Shaokun Lyu

Mr. Shaokun Lyu

orcid

Research Focus & Metrics

Academic Career Length

2Years (2025-Present)

(Calculated once Scilit publication data is synced: current year − year of first publication + 1)

Representative Publications

View All Publications
5 November 2025 in Urban Informatics
Verified
Journal Article
Open access
PDF file
MIMuhammad Ibrahim
Muhammad Ibrahim
SWSiqin Wang
Siqin Wang
SLShaokun Lyu
Shaokun Lyu
NANiaz Ahmad
Niaz Ahmad
NJNasir Muhammad Jamal
Nasir Muhammad Jamal
Sustainable urban development heavily relies on the provision of accessible and well-managed green spaces, which enhance environmental quality and urban livability. However, in many fast-growing cities, green spaces are unequally distributed and poorly accessible. Therefore, this study assesses the provision, spatial distribution, accessibility, quality and management of green spaces in Mardan, Pakistan, a rapidly urbanising secondary city in South Asia. Using a mixed-method approach combines GIS-based spatial analysis and field surveys to evaluate the quantity, quality, and accessibility of urban green spaces (UGS). Landsat 8/9 imagery in ArcGIS Pro 3.0 was used to evaluate the UGS coverage; accessibility was evaluated through the Two-Step Floating Catchment Area (2SFCA); and quality was assessed using a locally adapted Qualitative Green Space Index (QGSI). Results show that only 307 acres (0.87%) of land is dedicated to green space within an overall urban area of 35,126 acres, translating to a per capita availability of merely 3.1 m 2 , significantly less than the recommended global benchmark. QGSI scores demonstrated considerable discrepancies, with higher education institutions excelling in management and aesthetics compared to municipal authorities. Results from the 2SFCA underscore substantial spatial inequalities in accessibility, particularly in the northern and eastern areas of Mardan. This study offers spatial insights aimed at fostering evidence-based planning for equitable and sustainable development of green infrastructure in intensively developing areas.

16 December 2025 in Abstracts of the ICA
Verified
Journal Article
Open access
SWSiqin Wang
Siqin Wang
JYJooyoung Yoo
Jooyoung Yoo
WCWenhui Cai
Wenhui Cai
FYFan Ellie Yang
Fan Ellie Yang
Xiao HuangXiao Huang
Xiao Huang
SLShaokun Lyu
Shaokun Lyu
Aligned with the United Nations' Sustainable Development Goals, creating inclusive, safe, and sustainable cities has become a key objective in urban planning and environmental management. While prior studies have examined built environment characteristics and social disparities, few have explored how neighborhood visual environments-shaped by actual built features-differ across social and vulnerable groups at a large scale. This study addresses this gap by developing a multi-modal machine learning framework to assess visual environmental inequity in Los Angeles County, a region notable for its ethnic diversity and socioeconomic contrasts (Figure 1). Using over 500,000 street view images from Mapillary and actual built environment data from OpenStreetMap and Google Earth Engine, we quantify neighborhoods in terms of 5D dimensions (density, diversity, design, distance, destination) and measure visual perceptions (beautiful, safe, wealthy, livable, boring, depressing) using a ResNet-based image classification model trained on crowd-sourced perception scores. Semantic segmentation is conducted using DeepLabV3+, and a gradient boosting ensemble model identifies the built features most associated with perceived soundness.