topological data analysis in order to systematically assess the topological structure evolution of temporal multilayer networks. The results indicate that different agricultural trade networks reveal hidden clustering characteristics in different years. In addition, this study combines principles from landscape ecology to construct a dynamic community spatiotemporal change model of grain trade networks, aiming to comprehensively reveal potential patterns and dynamic trends in grain trade networks and provide valuable information for grain trade decision‐making.
{"title":"Spatiotemporal analysis of global grain trade multilayer networks considering topological clustering","authors":"Youjun Tu, Zihan Shu, Wenjun Wu, Zongyi He, Junli Li","doi":"10.1111/tgis.13149","DOIUrl":"https://doi.org/10.1111/tgis.13149","url":null,"abstract":"With accelerating globalization, the complexity of the global grain trade network structure is increasing. Traditional network analysis approaches have certain limitations in capturing these dynamic changes and hidden topological structures in data. Based on global import and export trade data for rice, wheat, and corn from 1988 to 2022, this study has proposed a novel method for the topological clustering of temporal multilayer networks based on topological data analysis in order to systematically assess the topological structure evolution of temporal multilayer networks. The results indicate that different agricultural trade networks reveal hidden clustering characteristics in different years. In addition, this study combines principles from landscape ecology to construct a dynamic community spatiotemporal change model of grain trade networks, aiming to comprehensively reveal potential patterns and dynamic trends in grain trade networks and provide valuable information for grain trade decision‐making.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-02-24","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139948473","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The use of GIS to enhance student learning in geographical education has garnered broad recognition. Notwithstanding this, the diffusion of GIS technology into class teaching has been slow. This study endeavored to examine the effects of GIS usage in air pollution teaching on learning outcomes of secondary school students. To this end, two parallel classes in the same academic year were chosen as the control and experimental groups. A quasi‐experimental research design was used to compare the learning outcomes of the experimental group who were exposed to the use of GIS in air pollution teaching with those of the control group who were not. The results show that GIS‐based teaching does lead to improvement in students' learning outcomes, although not uniformly. More specifically, GIS‐based teaching enhances high‐order cognitive abilities related to application and analysis, highlighting the effectiveness of GIS as a tool in educational settings, especially for developing advanced cognitive abilities.
{"title":"Does the use of GIS in geographical education yield better learning outcomes? Evidence from a quasi‐experimental study on air pollution teaching","authors":"Daihu Yang, Chuanbing Wang, Liqing Qian","doi":"10.1111/tgis.13142","DOIUrl":"https://doi.org/10.1111/tgis.13142","url":null,"abstract":"The use of GIS to enhance student learning in geographical education has garnered broad recognition. Notwithstanding this, the diffusion of GIS technology into class teaching has been slow. This study endeavored to examine the effects of GIS usage in air pollution teaching on learning outcomes of secondary school students. To this end, two parallel classes in the same academic year were chosen as the control and experimental groups. A quasi‐experimental research design was used to compare the learning outcomes of the experimental group who were exposed to the use of GIS in air pollution teaching with those of the control group who were not. The results show that GIS‐based teaching does lead to improvement in students' learning outcomes, although not uniformly. More specifically, GIS‐based teaching enhances high‐order cognitive abilities related to application and analysis, highlighting the effectiveness of GIS as a tool in educational settings, especially for developing advanced cognitive abilities.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-02-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139948471","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Pedestrian trajectory data, which can be used to mine pedestrian motion patterns or to model pedestrian dynamics, is crucial for indoor location-based service studies and applications. However, researchers are faced with the challenges of data shortage and privacy restrictions when using pedestrian trajectory data. We present an Indoor Pedestrian Trajectory Generator (IPTG), which is a novel deep learning model to synthesize pedestrian trajectory data. IPTG first produces feature sequences that encode the spatial–temporal and semantic features of the walking process and then interpolates them into complete trajectories using A* and perturbation algorithms. IPTG has specially designed loss functions that preserve topological constraints and semantic characteristics. Incorporating the prior knowledge of environment constraints and pedestrian walking patterns, the IPTG model is capable of generating topologically and logically sound indoor pedestrian trajectories. We evaluated the synthesized trajectories based on multiple metrics and examined the generated trajectories qualitatively. The results show that IPTG outperforms several baselines, demonstrating its ability to generate semantically meaningful and spatiotemporally coherent trajectories.
