Nowcasting Air Quality Using Twitter

Pulse Lab Jakarta

Project Description

In some communities in Indonesia, real-time air quality information is not available, which is crucial for improving response efforts in regions affected by air pollution.

Pulse Lab Jakarta developed a model that leverages real-time sensing and integrates social media images. The model produced at best, 87.24 per cent forecast accuracy — an improvement of 18.11 per cent compared to the baseline model (that uses only satellite and air quality information) based on 2014 data from Pekanbaru, Riau.

Pulse Lab Jakarta has been working closely with the National Information Resources Service in the Ministry of Interior Safety of the Republic of Korea to provide technical assistance for a similar model that the Ministry is developing to monitor the prevalence of fine dust particles in South Korea.

Read more: Nowcasting Air Quality Using Social Media 

Did you find this project interesting? Share it with your networks!

Below you can find our latest examples of our collaborative research, prototypes and experiments, where we analyse digital data to advance global development, support humanitarian action, and promote peace. For more, go to the research projects page.

Pulse Lab New York

UN Open GIS Initiative: Geo-AI Working Group

UN Global Pulse has joined the UN Open GIS Initiative as co-chair of a newly formed Geo-AI Working Group alongside the Food and Agriculture Organization (FAO). UN Open GIS is

Scroll to Top