Revealing relationships between levels of air quality and walkability using explainable artificial intelligence techniques

Kód výsledku v IS VaVaI

<a href="https://www.isvavai.cz/riv?ss=detail&h=RIV%2F00216305%3A26210%2F26%3A0201442" target="_blank" >RIV/00216305:26210/26:0201442 - isvavai.cz</a>

Výsledek na webu

<a href="https://link.springer.com/article/10.1007/s10098-024-03012-9" target="_blank" >https://link.springer.com/article/10.1007/s10098-024-03012-9</a>

DOI - Digital Object Identifier

<a href="http://dx.doi.org/10.1007/s10098-024-03012-9" target="_blank" >10.1007/s10098-024-03012-9</a>

Jazyk výsledku

angličtina

Název v původním jazyce

Revealing relationships between levels of air quality and walkability using explainable artificial intelligence techniques

Popis výsledku v původním jazyce

Based on the global interest in environmental and health issues related to air pollution, this study addresses the impact of air quality on walking and related factors in cities. This study analyzes the impact of air quality on pedestrian volume in Seoul, Korea, and the relationship between these two variables. In this study, an Artificial Intelligence model was first built to predict pedestrian volume using various urban environmental variables. Then, using Explainable Artificial Intelligence techniques, various factors affecting pedestrian volume were post-analyzed and the interaction between pedestrian volume and air quality was identified. The results of the study show that air quality indicators have a high variable importance in predicting pedestrian volume, and when the indicators improve above a certain level, pedestrian volume is rapidly activated. In addition, the concentration of fine dust does not have a significant effect on the increase in pedestrian volume on weekdays and in urban centers where essential travel occurs, whereas in neighborhood parks, pedestrian volume elastically decreased due to the deterioration of air quality, and this phenomenon was more pronounced when the fine dust rating was downgraded. Finally, the sensitivity of walking variation by air quality was analyzed in consideration of population characteristics in neighborhood parks. In general, it was confirmed that women were more vulnerable to air quality than men, and young adults were relatively more vulnerable to air quality than children and the elderly in the age group, and this difference appeared differently depending on regional characteristics.

Název v anglickém jazyce

Revealing relationships between levels of air quality and walkability using explainable artificial intelligence techniques

Popis výsledku anglicky

Based on the global interest in environmental and health issues related to air pollution, this study addresses the impact of air quality on walking and related factors in cities. This study analyzes the impact of air quality on pedestrian volume in Seoul, Korea, and the relationship between these two variables. In this study, an Artificial Intelligence model was first built to predict pedestrian volume using various urban environmental variables. Then, using Explainable Artificial Intelligence techniques, various factors affecting pedestrian volume were post-analyzed and the interaction between pedestrian volume and air quality was identified. The results of the study show that air quality indicators have a high variable importance in predicting pedestrian volume, and when the indicators improve above a certain level, pedestrian volume is rapidly activated. In addition, the concentration of fine dust does not have a significant effect on the increase in pedestrian volume on weekdays and in urban centers where essential travel occurs, whereas in neighborhood parks, pedestrian volume elastically decreased due to the deterioration of air quality, and this phenomenon was more pronounced when the fine dust rating was downgraded. Finally, the sensitivity of walking variation by air quality was analyzed in consideration of population characteristics in neighborhood parks. In general, it was confirmed that women were more vulnerable to air quality than men, and young adults were relatively more vulnerable to air quality than children and the elderly in the age group, and this difference appeared differently depending on regional characteristics.

Druh

J_imp - Článek v periodiku v databázi Web of Science

CEP obor

—

OECD FORD obor

10511 - Environmental sciences (social aspects to be 5.7)

Projekt

—

Návaznosti

I - Institucionalni podpora na dlouhodoby koncepcni rozvoj vyzkumne organizace

Rok uplatnění

2025

Kód důvěrnosti údajů

S - Úplné a pravdivé údaje o projektu nepodléhají ochraně podle zvláštních právních předpisů

Název periodika

Clean Technologies and Environmental Policy

ISSN

1618-954X

e-ISSN

1618-9558

Svazek periodika

27

Číslo periodika v rámci svazku

12

Stát vydavatele periodika

US - Spojené státy americké

Počet stran výsledku

17

Strana od-do

8623-8639

Kód UT WoS článku

001314848100001

EID výsledku v databázi Scopus

2-s2.0-85204304656