{"title":"A deep pedestrian trajectory generator for complex indoor environments","authors":"Zhenxuan He, Tong Zhang, Wangshu Wang, Jing Li","doi":"10.1111/tgis.13143","DOIUrl":"https://doi.org/10.1111/tgis.13143","url":null,"abstract":"Pedestrian trajectory data, which can be used to mine pedestrian motion patterns or to model pedestrian dynamics, is crucial for indoor location-based service studies and applications. However, researchers are faced with the challenges of data shortage and privacy restrictions when using pedestrian trajectory data. We present an <i>Indoor Pedestrian Trajectory Generator</i> (IPTG), which is a novel deep learning model to synthesize pedestrian trajectory data. IPTG first produces feature sequences that encode the spatial–temporal and semantic features of the walking process and then interpolates them into complete trajectories using A* and perturbation algorithms. IPTG has specially designed loss functions that preserve topological constraints and semantic characteristics. Incorporating the prior knowledge of environment constraints and pedestrian walking patterns, the IPTG model is capable of generating topologically and logically sound indoor pedestrian trajectories. We evaluated the synthesized trajectories based on multiple metrics and examined the generated trajectories qualitatively. The results show that IPTG outperforms several baselines, demonstrating its ability to generate semantically meaningful and spatiotemporally coherent trajectories.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-02-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139771713","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Reza Mohammadi, Mohammad Taleai, Philipp Otto, Monika Sester
Contemporary spatial statistics studies often underestimate the complexity of road networks, thereby inhibiting the strategic development of effective interventions for car accidents. In response to this limitation, the primary objective of this study is to enhance the spatiotemporal analysis of urban crash data. We introduce an innovative spatial-temporal weight matrix (STWM) for this purpose. The STWM integrates external covariates, including road network topological measurements and economic variables, offering a more comprehensive view of the spatiotemporal dependence of road accidents. To evaluate the functionality of the presented STWM, random effect eigenvector spatial filtering analysis is employed on Boston's traffic accident data from January to March 2016. The STWM improves analysis, surpassing distance-based SWM with a lower residual standard error of 0.209 and a higher adjusted R2 of 0.417. Furthermore, the study emphasizes the influence of road length on crash incidents, spatially and temporally, with random standard errors of 0.002 for spatial effects and 0.026 for non-spatial effects. This is particularly evident in the north and center of the study area during specific periods. This information can help decision-makers develop more effective urban development models and reduce future crash risks.
{"title":"Analyzing urban crash incidents: An advanced endogenous approach using spatiotemporal weights matrix","authors":"Reza Mohammadi, Mohammad Taleai, Philipp Otto, Monika Sester","doi":"10.1111/tgis.13138","DOIUrl":"https://doi.org/10.1111/tgis.13138","url":null,"abstract":"Contemporary spatial statistics studies often underestimate the complexity of road networks, thereby inhibiting the strategic development of effective interventions for car accidents. In response to this limitation, the primary objective of this study is to enhance the spatiotemporal analysis of urban crash data. We introduce an innovative spatial-temporal weight matrix (STWM) for this purpose. The STWM integrates external covariates, including road network topological measurements and economic variables, offering a more comprehensive view of the spatiotemporal dependence of road accidents. To evaluate the functionality of the presented STWM, random effect eigenvector spatial filtering analysis is employed on Boston's traffic accident data from January to March 2016. The STWM improves analysis, surpassing distance-based SWM with a lower residual standard error of 0.209 and a higher adjusted <i>R</i><sup>2</sup> of 0.417. Furthermore, the study emphasizes the influence of road length on crash incidents, spatially and temporally, with random standard errors of 0.002 for spatial effects and 0.026 for non-spatial effects. This is particularly evident in the north and center of the study area during specific periods. This information can help decision-makers develop more effective urban development models and reduce future crash risks.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-02-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139771708","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
