How We Are Using Technology, Data, And Autorickshaws To Track Delhi’s Pollution

Posted on April 30, 2016 in Environment

By Christine Garcia:

A 2014 WHO study found that Delhi is the most polluted city among the 1,600 cities from 91 countries that were studied. The first step to solving Delhi’s pollution is learning more about it — how bad the pollution actually is, where in the city it is worst, and what factors most contribute to high pollution levels. Yet Delhi doesn’t have enough data to fully understand and address this pollution.

The Delhi Pollution Control Committee has set up just 6 pollution monitoring stations to cover an estimated population of 18.5 million people. Each of these stations costs an estimated ₹1.1 crore ($165,000), which makes it difficult to install more stations. These stations are fixed in a single position, sampling the same location over and over. They monitor gases like ammonia, mercury, and ozone, PM2.5, PM10, air pressure, air temperature, humidity, wind direction, and wind speed.

delhi autorickshaw
Source: Paul Hamilton/Flickr

SocialCops is running an experiment to change this paradigm and create a massive database of air pollution data in Delhi. The data company has created 5 low-cost GPS-enabled IOT (Internet of Things) devices that measure the number of airborne PM10 particles. The parts for these devices were sourced from manufacturers in China and put together in-house, bringing the cost to about ₹6,500 ($100) per device.

To make these pollution sensors just as mobile as Delhi’s citizens, SocialCops deployed its devices in 5 auto rickshaws. Since autos are open vehicles with lots of airflow, they serve as the perfect environment for measuring air pollution. As these autos travel through Delhi, SocialCops’ devices measure PM10 levels and transmit the data back to the SocialCops data platform every 30 seconds.

The greater mobility and reduced cost of these devices comes at a cost — the particle sensor is less accurate than those used by traditional pollution monitors. SocialCops’ devices determine the number of airborne particles by reading the ambient air opaqueness, instead of measuring the precise mass of the collected particles. To solve this drop in precision, SocialCops has increased the sample size significantly. With just 5 devices, SocialCops is collecting more than 15,000 unique pollution data points every day. These data points are used to calculate the Air Quality Index (AQI), based on the National Air Quality Index of India standards.

SocialCops has opened this data to the public on a real-time dashboard, where anyone can view the overall air quality score for each day, examine how air quality changes on an hourly basis, and even track each device as it travels across the city.

Talking about this experiment, Prukalpa Sankar (co-founder of SocialCops) says, “Our mission at SocialCops is to drive better decisions through data. Currently, our data platform integrates data collected via low-cost mobile devices, over 600 public data sources, and internal organization data, which is then visualized through interactive dashboards. Integrating data collection via low-cost IoT devices was a natural next step.”

This initiative could be deployed at a greater scale in the future, with 100 sensors deployed across Delhi, for example. The base cost of the required hardware would still be considerably less than acquiring the traditional equipment used to measure air pollution. With 100 sensors deployed, the average pollution level for each day could be calculated from over 250,000 individual readings, and the sensors could be deployed to a wider area of the city.