ΑΙhub.org
 

Observing air quality and flow in cities for public health in times of climate change

by
12 February 2021



share this:

Sentinel 5P satellite for monitoring urban heat islands and the air pollution
Sentinel 5P satellite for monitoring urban heat islands and the air pollution. Image source: Sharing Earth Observational Resources.

With my co-authors Pablo Torres, Sergio Hoyas (both from Instituto Universitario de Matemática Pura y Aplicada, Universitat Politécnica de Valencia, Spain) and Ricardo Vinuesa (from Engineering Mechanics, KTH Royal Institute of Technology, Sweden), we have written a book chapter which focuses on the key role of machine learning (ML) methods to analyze air quality and air flow in urban environments (especially in dense cities) which might be an indicator of public health [1].
AIhub focus issue on climate action
We have provided a review of the ML methods used in this field and we have highlighted the relevance of the urban air quality and air flow to the number of hospitalizations and respiratory diseases as they were reported in the literature. With our survey and based on our pre-studies [2,3], we have suggested these points:

  • ML methods can help for modelling air pollutant distribution.
  • ML methods can help for modelling urban airflow dynamics.
  • Remote sensing satellites can provide important information for observing air pollutants and creating urban maps which allow simulation of urban airflow dynamics.
  • ML methods can help estimate higher resolution air pollutant maps based on the lower resolution remote sensing satellite observations and in-situ sensors. In this way, ML methods can importantly increase the accuracy of traditional air-pollution approaches while limiting the development cost of the models.
  • Once the air pollutant distribution maps and the urban airflow dynamics are known, ML methods can help to estimate expected number of respiratory diseases and the expected number of hospitalizations in an area.

Here is a mini lecture which summarizes our book chapter in a video [4].

References:

[1] P. Torres, B. Sirmacek, S. Hoyas, R. Vinuesa, AIM in Climate Change and City Pollution, Artificial Intelligence in Medicine Book, Springer Nature, to be published February 2021.
[2] R. Vinuesa, et al. The role of artificial intelligence in achieving the Sustainable Development Goals Nature Communications, vol. 11, 2020, p. 233.
[3] L. Guastoni, A. Güemes, A. Ianiro, S. Discetti, P. Schlatter, H. Azizpour, R. Vinuesa,
Convolutional-network models to predict wall-bounded turbulence from wall quantities, e-print, 2020.
[4] Climate change and urban pollution, short lecture video



tags: ,


Beril Sirmacek is an associate professor at Saxion University of Applied Sciences
Beril Sirmacek is an associate professor at Saxion University of Applied Sciences




            AIhub is supported by:


Related posts :



Keeping learning-based control safe by regulating distributional shift

We propose a new framework to reason about the safety of a learning-based controller with respect to its training distribution.
30 September 2022, by

Bipedal robot achieves Guinness World Record in 100 metres

Cassie the robot, developed at Oregon State University, records the fastest 100 metres by a bipedal robot.
29 September 2022, by

#IJCAI2022 distinguished paper – Plurality veto: A simple voting rule achieving optimal metric distortion

How can we create a voting system that best represents the preferences of the voters?
28 September 2022, by

AIhub monthly digest: September 2022 – environmental conservation, retrosynthesis, and RoboCup

Welcome to our monthly digest, where you can catch up with AI research, events and news from the month past.
27 September 2022, by

The Machine Ethics Podcast: Rights, trust and ethical choice with Ricardo Baeza-Yates

Host Ben Byford chats to Ricardo Baeza-Yates about responsible AI, the importance of AI governance, questioning people's intent to create AGI, and more.
26 September 2022, by

Recurrent model-free RL can be a strong baseline for many POMDPs

Considering an approach for dealing with realistic problems with noise and incomplete information.
23 September 2022, by





©2021 - Association for the Understanding of Artificial Intelligence


 












©2021 - ROBOTS Association