Deteriorating air quality and its adverse health impact have raised significant concerns amongst civil society, NGOs, and policymakers. Air pollution and climate change are
closely intertwined, share common causes, and often exacerbate each other. While climate change is a long-term phenomenon,
air pollution aggravates it significantly, leading to immediate and urgent consequences of immense magnitude. Given this correlation, measures to improve air quality, especially urban air pollution, will
catalyse action on climate action.
Assessing efficacy
Ranked
fourth in the
World Air Quality Report by IQAir, Delhi generally makes headlines as one of the world’s most polluted cities. However, air pollution is essentially a pan-India urban menace, with
39 Indian cities featuring in the top 50 polluted cities globally.
State governments in Haryana, Punjab, and Rajasthan devised actionable plans to address air pollution caused by stubble burning.
In 2016, due to
hazardous air pollution levels, authorities in Delhi implemented temporary measures, including shutting down schools, colleges, and industries, and banning diesel generators. The
Delhi government and the Central Pollution Control Board (CPCB) developed the Air Quality Index (AQI)-based Graded Response Access Plan (GRAP), which adjusts the level of action and measures taken according to the levels of air quality—from
good to severe+ pollution, determined by averaging pollutant concentrations over specific time intervals. Similarly,
state governments in Haryana, Punjab, and Rajasthan devised actionable plans to address air pollution caused by
stubble burning. However, their attempts have largely remained confined to
crisis response, as the extreme volatility of air quality makes identification of patterns and implementation of sustainable preventive measures difficult, especially in the absence of comprehensive yet targeted data analysis.
Likewise,
the National Clean Air Programme (NCAP), implemented in 2019, aims to improve India’s air quality in 131 cities in India with real-time monitoring. The programme aims to achieve a
40-percent reduction in pollutant concentration, complying with the
National Ambient Air Quality Standards (NAAQS) for PM 10 concentrations by 2026.
PM 2.5 and PM 10 are fine particulate matter composed of tiny droplets of liquid, dry solid fragments, and solid cores with liquid coatings that can lead to harmful health effects when inhaled. Additionally, initiatives such as the
National Air Quality Monitoring Programme (NAMP),
Commission for Air Quality Management, and
subsidies for Turbo Happy Seeder machines (THS) aim to improve air quality by discouraging crop residue burning.
The CPCB employs spatial averaging to assess compliance with NCAP standards because only around half of the NCAP cities have real-time monitoring stations and most of the cities’ monitoring stations did not meet the minimum data requirement.
Despite such measures, a Centre for Science and Environment analysis revealed a
minimal disparity in PM2.5 levels between cities included in the NCAP and those not covered by it, indicating that air pollution was a much wider urban problem. Data monitoring may play a significant role in explaining this observation. The CPCB employs spatial averaging to assess compliance with NCAP standards because only around half of the NCAP cities have real-time monitoring stations and most of the cities’ monitoring stations
did not meet the minimum data requirement. In contrast, international agencies like the United States (US) Environmental Protection Agency ( The CPCB could consider implementing a robust protocol that regularly analyses real-time air quality data to ensure robust and effective policy response. Oklahoma Gas & Electric and Austin Energy in the US have implemented programmes that use data analytics to
reduce the power demand for air conditioning by 30 percent without the end users even realising a change and thereby avoiding building additional power plant capacities. Deploying data analysis tools by cross-checking consumption against monthly electricity bills also helped the US to tackle
energy theft. The US’ experience shows how improved data analysis, management, and collection can also be used for developing climate mitigation strategies effectively.
Data-driven development
Harnessing data is vital in combating climate change. Establishing a comprehensive and regularly updated air quality data repository is crucial to informed decision-making. As the G20 president,
India emphasised the significance of “Data for Development” (D4D) in its agenda.
India’s G20 Sherpa, Amitabh Kant, underlined the importance of accessible granular data to
achieve the United Nations Sustainable Development Goals (SDGs) while criticising those who limit data access and emphasising its value for academic and research purposes.
A sustainable future calls for a discourse on data privacy norms, cross-border data sharing, localisation of sensitive data of national importance, and onboarding of all stakeholders.
The Indian government has made
large datasets of 36 critical sectors public, accompanied by
analytics and visualisation tools. By making such large datasets public, India has taken the baton in the marathon of using data for real development. Implementing data-driven policy frameworks encourages other developing nations to build capacity in this space. It paves the way for future global collaboration to
attain SDG 3.9, which seeks to reduce death and illness due to air, water, and soil contamination. A sustainable future calls for a discourse on data privacy norms, cross-border data sharing, localisation of sensitive data of national importance, and onboarding of all stakeholders.
From data to insights
In light of the abundance of data available, it is crucial to use it to extract valuable insights. Data analytics could enable the government to identify pain points and implement adaptable policies promptly, unlike the
NCAP, where there are no time-bound targets for the reduction of pollution.
Air quality monitors collect pollutant data hourly, creating an extensive repository of data that qualifies as
big data due to its high velocity, variety, value, and veracity. Using
spatial averages on such datasets is a rudimentary approach because it oversimplifies the complexity of air pollution by neglecting microscale variations of pollutants within a given area, population exposure to air pollutants and its impact on their health, source identification of pollution, and other geographical meteorological local conditions. In comparison, the
Transfer Income Model, a
microsimulation model that analyses the impact of tax, transfer, and health programmes in the US, is a better approach. It employs causal inferential statistics to examine variations within the sample and how policy changes across time and geography. Such a model could be used in India through a hybrid framework of NCAP and GRAP. Additionally, machine learning and artificial intelligence can be employed to automate the formulation, analysis, and ongoing enhancement of policies addressing the dynamic nature of air quality.
Air quality monitors collect pollutant data hourly, creating an extensive repository of data that qualifies as big data due to its high velocity, variety, value, and veracity.
Predictive analytics has found promising applications in healthcare, exemplifying its immense potential for future utilisation. The
Australian Institute of Health and Welfare uses predictive analytics to generate insights on factors like healthcare expenditure and population growth. Similarly, a predictive model can be created using past time series data from multiple air quality monitors to forecast AQI. For instance, if sulphur is the primary cause of severe AQI, the government should target
specific activities contributing to sulphur pollution instead of implementing a basket of
predetermined actions.
Predictive analytics in AQI determination can assess policy effectiveness, identify optimal parameters that have minimal impact on the economy and ensure improved air quality.
Way forward
A dynamic framework incorporating predictive policy formulation supported by data can be the next phase in tackling air quality issues effectively and proactively in India. The utilisation of data is paramount in addressing global challenges such as climate change. This warrants increased attention, and analytics could provide valuable assistance. Addressing climate change necessitates a collaborative global plan, where India has the potential to emerge as a leading force, showcasing thought leadership and impactful action.
Rahul Rajeev is an intern with the Geoeconomics programme at the Observer Research Foundation.
The views expressed above belong to the author(s). ORF research and analyses now available on Telegram! Click here to access our curated content — blogs, longforms and interviews.
PREV