The reliability of hourly PM2.5 data obtained from air quality monitoring stations is compromised as a result of the missing values, thereby impeding the thorough examination of crucial information. In this paper, we present a spatiotemporal (ST) stacking machine learning (ML) method with daily-cycle restrictions for reconstructing missing hourly PM2.5 records. First, the ST neighbors for the target station with missing values are selected at a daily scale. Subsequently, the non-null data within the ST neighbors undergo an iterative P-BSHADE interpolation process for re-interpolation. Next, a stacking ML model is constructed using the re-interpolation values and several environmental factors associated with PM2.5 as the predictors, while the observed PM2.5 is taken as the independent variable. Finally, the missing values are reconstructed by inputting the predictors into the trained stacking model. The study utilized hourly PM2.5 data in the Beijing-Tianjin-Hebei region as a case study to assess the effectiveness of the proposed method, using daily missing ratios of 10%, 30%, and 50%, respectively. The accuracy of the proposed method was then compared to four contemporary ST interpolation methods. The results indicate that the proposed method exhibits superior performance compared to the classical methods. Specifically, it achieves a reduction in the average root mean square error and mean absolute error by at least 40.6% and 40.1%, respectively. Additionally, the proposed method demonstrates the successful recovery of extreme values in the hourly PM2.5 records, in contrast to the classical methods which often exhibit a tendency to overestimate low values and underestimate high values. Overall, the proposed method presents a viable and efficient approach to recover missing values in the hourly PM2.5 records that demonstrate evident daily periodic patterns.
从空气质量监测站获得的每小时 PM2.5 数据由于存在缺失值，其可靠性大打折扣，从而阻碍了对关键信息的全面研究。本文提出了一种具有日周期限制的时空（ST）堆叠机器学习（ML）方法，用于重建缺失的 PM2.5 小时记录。首先，以日为尺度选择有缺失值的目标站的 ST 邻居。随后，对 ST 邻域内的非空数据进行迭代 P-BSHADE 插值，以重新插值。然后，使用重新插值和与 PM2.5 相关的几个环境因素作为预测因子，同时将观测到的 PM2.5 作为自变量，构建堆叠 ML 模型。最后，通过将预测值输入训练有素的堆叠模型来重建缺失值。研究利用京津冀地区每小时的 PM2.5 数据作为案例，分别使用 10%、30% 和 50%的日缺失率来评估建议方法的有效性。然后，将所提方法的准确性与四种当代 ST 插值方法进行了比较。结果表明，与传统方法相比，建议的方法表现出更优越的性能。具体来说，它将平均均方根误差和平均绝对误差分别降低了至少 40.6% 和 40.1%。此外，提议的方法成功地恢复了每小时 PM2.5 记录中的极端值，而传统方法往往表现出高估低值和低估高值的倾向。总之，建议的方法是恢复 PM2.5 小时记录中缺失值的一种可行而有效的方法，这些记录显示出明显的日周期模式。
{"title":"Spatiotemporal stacking method with daily-cycle restrictions for reconstructing missing hourly PM2.5 records","authors":"Chuanfa Chen, Kunyu Li","doi":"10.1111/tgis.13141","DOIUrl":"https://doi.org/10.1111/tgis.13141","url":null,"abstract":"The reliability of hourly PM2.5 data obtained from air quality monitoring stations is compromised as a result of the missing values, thereby impeding the thorough examination of crucial information. In this paper, we present a spatiotemporal (ST) stacking machine learning (ML) method with daily-cycle restrictions for reconstructing missing hourly PM2.5 records. First, the ST neighbors for the target station with missing values are selected at a daily scale. Subsequently, the non-null data within the ST neighbors undergo an iterative P-BSHADE interpolation process for re-interpolation. Next, a stacking ML model is constructed using the re-interpolation values and several environmental factors associated with PM2.5 as the predictors, while the observed PM2.5 is taken as the independent variable. Finally, the missing values are reconstructed by inputting the predictors into the trained stacking model. The study utilized hourly PM2.5 data in the Beijing-Tianjin-Hebei region as a case study to assess the effectiveness of the proposed method, using daily missing ratios of 10%, 30%, and 50%, respectively. The accuracy of the proposed method was then compared to four contemporary ST interpolation methods. The results indicate that the proposed method exhibits superior performance compared to the classical methods. Specifically, it achieves a reduction in the average root mean square error and mean absolute error by at least 40.6% and 40.1%, respectively. Additionally, the proposed method demonstrates the successful recovery of extreme values in the hourly PM2.5 records, in contrast to the classical methods which often exhibit a tendency to overestimate low values and underestimate high values. Overall, the proposed method presents a viable and efficient approach to recover missing values in the hourly PM2.5 records that demonstrate evident daily periodic patterns.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-02-13","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139771676","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Ramón Molinero-Parejo, Francisco Aguilera-Benavente, Montserrat Gómez-Delgado
