Applied GeographyPub Date : 2025-03-25DOI: 10.1016/j.apgeog.2025.103605
Qi Long, Jun Ma
{"title":"Exploring urban environmental semantics for air quality prediction using explainable multi-view spatiotemporal graph neural networks","authors":"Qi Long, Jun Ma","doi":"10.1016/j.apgeog.2025.103605","DOIUrl":"10.1016/j.apgeog.2025.103605","url":null,"abstract":"<div><div>Accurate air quality forecasting is essential for urban management and public health, yet it remains challenging due to the complexity of spatiotemporal air pollution dynamics and the interplay of static and dynamic urban factors. Traditional models often neglect the influence of static urban drivers, such as built environment features, which are critical to understanding pollution patterns. Addressing this limitation, we propose a multi-view, multi-modal Spatio-Temporal Graph Neural Network (STGNN) framework that integrates dynamic pollution data with static urban environmental semantics to improve predictive performance and interpretability. By embedding static features, such as Points of Interest (POIs), into the graph structure and leveraging a self-attention mechanism, our model captures complex spatial dependencies and temporal dynamics. Furthermore, an integrated Explainer module enhances transparency by revealing the spatial and feature-level influences driving air quality predictions. Experimental results demonstrate that our approach not only achieves superior predictive accuracy compared to benchmark models but also provides actionable insights into the relationships between urban features and air quality. This study highlights the importance of integrating multi-modal data and interpretability in advancing air quality prediction, offering valuable implications for urban planning and pollution mitigation strategies.</div></div>","PeriodicalId":48396,"journal":{"name":"Applied Geography","volume":"178 ","pages":"Article 103605"},"PeriodicalIF":4.0,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143682286","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied GeographyPub Date : 2025-03-25DOI: 10.1016/j.apgeog.2025.103591
Laura Hostettler Macias, Emmanuel Ravalet, Patrick Rérat
{"title":"How does telework impact daily and residential mobilities: New geographies of working and living in Switzerland","authors":"Laura Hostettler Macias, Emmanuel Ravalet, Patrick Rérat","doi":"10.1016/j.apgeog.2025.103591","DOIUrl":"10.1016/j.apgeog.2025.103591","url":null,"abstract":"<div><div>The practice of telework has undergone a transformative shift, fundamentally reshaping work and lifestyle choices. Switzerland, like many other regions, experienced a remarkable acceleration of this shift, with the COVID-19 pandemic propelling telework from 25% of the workforce before the outbreak to 37.1% by the year 2022 (FSO, 2023). This surge in telework adoption has potentially enabled a re-evaluation of how people engage with their professional lives, offering new possibilities for individuals with diverse lifestyles and life course situations. This article explores the implications of telework on daily and residential mobility, focusing on the Swiss context. Our research addresses two key questions: Firstly, how does telework influence commuting patterns, and what are the resulting rebound effects on daily mobility. Secondly, what transformations occur in residential situations because of telework, and how do they influence mobility or immobility, and the choice of residence locations. To answer these questions, we analyze an ad hoc survey (n = 5′100). We will be discussing teleworking practices, socio-demographic factors, mobilities, and residential situations. Our central result is that telework reduces commuting frequencies while facilitating residential immobility but creating longer distances between workplaces and residences.</div></div>","PeriodicalId":48396,"journal":{"name":"Applied Geography","volume":"178 ","pages":"Article 103591"},"PeriodicalIF":4.0,"publicationDate":"2025-03-25","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143682285","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied GeographyPub Date : 2025-03-22DOI: 10.1016/j.apgeog.2025.103603
Juan Lin , Han Li , Shuyu Xing , Weiye Xiao
{"title":"Spatial adaptations in hospitality amid COVID-19: A case study of Xiamen's B&B sector","authors":"Juan Lin , Han Li , Shuyu Xing , Weiye Xiao","doi":"10.1016/j.apgeog.2025.103603","DOIUrl":"10.1016/j.apgeog.2025.103603","url":null,"abstract":"<div><div>Despite numerous studies on COVID-19's impact on the global hospitality industry, China's accommodation sector faced uniquely severe challenges due to the Zero-COVID policy, underscoring the need for a detailed quantitative analysis of how the pandemic reshaped the geography of the particularly vulnerable bed and breakfast (B&B) sector. This study employs Xiamen, a renowned tourist destination in China, as a case study to explore the pandemic's effects on the spatial dynamics of new, surviving, and closed B&Bs by comparing data from the 2018–2020 and 2020–2022 periods. Our findings indicate that despite a significant number of closures, the overarching spatial pattern of B&Bs in Xiamen has remained consistent. However, the emergence of new B&Bs has become more scattered, with a notable trend towards the suburbs, suggesting a dual trend of both reliance on and independence from tourist attractions. Moreover, the pandemic has significantly changed the locational preferences of B&Bs, shifting the focus from high-end to more ordinary tourism resources—such as from prioritizing natural amenities to emphasizing social factors.</div></div>","PeriodicalId":48396,"journal":{"name":"Applied Geography","volume":"178 ","pages":"Article 103603"},"PeriodicalIF":4.0,"publicationDate":"2025-03-22","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143682284","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied GeographyPub Date : 2025-03-19DOI: 10.1016/j.apgeog.2025.103600
