Fengyuan Zhang

Dr. Fengyuan Zhang

Hong Kong Polytechnic University, Hong Kong, China
orcid

Research Focus & Metrics

Academic Career Length

5Years (2022-Present)

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

Representative Publications

View All Publications
Verified
Journal Article
Open access
PDF file
JQJiarui Qin
Jiarui Qin
YFYizhe Feng
Yizhe Feng
YSYehua Sheng
Yehua Sheng
YHYi Huang
Yi Huang
FZFengyuan Zhang
Fengyuan Zhang
KZKaixuan Zhang
Kaixuan Zhang
Urban street comfort is a crucial measure of street environmental quality. However, traditional evaluations primarily focus on physical elements, often neglecting pedestrian perceptions. In this study, considering five core evaluation dimensions—safety, mobility, aesthetics, perceptibility, and convenience—an innovative quantitative evaluation model is proposed to assess pedestrian-perceived comfort on urban streets by integrating physical environmental factors and subjective experiences. This analysis comprises two steps: evaluation indicator extraction and weight application. Indicators are extracted from multi-source data (street-view images, real-time traffic data, points of interest, and pedestrian surveys) using a deep learning method. A comprehensive weighting method combining entropy weight and the analytic hierarchy process is used to determine the relative importance of each factor. This study focuses on Nanjing as a case study, and the results reveal significant variations across the five dimensions and their 11 secondary indicators. Street environment safety (0.143) is critical for street safety, while the degree of street traffic congestion (0.121) dominates street mobility. Street aesthetics is primarily influenced by building enclosure (0.105), and street convenience is strongly affected by the number of surrounding bus stops (0.260). Spatial analysis indicates higher comfort levels in urban centers due to well-developed infrastructure, whereas peripheral areas face challenges from inadequate facilities. Notably, areas around parks demonstrate elevated pedestrian-perceived comfort levels, highlighting the importance of green spaces. Overall, the proposed evaluation system provides new insights from the perspective of pedestrian experience and offers valuable guidance for urban planning and policy.

6 June 2023 in International Journal of Digital Earth
Verified
Journal Article
Open access
FZFengyuan Zhang
Fengyuan Zhang
Wenzhong ShiWenzhong Shi
Wenzhong Shi
MCMin Chen
Min Chen
WHWei Huang
Wei Huang
Xintao LiuXintao Liu
Xintao Liu

10 January 2023 in IEEE Geoscience and Remote Sensing Letters
Verified
Journal Article
Closed access
ZXZhiwei Xie
Zhiwei Xie
MYMingliang Yuan
Mingliang Yuan
FZFengyuan Zhang
Fengyuan Zhang
MCMin Chen
Min Chen
JSJiaqiang Shan
Jiaqiang Shan
Xintao LiuXintao Liu
Xintao Liu
Polycentric urban structures determine the combination and correlation of urban resources. In the past, nighttime light data was often used to identify the center locations, but the borders of polycentric urban regions (PURs) could not be obtained. Using multi-source remote sensing data and graph, this research proposes an effective method for polycentric structure identification. First, we regard nighttime light data as a continuous mathematical surface, which can be constructed as nighttime light intensity graphs (NLIG). Then, the space-optimized Girvan-Newman (SGN) method is proposed to detect the communities, and the eigenvector centrality and gray value are used to discover the central node of each community. Finally, the geographical location mapping between Landsat 8 data segmentation objects and nodes is established, and the PURs and centers can be mapped to the communities and central nodes. This study toke Shenyang, Chengdu, and Xi’an as study areas and used monthly NPP-VIIRS data in April 2019 and Landsat 8 data in January and August 2019. The average accuracies of PURs and centers identified by the proposed method were 86.24% and 72.5%, respectively. The developed method can provide technical support and data support for urban planning.

12 August 2024 in Geo-spatial Information Science
Verified
Journal Article
Open access
ZXZhiwei Xie
Zhiwei Xie
YWYifan Wu
Yifan Wu
ZMZaiyang Ma
Zaiyang Ma
MCMin Chen
Min Chen
ZQZhen Qian
Zhen Qian
BPBo Peng
Bo Peng

30 December 2022 in Remote Sensing
Verified
Journal Article
Open access
PDF file
ZXZhiwei Xie
Zhiwei Xie
MYMingliang Yuan
Mingliang Yuan
FZFengyuan Zhang
Fengyuan Zhang
MCMin Chen
Min Chen
MTMeng Tian
Meng Tian
RLRuizhao Liu
Ruizhao Liu
The urban spatial structure is a key feature of the distribution of social and economic resources. The spatial structure of an urban agglomeration is an abstract relationship expression of urbanization. Urban agglomerations develop for multiple reasons, including urban planning and natural evolution. To date, most research related to urban agglomeration has been based on single data source, which is a limitation. This research aims to propose a spatial structure identification method for urban agglomerations via a complex network based on nighttime light data and railway data. Firstly, we extracted the urban built-up area using defense meteorological satellite program/operational line scanner (DMSP/OLS) data, and divided it into urban objects to obtain the nighttime light urban network (NLUN) by borough. Secondly, we aggregated railway stations at municipal level using railway operation data to obtain the railway urban network (RUN). Following this, we established a composite urban network (CUN) consisting of the NLUN and the RUN based on the composite adjacency matrix. Finally, the Louvain algorithm and the comprehensive strength index (CSI) were used to detect the communities and central nodes of the CUN and obtain the urban agglomerations and core cities. The results show that urban agglomeration identification based on the CUN has the best accuracy, which is 5.72% and 15.94% higher than that of the NLUN and RUN, respectively. Core cities in the urban agglomeration identified by the CSI in the CUN are at least 3.04% higher than those in the single-source urban network. In addition, the distribution pattern of Chinese urban agglomerations in the study area is expressed as “three vertical”, and the development level of urban agglomeration shows an unbalanced trend.

8 March 2024 in IEEE Journal of Selected Topics in Applied Earth Observations and Remote Sensing
Verified
Journal Article
Open access
YWYifan Wu
Yifan Wu
ZXZhiwei Xie
Zhiwei Xie
ZMZaiyang Ma
Zaiyang Ma
MCMin Chen
Min Chen
FZFengyuan Zhang
Fengyuan Zhang
SZShuaizhi ZHAI
Shuaizhi ZHAI
Change detection via remote sensing data is a popular method for monitoring land cover/land use. Graph attention network (GAT) is a method that can improve the change detection performance of land cover/land use monitoring by enhancing the feature representation of remote sensing images. However, the shortcomings of connection sparsity and insufficient sample feature mining of the GAT affect the application of these methods in change detection. This paper proposes a Siamese autoencoder graph attention networks for object-oriented land cover/land use change detection via high-resolution remote sensing, which is useful for semi-supervised problem methods with poor simplicity. First, we reduce the pressure of graph network model operations and obtain multidimensional features via the growing multilevel segmentation strategy (GMSS). The adjacency matrix is established by adding strongly connected edges via the weighted difference similarity matching method (WDSM) with image objects as nodes. Second, we use the Siamese autoencoder to pretrain the node features and migrate the weight parameters to the GAT feature extraction layer. Finally, a small number of samples are selected to train the GAT and predict all nodes. The experimental results show that the average overall accuracy of the proposed method is 95.41%, and the average F1 score is 89.35%, which are at least 5.04% and 10.84% better than those of other typical methods, such as the graph convolutional network (GCN). In particular, detecting roads and bare soil is significantly better than that of other methods.