Descriptive scenarios about the possible evolution of land use in our cities are essential instruments in urban planning. Although the simulation of these scenarios has enormous potential, further characterization is needed in order to be able to evaluate and compare them so as to provide more effective support for public policy. One of the most commonly used tools for assessing these scenarios is spatial moving-window metrics, a useful mechanism for extracting accurate information from simulated land-use maps on urban diversity and urban growth patterns. This article seeks to explore this question further and has two main aims. First, to develop and implement vSHEI and vLEI, two multiscale composition and configuration vector moving-window metrics for calculating urban diversity and urban growth patterns. Second, to test these metrics using the spatially explicit simulation of three prospective scenarios in the Henares Corridor (Spain), comparing the results and analyzing how well the scenario narratives match their spatial configuration, as measured using vSHEI and vLEI. Via the implementation of vSHEI and vLEI, we obtained urban diversity and urban expansion values at a local level, offering more precise and more realistic, mappable information on the composition and configuration of urban land use than that provided by raster metrics or by vector Patch-Matrix model metrics. We also used these metrics to test whether the simulated scenarios matched their description in the narrative storylines. Our results demonstrate the potential of vector moving-window metrics for characterizing the urban patterns that might develop under different scenarios at the parcel level.
{"title":"Adapting moving-window metrics to vector datasets for the characterization and comparison of simulated urban scenarios","authors":"Ramón Molinero-Parejo, Francisco Aguilera-Benavente, Montserrat Gómez-Delgado","doi":"10.1111/tgis.13139","DOIUrl":"https://doi.org/10.1111/tgis.13139","url":null,"abstract":"Descriptive scenarios about the possible evolution of land use in our cities are essential instruments in urban planning. Although the simulation of these scenarios has enormous potential, further characterization is needed in order to be able to evaluate and compare them so as to provide more effective support for public policy. One of the most commonly used tools for assessing these scenarios is spatial moving-window metrics, a useful mechanism for extracting accurate information from simulated land-use maps on urban diversity and urban growth patterns. This article seeks to explore this question further and has two main aims. First, to develop and implement vSHEI and vLEI, two multiscale composition and configuration vector moving-window metrics for calculating urban diversity and urban growth patterns. Second, to test these metrics using the spatially explicit simulation of three prospective scenarios in the Henares Corridor (Spain), comparing the results and analyzing how well the scenario narratives match their spatial configuration, as measured using vSHEI and vLEI. Via the implementation of vSHEI and vLEI, we obtained urban diversity and urban expansion values at a local level, offering more precise and more realistic, mappable information on the composition and configuration of urban land use than that provided by raster metrics or by vector Patch-Matrix model metrics. We also used these metrics to test whether the simulated scenarios matched their description in the narrative storylines. Our results demonstrate the potential of vector moving-window metrics for characterizing the urban patterns that might develop under different scenarios at the parcel level.","PeriodicalId":47842,"journal":{"name":"Transactions in GIS","volume":null,"pages":null},"PeriodicalIF":2.4,"publicationDate":"2024-02-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"139771711","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":3,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
京公网安备 11010802042870号
京ICP备2023020795号-1
扫码关注我们
求助内容：
应助结果提醒方式：