Search research articles

ABOUT JoVE

Overview Leadership Blog JoVE Help Center

AUTHORS

Publishing Process Editorial Board Scope & Policies Peer Review FAQ Submit

LIBRARIANS

Testimonials Subscriptions Access Resources Library Advisory Board FAQ

RESEARCH

JoVE Journal Methods Collections JoVE Encyclopedia of Experiments Archive

EDUCATION

JoVE Core JoVE Business JoVE Science Education JoVE Lab Manual Faculty Resource Center Faculty Site

Terms & Conditions of Use

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

Streetview greenspace types and dementia risk in older adults: The Multi-Ethnic Study of Atherosclerosis.

American journal of epidemiology·2026

Same author

Urban ambient air pollution and blood pressure in schoolchildren in Accra, Ghana.

Scientific reports·2026

Same author

The Accra school health and environment study (ASHES): a study of the urban environment and child health and development in Accra.

Environmental research communications·2026

Same author

Global Healthy and Sustainable City Indicators: Collaborative development of an open science toolkit for calculating and reporting on urban indicators internationally.

Environment and planning. B, urban analytics and city science·2026

Same author

Assessing greenspace and cardiovascular disease risk through deep learning analysis of street-view imagery in the US-based nationwide Nurses' Health Study.

Environmental epidemiology (Philadelphia, Pa.)·2026

Same author

Estimating the impact of nutritional transition and ending hunger on tuberculosis in 12 high-burden countries: a model-based scenario analysis.

BMJ global health·2025

Search research articles

Related Experiment Video

Updated: Jul 16, 2025

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

A Deep Learning Approach for Meter-Scale Air Quality Estimation in Urban Environments Using Very

Meytar Sorek-Hamer^1,2, Michael von Pohle^1,2, Adwait Sahasrabhojanee^1,2

¹Universities Space Research Association (USRA), Mountain View, CA.

Atmosphere

|September 19, 2023

Summary

High-resolution air quality (AQ) mapping is now possible at the hundred-meter scale using satellite imagery and deep learning. This approach accurately estimates pollution levels, aiding in identifying sources and informing local environmental actions.

Keywords:

Air quality Deep learning Remote Sensing Satellite Imagery Urban environment

More Related Videos

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Investigating the Relationship between Sea Surface Chlorophyll and Major Features of the South China Sea with Satellite Information

Investigating the Relationship between Sea Surface Chlorophyll and Major Features of the South China Sea with Satellite Information

Published on: June 13, 2020

Related Experiment Videos

Last Updated: Jul 16, 2025

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Early Detection of Cyanobacterial Blooms and Associated Cyanotoxins using Fast Detection Strategy

Published on: February 25, 2021

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Author Spotlight: UAV Remote Sensing for Efficient Invasive Plant Biomass Estimation

Published on: February 9, 2024

Investigating the Relationship between Sea Surface Chlorophyll and Major Features of the South China Sea with Satellite Information

Investigating the Relationship between Sea Surface Chlorophyll and Major Features of the South China Sea with Satellite Information

Published on: June 13, 2020

Area of Science:

Environmental Science
Remote Sensing
Artificial Intelligence

Background:

Ground-based air quality (AQ) monitoring is lacking in many populated urban areas globally.
Current satellite-based AQ models offer limited kilometer-scale resolution.
Accurate, high-resolution AQ data is crucial for identifying pollution sources and enabling targeted interventions.

Purpose of the Study:

To assess the feasibility of using high-spatial-resolution satellite imagery and deep neural networks (DNNs) for hundred-meter-scale AQ mapping in urban environments.
To develop and evaluate a novel image-based object-detection approach for continuous AQ estimation.
To explore the potential for global application, particularly in urban areas with limited ground monitoring infrastructure.

Main Methods:

Utilized very high-spatial-resolution (2.5 m) commercial satellite imagery as input for a DNN.
Trained the DNN to associate visual urban features with air pollutant concentrations.
Validated the model using ground monitoring data and land-use regression for PM2.5 and NO2 in London, Vancouver, Los Angeles, and New York City.

Main Results:

Achieved a low error rate with a total Root Mean Square Error (RMSE) < 2 µg/m³.
Demonstrated the significant contribution of specific urban features, such as green spaces and road networks, to AQ estimation.
Successfully generated hundred-meter-scale AQ maps for multiple major cities.

Conclusions:

The image-based object-detection approach using satellite imagery and DNNs is a feasible and accurate method for high-resolution AQ mapping.
This technique can provide valuable insights into localized air pollution, even in areas lacking ground monitoring.
The model shows promise for scalable global applications in both developed and developing urban settings, with further research on domain transferability.