Identifying Sustainable Development Patterns of Nations and Cities in Three Asian Regions with Unsupervised Learning

DC Field Value Language
dc.contributor.author Doyun Lee; Jiyeon Park; Danbi Kim; Steven Jige Quan -
dc.date.accessioned 2023-01-18T16:30:38Z -
dc.date.available 2023-01-18T16:30:38Z -
dc.date.issued 20221231 -
dc.identifier.citation 환경정책. 제30권 특별호 2022년 12월 47-57 p. -
dc.identifier.uri https://repository.kei.re.kr/handle/2017.oak/23821 -
dc.identifier.uri http://library.kei.re.kr/dmme/img/001/021/027/005/03_Identifying_Sustainable_Development_Patterns_of_Nations_and_Cities_in_Three_Asian_Regions_with_Unsupervised_Learning_Doyun_Lee.pdf -
dc.description.abstract Asia, the largest and most populous continent in the world, is in dire need of sustainable development due to its rapid urbanization; particularly, the Southeast, South, and West Asia regions demand the most attention. However, previous studies have been limited in examining sustainable development patterns in the three regions. This study identified sustainability development patterns in 23 countries and 33 major cities in three Asian regions using time series clustering, an unsupervised learning technique. Considering the three pillars of sustainability, three clusters were identified at both national and city levels based on three variables: population, GDP per capita, and total energy/electricity consumption per capita. The identified clusters suggested diverse sustainable development patterns in each of the three regions. The largest clusters at national and city levels exhibited a rapid development trend in all three aspects, indicating an urgent need to pursue sustainable development. Other clusters revealed complex trends that were closely linked to local development characteristics. Overall, the clusters at both national and city levels transcend the regions significantly, suggesting that future policymaking in the three regions should be tailored to local issues and take cues from regions with similar patterns rather than adhering to the conventional notion of Asian regions. The results provide fresh insights into sustainable development patterns in the three regions, thereby helping policymakers make better policy comparisons and more targeted policy execution decisions. [Key Words] South Asia, Southeast Asia, West Asia, Time Series Clustering, Machine Learning -
dc.format.extent 47-57 p. -
dc.publisher 한국환경연구원, 한국환경정책학회 -
dc.title Identifying Sustainable Development Patterns of Nations and Cities in Three Asian Regions with Unsupervised Learning -
dc.type 환경정책 -
dc.identifier.citationtitle 환경정책 -
dc.identifier.citationvolume 제30권 특별호 2022년 12월 -
Appears in Collections:
Periodicals(정기간행물) > Journal of Environmental Policy and Administration(환경정책)
Files in This Item:

qrcode

Items in DSpace are protected by copyright, with all rights reserved, unless otherwise indicated.

Browse