Grantham Scholar Rohit Chakraborty researches and develops models and techniques that improve how we monitor and communicate air pollution levels in cities.
Rohit is an Electronics and Communications Engineering graduate. His expertise is in Internet of Things (IoT) devices. IoT devices are everyday objects connected to the internet and able to identify themselves to other devices. IoT includes ‘smart’ home appliances, health trackers, environmental monitors and Transport Data Loggers (such as TDL – Bosch GmBh, Germany).
For his research Rohit employs a variety of deep learning techniques. These range from data analysis and machine learning, to human-computer interaction methods, such as Neural Networks and AI based modelling.
Air pollution is a major problem. For example, the World Health Organisation estimates that air pollution was responsible for 1 in 8 of the total number of deaths worldwide in 2012.
Responding to this crisis, Rohit’s project aims to develop models and techniques that improve how we monitor and communicate air pollution levels in cities. This new approach should be achievable without the need to significantly invest in monitoring equipment.
The project will explore how nitrogen dioxide relates to particulates (PM10/2.5). Plus it will explore how other indicators in cities can be used to evaluate air quality. Overall, the aim is to help people avoid high concentrations of pollution. Additionally, the project explores how high-quality data (e.g. AURN – DEFRA data sets) can support the development of models and techniques. Using these data sets could considerably improve near real-time monitoring and communication of the pollution level in cities.
Sheffield will be used to test these innovations. Rohit will work with local electronics company Pimoroni to develop the analytical equipment. After this he will test the low-cost IoT network in a city in a developing country (Kampala).
DEFRA high quality fixed sensors will be combined with high-quality mobile sensing vehicles from the Urban Flows Observatory. Added to this will be Sentinel-5P Satellite data. This satellite data focuses on the measurement of reactive gas pollutants (e.g. NO2, CO, SO2, along with PM2.5 & PM10) under prevailing meteorological conditions.
Together these will be used to calibrate and validate data from a network of Internet of Things based Low-Cost Sensors (LCSs). Through an app on mobile phones, these sensors track NO2, CO, SO2 and fine particulate matter concentration. As a result, Rohit will be able to assess how the DEFRA data sets can be integrated and utilised with the LCS network when assessing gas and particulate readings in a city.
The project will comprise:
Previous models have only encoded data related to spatial locations. In contrast, this project develops and validates statistical models and deep learning algorithms to capture the spatiotemporal dependency for detection, estimation and multistep short-term prediction of air pollution concentration and the inference of particulate levels.
We will also identify and incorporate other types of data provided by ‘social sensors’, e.g. people equipped with mobile wearable sensors such as Flow sensors from Plume labs. The project will develop methods both for people-centric and environment-centric applications. The sensor node can be on a mobile app, such as a cell phone but can also be on a vehicle platform. The research will focus on the development of the workflow to integrate DAFNI with live DEFRA and IoT sensor data novel algorithms in the context of three particular drivers.
Additionally, the research will explore the development of scalable approaches for big data management. Compressed sensing methods will be adopted that allow for sampling and retaining only the most informative data.
Currently, Rohit is working with Paris based Plume Labs on mobile sensors. He is also working with Insplorion (a Swedish start-up) to understand how to use Nano-Plasmonic sensing to measure NOx Gases.
Alongside this, Rohit is involved in various citizen-science projects. For example, he organises workshops to build low-cost monitors.
Plus Rohit has used mobile trackers on Sheffield school-runs to assess how much children are exposed to pollutants. The hope is that the awareness will help bring a paradigm shift in policy making and reducing pollution overall.
Our Rohit is rarely out of the news!
First UK warning system for woodburner air pollution. In 2022, Rohit launched Burner Alert, the UK’s first warning system for woodburner air pollution. The launch was covered by The Guardian and iNews.
Air pollution rebounds as UK lockdown measures ease and cars hit the roads. iNews spoke to Rohit about post-lockdown air pollution.
Multidisciplinary knowledge exchange and cake. At Internal Seminars and Cake – ISAC – the Grantham Scholars showcase their work in an informal setting. Rohit was one of the presenters who Centre Administrator Jana Green captured on camera for this write up of ISAC March 2022.
Our air pollution expert in the Guardian. In 2021 Rohit published work that shows wood burners cause indoor pollution. As a result, he was interviewed by the Guardian’s Environment Editor Damian Carrington. Other media picked up the story too.
Rohit appeared on the BBC’s One Show recently to talk about air pollution and how it changed due to lockdown. He also spoke about how air pollution affects death due to Covid-19. You can find a link to the interview and a transcript here.
For an overview of Rohit’s work on air pollution, read this interview with him: Air pollution in Sheffield: interview with Rohit Chakraborty
Read Rohit’s blog: low-cost ‘Volunteer Sensors’ to help solve the air pollution problem in Sheffield
You can follow Rohit on Twitter.
Indoor Air Pollution from Residential Stoves: Examining the Flooding of Particulate Matter into Homes during Real-World Use
by Rohit Chakraborty, James Heydon, Martin Mayfield 1OrcID and Lyudmila Mihaylova.
Can portable air quality monitors protect children from air pollution on the school run? An exploratory study
James Heydon & Rohit Chakraborty
Environmental Monitoring and Assessment volume 192, Article number: 195 (2020)