Air pollution from burning fossil fuels affects human health, but predicting the level of pollution at any time and place is still difficult. Satellite observations on the ground each measure air pollution, but they come with limitations, as stated by many scientists.
In order to combat this issue, an aproach consisting in many deep learning, should be used in order to analyze the relationship between satellite and infield observations of nitrogen dioxide in some areas.
A deep learning algorithm works like a human brain and has many layers of neurons designed to process data and create models. The system learns and trains based on the connections it finds in the big data, the scientists said. Scientists tested two deep learning algorithms and found that compared to ground observations and satellite surveys more accurately predicted nitrogen dioxide levels. Adding information such as weather data, elevation, and location of bus stations, major roads, and fire stations also improved forecast accuracy.
“The challenge here is whether we can find a linkage between measurements from earth’s surface and satellite observations of the troposphere, which are actually far away from each other. That’s where deep learning comes in.” said a scientist that worked on this study.
Niciun comentariu:
Trimiteți un comentariu