PMID- 37989945
OWN - NLM
STAT- MEDLINE
DCOM- 20231225
LR  - 20231225
IS  - 1614-7499 (Electronic)
IS  - 0944-1344 (Linking)
VI  - 30
IP  - 59
DP  - 2023 Dec
TI  - Urban surface classification using semi-supervised domain adaptive deep learning 
      models and its application in urban environment studies.
PG  - 123507-123526
LID - 10.1007/s11356-023-30843-8 [doi]
AB  - High-resolution urban surface information, e.g., the fraction of 
      impervious/pervious surface, is pivotal in studies of local thermal/wind 
      environments and air pollution. In this study, we introduced and validated a 
      domain adaptive land cover classification model, to automatically classify Google 
      Earth images into pixel-based land cover maps. By combining domain adaptation 
      (DA) and semi-supervised learning (SSL) techniques, our model demonstrates its 
      effectiveness even when trained with a limited dataset derived from Gaofen2 (GF2) 
      satellite images. The model's overall accuracy on the translated GF2 dataset 
      improved significantly from 19.5% to 75.2%, and on the Google Earth image dataset 
      from 23.1% to 61.5%. The overall accuracy is 2.9% and 3.4% higher than when using 
      only DA. Furthermore, with this model, we derived land cover maps and 
      investigated the impact of land surface composition on the local meteorological 
      parameters and air pollutant concentrations in the three most developed urban 
      agglomerations in China, i.e., Beijing, Shanghai and the Great Bay Area (GBA). 
      Our correlation analysis reveals that air temperature exhibits a strong positive 
      correlation with neighboring artificial impervious surfaces, with Pearson 
      correlation coefficients higher than 0.6 in all areas except during the spring in 
      the GBA. However, the correlation between air pollutants and land surface 
      composition is notably weaker and more variable. The primary contribution of this 
      paper is to provide an efficient method for urban land cover extraction which 
      will be of great value for assessing the urban surface composition, quantifying 
      the impact of land use/land cover, and facilitating the development of informed 
      policies.
CI  - (c) 2023. The Author(s), under exclusive licence to Springer-Verlag GmbH Germany, 
      part of Springer Nature.
FAU - Ding, Xiaotian
AU  - Ding X
AD  - College of Civil Engineering and Architecture, Zhejiang University, Hangzhou, 
      China.
AD  - Center for Balance Architecture, Zhejiang University, Hangzhou, China.
AD  - International Research Center for Green Building and Low-Carbon City, 
      International Campus, Zhejiang University, Haining, China.
FAU - Fan, Yifan
AU  - Fan Y
AD  - College of Civil Engineering and Architecture, Zhejiang University, Hangzhou, 
      China. yifanfan@zju.edu.cn.
AD  - Center for Balance Architecture, Zhejiang University, Hangzhou, China. 
      yifanfan@zju.edu.cn.
AD  - International Research Center for Green Building and Low-Carbon City, 
      International Campus, Zhejiang University, Haining, China. yifanfan@zju.edu.cn.
FAU - Li, Yuguo
AU  - Li Y
AD  - Department of Mechanical Engineering, The University of Hong Kong, Hong Kong SAR, 
      China.
FAU - Ge, Jian
AU  - Ge J
AD  - College of Civil Engineering and Architecture, Zhejiang University, Hangzhou, 
      China.
AD  - International Research Center for Green Building and Low-Carbon City, 
      International Campus, Zhejiang University, Haining, China.
LA  - eng
GR  - 51908489/the National Natural Science Foundation of China (NSFC)/
GR  - 2023C03152/"Pioneer" and "Leading Goose" R&D Program of Zhejiang/
GR  - 100000-11320/209/Zhejiang University Global Partnership Fund/
PT  - Journal Article
DEP - 20231121
PL  - Germany
TA  - Environ Sci Pollut Res Int
JT  - Environmental science and pollution research international
JID - 9441769
RN  - 0 (Air Pollutants)
SB  - IM
MH  - *Deep Learning
MH  - China
MH  - *Air Pollution
MH  - Temperature
MH  - *Air Pollutants
MH  - Environmental Monitoring/methods
MH  - Cities
OTO - NOTNLM
OT  - Air quality
OT  - Deep learning
OT  - Domain adaptation
OT  - Semi-supervised learning
OT  - Urban environment
OT  - Urban surface recognition
EDAT- 2023/11/22 06:44
MHDA- 2023/12/25 06:42
CRDT- 2023/11/22 00:03
PHST- 2023/07/21 00:00 [received]
PHST- 2023/10/29 00:00 [accepted]
PHST- 2023/12/25 06:42 [medline]
PHST- 2023/11/22 06:44 [pubmed]
PHST- 2023/11/22 00:03 [entrez]
AID - 10.1007/s11356-023-30843-8 [pii]
AID - 10.1007/s11356-023-30843-8 [doi]
PST - ppublish
SO  - Environ Sci Pollut Res Int. 2023 Dec;30(59):123507-123526. doi: 
      10.1007/s11356-023-30843-8. Epub 2023 Nov 21.