Introduction

Air quality in London has improved in recent years as a result of policies to reduce emissions, primarily from road transport, however further improvements are critical to public health. By utilising city-wide air quality sensors this project is developing machine learning algorithms and data science platforms to understand and improve air quality over London.

Explaining the science

Air quality in London has improved in recent years as a result of policies to reduce emissions, primarily from road transport. However, significant areas still exceed NO2 EU Limit Values. Poor air quality has particularly been identified as a threat to health, with an estimated 9,000+ Londoners dying early every year. Similar issues affect most cities across the UK and Europe.

At the same time, a revolution is happening in air quality monitoring. Traditionally, a relatively small number of reference quality sensors are used - followed by a period of modelling to create a London-wide snapshot (currently based on 2013 data). With the proliferation of increasingly affordable air quality sensors, it is possible to monitor air pollution at thousands of different locations in a city - greatly enhancing our ability to target and prioritise planned interventions. Increasingly companies, non-profit organisations, community groups and individuals also want to monitor the air and are investing in sensors.

This project develops machine learning algorithms, data science platforms and statistical methodology to integrate data and air pollution measurements from various heterogeneous sources in order to better estimate and accurately forecast air pollution across the city of London. Given these hyper-local estimates and associated uncertainty the group then develops algorithms and optimisation techniques to inform citizens and help design and evaluate government policy.

Project aims

The main challenges of this work are:

  • To ensure that data from a wide range of networks can be brought together to a single place for analysis
  • To bring data into air quality models from a range of quality of sensors
  • To ensure that we monitor the effectiveness of the different interventions planned across London
  • To present the best estimates and forecasts in a way that app and web developers can then use to inform Londoners
  • To accurately find low pollution routes for Londoners to follow when walking, cycling or running through the city

The project researchers are developing machine learning algorithms, statistical methodology and data science platforms to understand and improve air quality over the city of London. Integrating varying-fidelity heterogeneous sensors in an overall real-time monitoring network for air quality, the project will develop state of the art machine learning models for high resolution air quality forecasting and change-point detection. This will help establish the most effective places to site future sensors, and inform policy to make targeted interventions that reduce the levels of pollution in key areas and at key times.

Applications

The goals of the project will be complemented by the parallel development of APIs and mobile apps to provide reliable, frequently updated and highly localised air quality data and forecasts for Londoners. Graph optimisation algorithms will be developed to use the air quality forecasts to find less polluted routes for people walking, running and cycling around London’s streets. Algorithms will be analysed for their complexity, efficiency and practicality.

Recent updates

January 2019

  • Jeremias Knoblauch has been selected as one of 21 PhD students worldwide to receive the Facebook Fellowship award. The award consists of a stipend worth $84,000 and additionally covers two years of university tuition fees.
  • Paper to appear: Aglietti. V., Damoulas. T. & Bonilla. E. (2019). Efficient Inference in Multi-task Cox Process Models. The 22nd International Conference on Artificial Intelligence and Statistics (AISTATS 2019).

December 2018

Ollie Hamelijnck gives interview to Wired, discussing how live traffic data from Waze can help predict air quality in real-time in London.

November 2018

October 2018

September 2018

June 2018

Paper to appear: Knoblauch, J., Jewson, J. & Damoulas T. (2018). Doubly Robust Bayesian Inference for Non-Stationary Streaming Data using β-Divergences (NIPS 2018).

May 2018

October 2017

The Turing's programme for data-centric engineering announced a collaboration with the Mayor of London to tackle air pollution in London using data sensors. Read articles in City AM, Business Daily and Air Quality News. Read the Turing press release.

Organisers

Researchers

Contact info

[email protected]

Related publications

Collaborators

Funders