David W.S. Wong , Fengxiu Zhang , Saba N. Siddiki , Chaowei Yang
{"title":"Spatial variabilities in factors affecting electric vehicle adoption across Virginia: A county-level analysis","authors":"David W.S. Wong , Fengxiu Zhang , Saba N. Siddiki , Chaowei Yang","doi":"10.1016/j.apgeog.2025.103600","DOIUrl":"10.1016/j.apgeog.2025.103600","url":null,"abstract":"<div><div>Adoption of electric vehicles (EV) has been increasing in recent years in the U.S. Studies have investigated the determinants of EV adoption, such as income and housing structure. However, few studies have examined the spatial variation in the effects of such factors on EV adoption rates. Using Virginia as a case, this study evaluates how the effects of factors commonly associated with EV adoption vary geographically and investigates the influence of two understudied factors — highway density and political preferences — at the county level. Using standard regression, spatial lag regression, and geographically weighted regression (GWR) models, this study assesses how highway density, percent of urban population, percent of 1-unit housing structures, commute time, percent of population 65 and older, median household income, and percent votes for the Republican candidate in 2020 affect EV adoption rates at the county level. Results show that highway density and urban environment are insignificant, and all other factors are significant based on standard and spatial lag regression models. However, GWR adds housing structure to the list of insignificant factors at the local scale, while the impacts of other significant factors vary across Virginia counties differently. Thus, local policies facilitating EV adoption may have different effectiveness levels across Virginia counties, a conclusion likely applicable to other states. The current study also ascertains the importance of commute time, income and age in affecting EV adoption, and highlights the significance of political preference, a factor that has not been assessed previously.</div></div>","PeriodicalId":48396,"journal":{"name":"Applied Geography","volume":"178 ","pages":"Article 103600"},"PeriodicalIF":4.0,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143643916","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied GeographyPub Date : 2025-03-19DOI: 10.1016/j.apgeog.2025.103601
Grzegorz Micek , Carles Méndez-Ortega , Martijn J. Smit
{"title":"Geographies of new ways of working","authors":"Grzegorz Micek , Carles Méndez-Ortega , Martijn J. Smit","doi":"10.1016/j.apgeog.2025.103601","DOIUrl":"10.1016/j.apgeog.2025.103601","url":null,"abstract":"<div><div>The geography of work has changed dramatically over the past years. The COVID-19 pandemic accelerated the flexibilization of labor, notably in spatial terms, but also in the way offices and other workplaces are organized. We discuss the role of new working spaces in the broader developments of digitization and flexibilization. The focus is on the factors behind the emergence of new workspaces and work models and their implications, including socio-economic inequalities. In particular, we set out a research agenda for studying the spatialities of new ways of working.</div></div>","PeriodicalId":48396,"journal":{"name":"Applied Geography","volume":"178 ","pages":"Article 103601"},"PeriodicalIF":4.0,"publicationDate":"2025-03-19","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143682283","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"OA","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied GeographyPub Date : 2025-03-18DOI: 10.1016/j.apgeog.2025.103598
Jason C. Senkbeil , Kathleen Sherman-Morris , S.M. Asger Ali , Cole Vaughn , Bernard Abubakari , Daniella Alaso
{"title":"Geographic constraints on rapid comprehension of tornado warning information","authors":"Jason C. Senkbeil , Kathleen Sherman-Morris , S.M. Asger Ali , Cole Vaughn , Bernard Abubakari , Daniella Alaso","doi":"10.1016/j.apgeog.2025.103598","DOIUrl":"10.1016/j.apgeog.2025.103598","url":null,"abstract":"<div><div>Sketch-mapping activities with in-person interviews were conducted with 65 participants in Alabama and Mississippi to explore how geographic awareness impacts risk perception for tornadoes. Geographic awareness metrics represented three variables: 1) the distance between their perceived home location and actual home location (P-A) on a blank map, 2) the correct percentage of counties (POC) labeled that bordered their home county, and 3) an assessment of the accuracy of their county shape (SHP) from their drawing. Results showed that participants who are more competent in one area of geographic awareness will also have some competency in the other measures. Accurate