Skip to content

waridrox/aqi-prediction

Folders and files

NameName
Last commit message
Last commit date

Latest commit

 

History

5 Commits
 
 
 
 
 
 
 
 

Repository files navigation

AQI Prediction - pre-COVID and post-COVID era

Motivation behind the project

Since industrialization, there has been an increasing concern about environmental pollution. As mentioned in the WHO report, 7 million premature deaths annually linked to air pollution. Air pollution is the world's largest single environmental risk. Moreover, as reported in the NY Times article, India’s Air Pollution Rivals China’s as World’s Deadliest. Using this dataset, one can explore India's air pollution levels at a more granular scale.

Dataset

This data is combined (across the years and various states of the country) and largely clean version of the Historical Daily Ambient Air Quality Data released by the Ministry of Environment and Forests and Central Pollution Control Board of India under the National Data Sharing and Accessibility Policy (NDSAP).

Graphs

vehicular pollution content

industrial pollution content - most polluted

industrial pollution content - min polluted

Pre COVID levels

Vehicular pollution - line graph

Industrial pollution content (most polluted) - line graph

Most polluted cities - industrial pollution

Most polluted cities - Vehicular pollution

Minimum polluted cities - Industrial pollution

Minimum polluted cities - Vehicular pollution

Post COVID levels

Conclusion

  1. Vehicular pollution contents are more related to air quality index.
  2. Delhi is the most polluted city in terms of vehicular pollution contents.
  3. Ahmadabad is the most polluted city in terms of industrial pollution content.
  4. After COVID19 pandemic there is gradual dicrease in vehicular pollution contents, industrial pollution content.
  5. Extra Gradient Boost classifier 100% accurately classify the target variable.

About

No description, website, or topics provided.

Resources

Stars

Watchers

Forks

Releases

No releases published

Packages

No packages published