What did you develop?
We developed different graphs which were capable of visualizing the changes in AQI before and after the COVID-19 pandemic and we made it very simple for the user to interact with the graph and identify hourly data as well.
Why is it important?
Even though the data is available in the tabular format they are difficult to interpret or understand, so to make it easy to understand we made interactive graphs using various python libraries. Since to solve any problem finding the root cause of the problem is important, so we can find out which gas is the most contributes to air pollution.
What does it do?
It helps to visualize the Air Quality data from the past five years to the pandemic time and helps the non-technical person to interpret data easily using interactive graph. It shows a graph of different gases so we can study which gas is contributing most to the pollution level. It compares the AQI data before lockdown and after lockdown side by side.
How does it work?
The user can interact with the graphs in different ways like hover, slide, zoom etc. and it will show the data for a particular day, month, year and by seeing that visualizations the user can understand the importance of the Air quality and we can hope for some reduction in Air degradation.
What do you hope to achieve?
We are trying to take it to the next level by making it for every city in India and major cities in the world, if the user just enters his location we can show the data easily for the whole day, month or year and can show graphs by comparing the present scenario to the previous year data.
Our main inspiration was the sudden change in our normal environment, as we can feel it after lockdown the air quality suddenly increased. So decided to use interactive graphs to prove that the quality of air has been improved and to make people aware about this fact. So we used data visualization techniques for this purpose.
We only used Jupyter Notebook for our whole project and we used different libraries for the data visualization such as plotly, folium, seaborn, matplotlib etc.
We spent our most of the time finding a reliable data source and we were not well versed with high-level data visualization techniques so we had to refer the documentation of all the libraries we used, which took time.
The data was from taken from a real time monitoring app which was made publicly available by the Central Pollution Control Board.
Our whole solution is demonstrated in our website whose link is given below.
The data was from taken from a real time monitoring app which was made publicly available by the Central Pollution Control Board and for plotting the data on map we used the latitude, longitude of all the cities.
www.simplemaps.com/data/in-cities