knowledge of tornado path direction was statistically significant with P-A distance, POC, SHP, and number of roads drawn. The demographic characteristics of participants and their geographic awareness scores were used with Principal Components Analysis and Cluster Analysis to detect which traits of participants were associated with better geographic awareness. Four distinct groups were identified with two groups having low or poor geographic awareness. The traits associated with these groups are nuanced. Of the four groups, the lowest ranking poor local geography group was characterized by the highest rate of home ownership, and was ranked second oldest, second in time lived in the county, and second in education, with higher racial and ethnic diversity than two groups. This suggests that experience, age, and education do not necessarily translate into knowing geographic information about the county or city. People with low geographic awareness are at a disadvantage when making protective action decisions during tornado warnings. More research is needed to examine the robustness of these results to determine best strategies for communicating information.</div></div>","PeriodicalId":48396,"journal":{"name":"Applied Geography","volume":"178 ","pages":"Article 103598"},"PeriodicalIF":4.0,"publicationDate":"2025-03-18","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143643915","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied GeographyPub Date : 2025-03-15DOI: 10.1016/j.apgeog.2025.103597
Gwanhui Han , Eunjung Yang
{"title":"How do multidimensional tourism factors affect community resilience?","authors":"Gwanhui Han , Eunjung Yang","doi":"10.1016/j.apgeog.2025.103597","DOIUrl":"10.1016/j.apgeog.2025.103597","url":null,"abstract":"<div><div>Community resilience is increasingly evaluated in light of growing uncertainties posed by disasters. While earlier research primarily focused on community-level factors, such as average income and education levels, recent studies have highlighted the importance of individual perceptions and industry contributions in shaping community resilience. Based on earlier discussions on the spatially diverse impacts of tourism on community resilience, this study investigates how individual- and industry-level factors in tourism contribute to community resilience over time and across regions. Using geographically weighted regression, we examined the spatially heterogeneous impacts of tourism factors on community resilience in tourism-dependent communities in Florida and the broader United States for 2015 and 2020. Notably, in contrast to national trends, excessive tourist congestion in Florida was not associated with a decline in community resilience, even when individual awareness of climate change was high. This indicates that raising awareness of climate change alone may be insufficient unless issues like tourist influx are directly addressed. Our findings emphasize the multidimensional nature of community resilience, advancing resilience theory and providing practical insights for localized strategies aimed at enhancing community resilience, particularly in tourism-dependent communities.</div></div>","PeriodicalId":48396,"journal":{"name":"Applied Geography","volume":"178 ","pages":"Article 103597"},"PeriodicalIF":4.0,"publicationDate":"2025-03-15","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143632175","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied GeographyPub Date : 2025-03-14DOI: 10.1016/j.apgeog.2025.103599
Yi Guo , Pengxin Chen , Yuanyuan Wan , Yiwen Zhu , Xianzhong Cao , Gang Zeng
{"title":"Technology transfer in asymmetric innovation corridors: Theory and empirical evidence from China","authors":"Yi Guo , Pengxin Chen , Yuanyuan Wan , Yiwen Zhu , Xianzhong Cao , Gang Zeng","doi":"10.1016/j.apgeog.2025.103599","DOIUrl":"10.1016/j.apgeog.2025.103599","url":null,"abstract":"<div><div>While top universities, tech giants, venture capitalists, and professional managers are pivotal in creating innovation corridors in Western developed countries, they are often lacking or scarce in emerging economies. China is currently developing an “asymmetric” innovation corridors model led by government policy, with the G60 Innovation Corridor as a noteworthy success story. However, this phenomenon has received limited theoretical attention. This paper conducts a social network analysis of technology transfer in strategic emerging industries along the G60 Innovation Corridor. We find that the scale of technology transfer from core cities to relatively less developed cities along the corridor is increasing, with numerous new technology transfer pathways emerging. Empirical findings further indicate that the government-led policy plays a significant role in this process. The specific internal mechanisms include the G60 Innovation Corridor policy's emphasis on integrating technology, digitalization, and finance, facilitating the agglomeration of high-tech enterprises, and enhancing innovation ecology (e.g., basic research, investment in scientific research, and openness to external influences). Moreover, our study reveals that policies related to the G60 Innovation Corridor not only facilitate firm-to-firm technology transfer but also enable technology transfer from scientific organizations (universities, research institutes) in core cities to firms in relatively less developed cities along the corridor.</div></div>","PeriodicalId":48396,"journal":{"name":"Applied Geography","volume":"178 ","pages":"Article 103599"},"PeriodicalIF":4.0,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143621169","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied GeographyPub Date : 2025-03-14DOI: 10.1016/j.apgeog.2025.103596
