空间结构如何影响心理修复?基于图神经网络和街景图像的方法

IF 7.9 1区 环境科学与生态学 Q1 ECOLOGY Landscape and Urban Planning Pub Date : 2024-08-01 DOI:10.1016/j.landurbplan.2024.105171
{"title":"空间结构如何影响心理修复?基于图神经网络和街景图像的方法","authors":"","doi":"10.1016/j.landurbplan.2024.105171","DOIUrl":null,"url":null,"abstract":"<div><p>The Attention Restoration Theory (ART) proposed four essential indicators (being away, extent, fascinating, and compatibility) for understanding urban and natural restoration quality. However, previous studies have overlooked the impact of spatial structure (the visual relationships between scene entities) and neighboring environments on restoration quality as they mostly relied on isolated questionnaires or images. This study introduces a spatial-dependent graph neural networks (GNNs) approach to address this gap and explore the relationship between spatial structure and restoration quality at a city scale. Two types of graphs were constructed: street-level graphs using sequential street view images (SVIs) to capture visual relationships between entities and represent spatial structure, and city-level graphs modeling the topological relationships of roads to capture the spatial features of neighboring entities, integrating perceptual, spatial, and socioeconomic features to measure restoration quality. The results demonstrated that spatial-dependent GNNs outperform traditional models, achieving an accuracy (Acc) of 0.742 and an F1 score of 0.740, indicating their exceptional ability to capture features of adjacent spaces. Ablation experiments further revealed the substantial positive impact of spatial structure features on the predictive performance for restoration quality. Moreover, the study highlighted the greater significance of naturally relevant entities (e.g., trees) compared to artificial entities (e.g., buildings) in relation to high restoration quality. This study clarifies the association between spatial structure and restoration quality, providing a new perspective to improve urban well-being in the future.</p></div>","PeriodicalId":54744,"journal":{"name":"Landscape and Urban Planning","volume":null,"pages":null},"PeriodicalIF":7.9000,"publicationDate":"2024-08-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":"0","resultStr":"{\"title\":\"How does spatial structure affect psychological restoration? A method based on graph neural networks and street view imagery\",\"authors\":\"\",\"doi\":\"10.1016/j.landurbplan.2024.105171\",\"DOIUrl\":null,\"url\":null,\"abstract\":\"<div><p>The Attention Restoration Theory (ART) proposed four essential indicators (being away, extent, fascinating, and compatibility) for understanding urban and natural restoration quality. However, previous studies have overlooked the impact of spatial structure (the visual relationships between scene entities) and neighboring environments on restoration quality as they mostly relied on isolated questionnaires or images. This study introduces a spatial-dependent graph neural networks (GNNs) approach to address this gap and explore the relationship between spatial structure and restoration quality at a city scale. Two types of graphs were constructed: street-level graphs using sequential street view images (SVIs) to capture visual relationships between entities and represent spatial structure, and city-level graphs modeling the topological relationships of roads to capture the spatial features of neighboring entities, integrating perceptual, spatial, and socioeconomic features to measure restoration quality. The results demonstrated that spatial-dependent GNNs outperform traditional models, achieving an accuracy (Acc) of 0.742 and an F1 score of 0.740, indicating their exceptional ability to capture features of adjacent spaces. Ablation experiments further revealed the substantial positive impact of spatial structure features on the predictive performance for restoration quality. Moreover, the study highlighted the greater significance of naturally relevant entities (e.g., trees) compared to artificial entities (e.g., buildings) in relation to high restoration quality. This study clarifies the association between spatial structure and restoration quality, providing a new perspective to improve urban well-being in the future.</p></div>\",\"PeriodicalId\":54744,\"journal\":{\"name\":\"Landscape and Urban Planning\",\"volume\":null,\"pages\":null},\"PeriodicalIF\":7.9000,\"publicationDate\":\"2024-08-01\",\"publicationTypes\":\"Journal Article\",\"fieldsOfStudy\":null,\"isOpenAccess\":false,\"openAccessPdf\":\"\",\"citationCount\":\"0\",\"resultStr\":null,\"platform\":\"Semanticscholar\",\"paperid\":null,\"PeriodicalName\":\"Landscape and Urban Planning\",\"FirstCategoryId\":\"93\",\"ListUrlMain\":\"https://www.sciencedirect.com/science/article/pii/S0169204624001701\",\"RegionNum\":1,\"RegionCategory\":\"环境科学与生态学\",\"ArticlePicture\":[],\"TitleCN\":null,\"AbstractTextCN\":null,\"PMCID\":null,\"EPubDate\":\"\",\"PubModel\":\"\",\"JCR\":\"Q1\",\"JCRName\":\"ECOLOGY\",\"Score\":null,\"Total\":0}","platform":"Semanticscholar","paperid":null,"PeriodicalName":"Landscape and Urban Planning","FirstCategoryId":"93","ListUrlMain":"https://www.sciencedirect.com/science/article/pii/S0169204624001701","RegionNum":1,"RegionCategory":"环境科学与生态学","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":null,"EPubDate":"","PubModel":"","JCR":"Q1","JCRName":"ECOLOGY","Score":null,"Total":0}
引用次数: 0

