Jove
Visualize
Contact Us
JoVE
x logofacebook logolinkedin logoyoutube logo
ABOUT JoVE
OverviewLeadershipBlogJoVE Help Center
AUTHORS
Publishing ProcessEditorial BoardScope & PoliciesPeer ReviewFAQSubmit
LIBRARIANS
TestimonialsSubscriptionsAccessResourcesLibrary Advisory BoardFAQ
RESEARCH
JoVE JournalMethods CollectionsJoVE Encyclopedia of ExperimentsArchive
EDUCATION
JoVE CoreJoVE BusinessJoVE Science EducationJoVE Lab ManualFaculty Resource CenterFaculty Site
Terms & Conditions of Use
Privacy Policy
Policies

Related Concept Videos

You might also read

Related Articles

Articles linked to this work by shared authors, journal, and citation graph.

Sort by
Same author

Refinement and application of 12S <i>rRNA</i> meta-barcoding primers for seafood identification in multispecies product.

Current research in food science·2026
Same author

Enhancement of ursolic acid (UA), an active ingredient in hawthorn, on the uptake and metabolism of 2,3,5,4'-tetrahydroxystilbene-2-O-β-D-glucoside (THSG) derived from Polygonum multiflorum.

Food research international (Ottawa, Ont.)·2026
Same author

A rapid visual detection method for indel polymorphisms in the bovine PRNP gene based on a duplex MIRA-LFD assay.

Frontiers in veterinary science·2026
Same author

Impact of a real-time automatic quality control system for magnetically controlled capsule gastroscopy: a multicenter randomized controlled trial.

BMC medicine·2026
Same author

Watchful Waiting in Children with Unifocal Osseous Langerhans Cell Histiocytosis.

The oncologist·2026
Same author

Whole-exome sequencing identifies PRSS56 variants in Chinese patients with microphthalmia.

BMC medical genomics·2026

Related Experiment Video

Updated: Jul 10, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

559

Urban surface classification using semi-supervised domain adaptive deep learning models and its application in urban

Xiaotian Ding1,2,3, Yifan Fan4,5,6, Yuguo Li7

  • 1College of Civil Engineering and Architecture, Zhejiang University, Hangzhou, China.

Environmental Science and Pollution Research International
|November 22, 2023
PubMed
Summary

This study introduces a domain adaptive land cover classification model for urban environments. The model accurately maps impervious surfaces, revealing their strong correlation with higher air temperatures in major Chinese cities.

Keywords:
Air qualityDeep learningDomain adaptationSemi-supervised learningUrban environmentUrban surface recognition

More Related Videos

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.5K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

Related Experiment Videos

Last Updated: Jul 10, 2025

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications
03:31

Author Spotlight: Enhancement of Salient Object Detection for Smart Grid Applications

Published on: December 15, 2023

559
Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images
08:20

Author Spotlight: AI-Driven Trypanosome Species Detection from Microscopic Images

Published on: October 27, 2023

1.5K
Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography
04:48

Application of Deep Learning-Based Medical Image Segmentation via Orbital Computed Tomography

Published on: November 30, 2022

2.8K

Area of Science:

  • Environmental Science
  • Remote Sensing
  • Urban Planning

Background:

  • High-resolution urban surface information is crucial for understanding local thermal environments, wind patterns, and air pollution.
  • Existing land cover classification methods often require extensive labeled data, limiting their application in diverse urban settings.

Purpose of the Study:

  • To develop and validate a domain adaptive land cover classification model for automatically generating pixel-based land cover maps from Google Earth images.
  • To assess the impact of urban land surface composition on local meteorological parameters and air pollutant concentrations.

Main Methods:

  • Combined domain adaptation (DA) and semi-supervised learning (SSL) techniques.
  • Trained the model using a limited dataset from Gaofen2 (GF2) satellite images to classify Google Earth imagery.
  • Derived land cover maps for Beijing, Shanghai, and the Great Bay Area (GBA).

Main Results:

  • The model significantly improved classification accuracy, reaching 75.2% on translated GF2 data and 61.5% on Google Earth data.
  • Air temperature showed a strong positive correlation (Pearson's r > 0.6) with artificial impervious surfaces across studied areas.
  • Correlations between air pollutants and land surface composition were weaker and more variable.

Conclusions:

  • The developed model offers an efficient method for urban land cover extraction, valuable for urban surface composition assessment.
  • Findings highlight the significant influence of impervious surfaces on urban air temperature.
  • The research supports informed urban planning and policy development regarding land use and environmental impacts.