Tech News

Turning night into day: a revolutionary approach to 24/7 air quality monitoring using cameras


Newswise — Air pollution is a critical global health issue, requiring innovative monitoring solutions. Traditional methods, which rely on ground stations, are expensive and geographically limited, preventing complete coverage. Recent technological advances have highlighted the potential of using visual data from surveillance cameras as a cost-effective alternative for air quality assessment.

A new study (do I: Published in Environmental sciences and ecotechnology (Volume 18, 2024) innovates with a hybrid deep learning model that significantly improves outdoor air quality monitoring using surveillance camera images. This approach improves estimates of air quality, including particulate matter2.5 and MPten concentrations and the air quality index (AQI), regardless of the time of day.

The research team skillfully combined convolutional neural networks (CNN) with long short-term memory networks (LSTM), creating a model that intelligently captures both the spatial details present in individual images and the temporal dynamics in a sequence of images. This innovative approach is particularly suited to overcoming the long-standing challenge of accurately estimating air quality during nighttime, a time when traditional image-based methods typically fail due to low-light conditions. By analyzing visual signals from monitoring images, such as haze and visibility, the model can predict concentrations of particulate matter (PM2.5 and MPten) and Air Quality Index (AQI) effectively, day or night.

Strong points

  • Three time series image datasets were constructed for air quality assessments.
  • CNN and LSTM are combined to obtain an average estimated R2 > 0.9 throughout the day.
  • Our method improves nighttime air quality estimation and improves overall accuracy.
  • Our method outperforms existing methods with differences on R2 being 0.02 to 0.22.

Dr Xuejun Liu, lead researcher and corresponding author, highlights: “Our model’s ability to accurately estimate air quality from images, regardless of day or night, marks a significant advance in use of technology for environmental monitoring. assessment of air quality in regions lacking infrastructure.

This research represents a substantial step forward in environmental monitoring, demonstrating the potential to significantly improve air quality assessments. This opens the door to more dynamic and cost-effective monitoring solutions that could significantly improve our understanding and management of air pollution on a global scale.


The references



Original source URL

Funding information

This work was supported by the National Key Research and Development Program of China (2021YFE0112300); the National Natural Science Foundation of China (NSFC) (41771420); the China Scholarship Council (CSC) State Scholarship Fund (201906865016); and the Postgraduate Research and Practice Innovation Program of Jiangsu Province (KYCX21_1341).

About Environmental sciences and ecotechnology

Environmental sciences and ecotechnology (ISSN 2666-4984) is an international peer-reviewed and open access journal published by Elsevier. The journal publishes important views and research across the spectrum of ecology and environmental sciences, such as climate change, sustainability, biodiversity conservation, environment and health, Green catalysis/processing for pollution control and AI-based environmental engineering. The latest ESE impact factor is 12.6, according to the Journal Citation ReportTM 2022.


Related Articles

Leave a Reply

Your email address will not be published. Required fields are marked *

Back to top button