摘要

注意力恢复理论(ART)提出了了解城市和自然恢复质量的四个基本指标(远离、范围、魅力和兼容性)。然而,以往的研究大多依赖于孤立的问卷调查或图像,忽略了空间结构(场景实体之间的视觉关系)和邻近环境对修复质量的影响。本研究引入了一种空间依赖图神经网络(GNN)方法来弥补这一不足,并在城市尺度上探索空间结构与修复质量之间的关系。研究构建了两类图:街道级图使用连续街景图像(SVI)来捕捉实体间的视觉关系并表示空间结构;城市级图以道路拓扑关系为模型,捕捉相邻实体的空间特征,综合感知、空间和社会经济特征来衡量修复质量。结果表明,依赖空间的 GNN 优于传统模型,准确率(Acc)达到 0.742,F1 得分为 0.740,表明其捕捉相邻空间特征的能力出众。消融实验进一步揭示了空间结构特征对修复质量预测性能的重大积极影响。此外,研究还强调,与人工实体(如建筑物)相比,与自然相关的实体(如树木)对高修复质量的影响更大。这项研究阐明了空间结构与修复质量之间的关联,为未来改善城市福祉提供了一个新的视角。
本文章由计算机程序翻译,如有差异,请以英文原文为准。
查看原文
分享 分享
微信好友 朋友圈 QQ好友 复制链接
本刊更多论文
How does spatial structure affect psychological restoration? A method based on graph neural networks and street view imagery

The Attention Restoration Theory (ART) proposed four essential indicators (being away, extent, fascinating, and compatibility) for understanding urban and natural restoration quality. However, previous studies have overlooked the impact of spatial structure (the visual relationships between scene entities) and neighboring environments on restoration quality as they mostly relied on isolated questionnaires or images. This study introduces a spatial-dependent graph neural networks (GNNs) approach to address this gap and explore the relationship between spatial structure and restoration quality at a city scale. Two types of graphs were constructed: street-level graphs using sequential street view images (SVIs) to capture visual relationships between entities and represent spatial structure, and city-level graphs modeling the topological relationships of roads to capture the spatial features of neighboring entities, integrating perceptual, spatial, and socioeconomic features to measure restoration quality. The results demonstrated that spatial-dependent GNNs outperform traditional models, achieving an accuracy (Acc) of 0.742 and an F1 score of 0.740, indicating their exceptional ability to capture features of adjacent spaces. Ablation experiments further revealed the substantial positive impact of spatial structure features on the predictive performance for restoration quality. Moreover, the study highlighted the greater significance of naturally relevant entities (e.g., trees) compared to artificial entities (e.g., buildings) in relation to high restoration quality. This study clarifies the association between spatial structure and restoration quality, providing a new perspective to improve urban well-being in the future.

求助全文
通过发布文献求助,成功后即可免费获取论文全文。 去求助
来源期刊
Landscape and Urban Planning
Landscape and Urban Planning 环境科学-生态学
CiteScore
15.20
自引率
6.60%
发文量
232
审稿时长
6 months
期刊介绍: Landscape and Urban Planning is an international journal that aims to enhance our understanding of landscapes and promote sustainable solutions for landscape change. The journal focuses on landscapes as complex social-ecological systems that encompass various spatial and temporal dimensions. These landscapes possess aesthetic, natural, and cultural qualities that are valued by individuals in different ways, leading to actions that alter the landscape. With increasing urbanization and the need for ecological and cultural sensitivity at various scales, a multidisciplinary approach is necessary to comprehend and align social and ecological values for landscape sustainability. The journal believes that combining landscape science with planning and design can yield positive outcomes for both people and nature.
期刊最新文献
A novel method of urban landscape perception based on biological vision process Neighborhood environmental conditions and well-being during the COVID-19 pandemic: A network analysis in Hong Kong adults Evaluating objective and perceived ecosystem service in urban context: An indirect method based on housing market ‘It’s not necessarily a social space’ − Institutions, power and nature’s wellbeing benefits in the context of diverse inner-city neighbourhoods Air regulation service is affected by green areas cover and fragmentation: An analysis using demand, supply and flow during COVID-19 quarantine
×
引用
GB/T 7714-2015
复制
MLA
复制
APA
复制
导出至
BibTeX EndNote RefMan NoteFirst NoteExpress
×
×
提示
您的信息不完整,为了账户安全,请先补充。
现在去补充
×
提示
您因"违规操作"
具体请查看互助需知
我知道了
×
提示
现在去查看 取消
×
提示
确定
0
微信
客服QQ
Book学术公众号 扫码关注我们
反馈
×
意见反馈
请填写您的意见或建议
请填写您的手机或邮箱
已复制链接
已复制链接
快去分享给好友吧!
我知道了
×
扫码分享
扫码分享
Book学术官方微信
Book学术文献互助
Book学术文献互助群
群 号:481959085
Book学术
文献互助 智能选刊 最新文献 互助须知 联系我们:info@booksci.cn
Book学术提供免费学术资源搜索服务,方便国内外学者检索中英文文献。致力于提供最便捷和优质的服务体验。
Copyright © 2023 Book学术 All rights reserved.
ghs 京公网安备 11010802042870号 京ICP备2023020795号-1