NASA and Google will expand their partnership to develop a global air quality monitoring network. The latter will use advanced algorithms to process satellite data and ground measurements in real time. It will eventually offer global coverage.
According to the agreement that has just been concluded, NASA and Google should expand theirin the field of scientific research to improve access to data from terrestrial and satellite air quality measurement systems. The long-term objective is to provide, on a local scale, near real-time estimates of the concentrations of pollutants such as nitrogen dioxide or fine particles.
Method of data processing by learning algorithms
In order to provide city-scale measurements and forecasts, the NASA and Google teams will combine the available data with learning algorithms:
As a first step, Google integrated into theCatalog the archive data of which lists events from 1980 to the present day, as well as data from the NASA Goddard Earth Observing System Composition Forecasts ( ) that use satellite observations of pollutants to map and predict air quality.
Sentinel observation satellite of the Copernicus program of the European Union [ESA/Nasa/RTS]
In a second step, NASA scientists should develop machine learning algorithms in Earth Engine, to identify the relationships between these new sets. Existing data, such as Google’s Street View mapping vehicles, surface observation stations and Earth monitoring satellites, such as the TROPOspheric Monitoring Instrument () of the satellite Sentinel, will also be used.
Understanding these relationships should allow the generation of high-resolution, near-time surface air quality maps in real time. Independent observations will be used to assess these maps on an ongoing basis.
To achieve spatial resolution high enough to distinguish air pollution disparities between neighborhoods or within cities, NASA scientists will also work with the Google Accelerated Science team to integrate data sources already available on the Google Earth Engine. , such as the location of major sources of pollution.
Street-view global coverage in 2020 [Google/Wikipedia]
The San Francisco region should be the first to benefit from this novelty. Next will come the cities of the lower Mekong, Thailand, Cambodia, Laos and Vietnam. Google and NASA’s goal is to eventually provide full global coverage.
“This partnership is a major step in integrating air pollution data from a range of critical sources, from ground-level observations to satellite data, into advanced machine learning algorithms,” said Pawan Gupta, scientist and head of the Universities Space Research Association (USRA) at NASA’s Marshall Space Flight Center. “This tool can allow us to estimate air pollution at the local scale and make the information available to all communities, especially those affected by poor air quality. »
In keeping with NASA’s Free and Open Data Policy, NASA and Google will make all products, algorithms, workflows, case studies, and tutorials developed under this partnership free and open to the public.
According to the World Health Organization and the World Bank, air pollution is responsible for approximately 7 million deaths worldwide each year, with an estimated total cost of 8.1 trillion dollars, c that is to say how valuable this information will be! It remains to be seen how they will be used.