We have been writing quite a few times about the influence of wind on air pollution, and how strong winds (or, to be more precise, strong ventilation) can help to clean the air in a very short time. But we never had the opportunity to create on a dynamic visualization of this phenomenon, so this is what this article will be writing about.
--
- South wind tend to increase the pollution in Beijing: If the wind is not strong enough (i.e. not ventilating enough), then the particules will get blocked by the montains and will not be able to move further to the north, thus creating a dense particule concentration in Beijing.
- North wind tend to clear the pollution: When the wind blows sufficiently from the North, the air gets almost immediately cleared since there is no "pollution source" in the north (or, at least, much less than in the south).
--
Air Quality Forecast Viewer
version 1.2 (2016/2/18)
version 1.2 (2016/2/18)
Loading..
--

To be more precise, the model should include vertical wind profile, as well as the forecasting for several heights (layers) - currently, the model is only using the forecast at 10 meters, 100 meters and 5KM. Moreover, the pollution sources should be more complete and include the overall world sources - currently, only sources from Hebei are included.
--
On the paper, Machine Learning based forecasting system look good, but in actual fact, are they any better than the tradtional deterministic models (which we do prefer at the World Air Quality Index project)? Refering to the excellent TED talk from Talithia Williams on 'Own your body's data', our answer to this question is "show us the data!", and that's something we will be writing about in our next article on forecasting!