Short description of the dataset. It contains:
* For 2 routes (about 10km in length) in Belgium,
-> Average modelled & measured air pollution concentrations
-> Temperature, Humidity, Wind Speed and Wind Direction from most close meteo station
-> X,Y coordinates and some samples of air pollution concentrations for each X,Y coordinate of the route on selected times
📷
Many types of analyses and visalization are possible with this dataset. Questions that can be answered with meaningful visaluzations of this dataset are among others but not limited to: how do air pollution concentrations vary in time ? (e.g. day of the week, month of the year, time of the day). How do the air pollution concentrations vary in space ? What is the relationship between the air pollution concentrations and the meteo conditions (temperature, humidity, wind speed, wind direction) ? What is the relationship between distance-to-the road and air pollution concentrations of Black Carbon ? How correlate measured and modelled concentrations & Does this depend o meteo ? How can all dimensions (space,time,meteo,modelled,measured,...) displayed in one ?
In a phirst phase , which will be discussed in this post, we start with some raw sketches of the data.
Sketch #1 (time-serie) displays the measured and modelled average air pollution concentration of Black Carbon over time while sketch #2 (space) displays the cumulative average (average over total time) air pollution concentrations of each X,Y coordinate for each route. Sketch #7 is another way of visualizing sketch #2 and sketch #8 also displays more or less the same with the difference that skech 2 and 7 display absolute numbers while those absolute number are converted to categorical classes for sketch #8.
Sketch #3 displays which % of the time each route has the lowest average air pollution concentration. Sketch #4 is a dotchart displaying the average airp ollution concentration of each route during day (0h-24h).
Sketch #5, #6, #10, #11 are focused on the correlation/relationship between variables in the dataset. Sketch #5 is a scatterplot for the correlation between air pollution and wind speed. #6 for air pollution and temperature, with an additional dimension: air pollution concentrations seperately for modelled and measured values. Also sketch #10 displays 3 dimensions in 2D with all the air pollution concentrations, wind speed and day of the week visualized: the average air pollution concentrations and average wind speed as a couple (X&Y axis) for each day of the week. On this way, a 2nd plot can be added to visualise both measured & modelled air pollution &meteo values for each day of the week. Because of reason of readability, it is choosen to not include this on this raw sketch, but with digital visualization this can be easily produced in a very readable way. Sketch #11 is another possible les suitable way to visualise this. Sketch #9 displays average modelled & measured concentration for each day of the week, without additional variables such as meteo.