Wei Yang , Jun Fei , Jingjing Li , Wende Li , Xuefeng Xie
{"title":"Environmental determinants of dynamic jogging patterns: Insights from trajectory big data analysis and interpretable machine learning","authors":"Wei Yang , Jun Fei , Jingjing Li , Wende Li , Xuefeng Xie","doi":"10.1016/j.apgeog.2025.103596","DOIUrl":"10.1016/j.apgeog.2025.103596","url":null,"abstract":"<div><div>The dynamic patterns of leisure jogging profile the jogger-environment interactions. However, the dynamic patterns and their nonlinear associations with environmental factors are poorly explored. Therefore, we develop a framework to uncover the dynamic jogging patterns and interpret their nonlinear and interactive associations with environments. Initially, the bivariate time series clustering method discerns daily and weekly patterns from the integrated jogging flow and duration. Then, interpretable machine learning methods including CatBoost, SHAP, and ALE plots elucidate the nonlinear and interactive relationships. An empirical analysis of Beijing, China was conducted using multisource data. Our finding highlights that (1) five distinct daily and weekly jogging patterns were investigated for area zoning. These patterns show notable spatial-temporal disparities in jogging flow and duration. (2) Built environment (BE) and visual environment are crucial in shaping jogging, with accessibility and facilities being significant contributors. (3) Environmental variables show significant nonlinear and threshold effects on leisure jogging, which vary across jogging patterns and urban areas. (4) Interaction effects among environmental factors were investigated. BE factors like sports amenity exert more significant interactions. Importantly, incorporating geographic locations enhances model performance as it captures spatial effects. These findings can help planners design refined intervention strategies for leisure activities.</div></div>","PeriodicalId":48396,"journal":{"name":"Applied Geography","volume":"178 ","pages":"Article 103596"},"PeriodicalIF":4.0,"publicationDate":"2025-03-14","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143628763","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}
Applied GeographyPub Date : 2025-03-12DOI: 10.1016/j.apgeog.2025.103595
Haowei Mu , Shanchuan Guo , Xingang Zhang , Bo Yuan , Chunqiang Li , Peijun Du
{"title":"Quantifying the anthropogenic sensitivity of ecological patterns in arid urban agglomeration","authors":"Haowei Mu , Shanchuan Guo , Xingang Zhang , Bo Yuan , Chunqiang Li , Peijun Du","doi":"10.1016/j.apgeog.2025.103595","DOIUrl":"10.1016/j.apgeog.2025.103595","url":null,"abstract":"<div><div>Human activities have profoundly reshaped fundamental ecological processes, pushing ecosystems toward unsustainable trajectories, particularly in the ecologically fragile regions such as Hohhot-Baotou-Ordos-Yulin urban agglomeration. To address these challenges, a quantitative framework was developed to evaluate anthropogenic sensitivity of ecological patterns. Functional connectivity was modeled using an omnidirectional circuit model to represent regional ecological patterns, with landscape elements extracted through morphological analysis. The mechanisms, intensity and pathways of anthropogenic sensitivity were explored using Geodetector and structural equation modeling, identifying habitat quality as a key mediating factor. The findings indicate that improving habitat quality greatly enhances omnidirectional connectivity. Among landscape elements, islets exhibit lower connectivity than the edges of core areas, despite higher resistance being assigned to the edges. In the Mu Us Desert, strip-like corridors serve as connectors but remain fragile, whereas in the Kubuqi Desert, patch-like corridors primarily function as barriers. Habitat quality and cultivated land emerge as dominant drivers of omnidirectional connectivity, while population and bare land contribute negatively through interactive effects that exceed the impacts of individual factors. Habitat quality directly enhances omnidirectional connectivity, with a path coefficient of 0.67. Bare land negatively impacts habitat quality, with a coefficient of −0.65, while cultivated land has a negative effect on grassland, with a coefficient of −0.82, indirectly shape regional ecological patterns. This study provides a quantitative understanding of the mechanisms driving anthropogenic sensitivity in ecological patterns, offering valuable insights to guide and optimize ecological spatial planning in arid urban agglomerations.</div></div>","PeriodicalId":48396,"journal":{"name":"Applied Geography","volume":"178 ","pages":"Article 103595"},"PeriodicalIF":4.0,"publicationDate":"2025-03-12","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"143600474","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":2,"RegionCategory":"地球科学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}