Subscribe to the Teradata Blog

Get the latest industry news, technology trends, and data science insights each week.

I consent that Teradata Corporation, as provider of this website, may occasionally send me Teradata Marketing Communications emails with information regarding products, data analytics, and event and webinar invitations. I understand that I may unsubscribe at any time by following the unsubscribe link at the bottom of any email I receive.

Your privacy is important. Your personal information will be collected, stored, and processed in accordance with the Teradata Global Privacy Policy.

Can Big Data Help Control India’s Spiraling Pollution?

Can Big Data Help Control India’s Spiraling Pollution?

On November 8, 2017, Delhi earned the dubious distinction of being named the world’s most polluted city. If that wasn’t bad enough, Delhi was only one among the nine Indian cities that ranked among the world’s 20 most polluted cities. The other eight include Gwalior, Allahabad, Patna, Raipur, Ludhiana, Kanpur, Firozabad and Lucknow. China in comparison has only four cities in this list and Saudi Arabia has three. These were the cities where the concentration of harmful PM 2.5 particles topped 700 micrograms per cubic metre (mpcm).  So while Delhi’s PM 2.5 concentration was 122, London’s average PM 2.5 is 15, in Paris it is 18, in Los Angeles it is 11, and in Beijing it is 85. India also ranks at number eight among the world’s top 20 countries with the most polluted urban areas. Both Pakistan and Bangladesh outrank us while Nepal and China trail us in this list.

Anyone who’s lived in a big Indian metro has had to deal with smog – especially in winter when dense cold air settles down, making it difficult for pollutants to be ‘breezed away.’ This smog is an outcome of not just vehicular exhaust fumes but also construction and desert dust, factory and power plant emissions and finally the burning of garbage and crop residue. According to the World Health Organization, over 5.5 million people die each year due to problems associated with breathing polluted air. The lack of clean air is even touted to be the third leading cause of death after heart disease and smoking.

The measures to address pollution range from the immediate to the long term and almost all of them have limited outcomes given multiple geographic and climatic variables in addition to those that are man-made. In such a situation what can our policy markers do? Several cities across the world are adopting interesting initiatives to address the problem. These include combining big data along with IoT and artificial intelligence. Using a network of connected sensors, scientists can, not just measure exactly where pollution is coming from, they can pinpoint the numerous factors that contribute to it, and ultimately, reduce it. And doing this over a period of time allows them to measure the cause and effect of pollution on a real-time basis. This in turn gives researchers options to use predictive analytics to ‘forecast’ pollution (as is being done in cities as disparate as Dubai, Chicago, Pittsburg London and Beijing to name a few) to manage it more effectively and intelligently.

So what can and should Delhi and other cities across North India do? First things first – they need to put out a widespread and integrated network of air quality monitoring sensors across the cities to begin real-time monitoring of air quality. This should be accompanied by a policy change to ensure that civic agencies install pollution meters across factories, commercial establishments (such as malls and office complexes), dump-yards and even locations such as schools and hospitals to begin monitoring of emissions and pollutant levels.  Air quality levels should be monitored across a wide spectrum of emissions so that civic agencies and citizens get information on spikes and dips in specific pollutants, allowing them to pin-point the cause to a specific source. Pollution control certificates whether for automobiles or factories and commercial establishments should be made real-time instead of being periodic (as it is now).

The data should also include other sources such as weather monitoring stations and satellites, traffic systems, industrial data, farm data, and even social media. By combining all this disparate data, predictive analytics can create highly accurate models to predict pollution trends in advance allowing civic agencies to make relevant predictions and changes to prevent spikes and keep pollution levels in check. A comprehensive and widespread network such as this to track the causes of pollution at source will allow government agencies to create smarter strategies to combat pollution – and when combined with predictive analytics, predictions in some cases can even be made in advance.

Big data and analytics can also help improve traffic management in addition to just monitoring pollution levels. Sensors will ensure that traffic flows and incident feeds are updated every second, with traffic-impacting incidents such as accidents, closures, and detours, also considered. Combining all this data will allow predictive analytics to throw up both predictive and historic traffic flows along with predictions of incidents basis which traffic police can gain improved insights into how traffic is behaving as well as anticipate and address problems before they happen. Over time smarter management of the causes of pollution – from traffic to power plants, to emissions from factories can help reduce and even contain pollution.

Reports put out by the WHO say that 90 per cent of the deaths caused by air pollution are in low and middle income countries. India is one of them. We need to adopt a pragmatic approach that makes use of technology to address an issue which by any account is alarming. By embracing the power of big data and analytics, policymakers can provide civic agencies the relevant tools and resources that, when used optimally, will help reduce pollution thereby enhancing our quality of life. This will be aided by new developments in sensor technology to ensure that pollution and its resultant impact can be monitored literally on a street-by-street basis. It is time we gave this serious thought.

Portrait of Rajesh Shewani

Rajesh Shewani

Rajesh Shewani heads Technology and Solutions at Teradata India. He comes with close to two decades of experience in the areas of Data Management, Advanced Analytics, Solution Architecture, Enterprise data warehousing and Business Intelligence to name a few.

At Teradata he is responsible for leading a team of experienced Business Analytics consultants, data scientists and solution architects focusing on Teradata Data Analytics solutions. Rajesh has worked in various areas of information management across different industries and functional domains, advising customers on devising corporate performance management and business analytics strategies that will help them achieve differential advantage.

Prior to Teradata, Rajesh was with IBM for over 14 years and performed various roles in technology leadership, architecture and consulting. In his most recent role at IBM he was Country Manager for technical sales for IBM Business Analytics portfolio that included Cognos, SPSS, OpenPages and Algorithmics, leading a team of analytics functional and technical sales architects. Rajesh is certified in technologies such as Cognos BI & FPM, SOA, WebSphere Application Server and DB2.

He holds a Masters in Business Marketing & Information Management from Narsee Monjee Institute of Management Studies.

View all posts by Rajesh Shewani

Turn your complex data and analytics into answers with Teradata Vantage.

Contact us