Introduction
The London Air Quality project began in 2016 with the aim to improve air quality over London by utilising city-wide air quality sensors to develop machine learning algorithms and data science platforms to better understand these issues. The team are now working to maximise the impact from this project by focusing on implementing the final stages of software engineering to finalise APIs and increase the scalability for delivering live air quality forecasts.
Explaining the science
In the first phase of the London Air Quality project, researchers developed 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. To find out more about the first phase, follow the link to the project page here.
Project aims
In order to maximize impact from the project we aim to demonstrate live 24-hour ahead pollution forecasting for an extended period of time in order to attract users, analyse and tune the behaviour of the system and the models with our policy partners, and release outputs to Greater London Authority (GLA), Transport for London (TfL), and the public domain via our APIs.
Applications
In this second phase, the team will maximise the impact from these forecast by demonstrating live 24-hour ahead pollution forecasting for an extended period of time. This will attract more users to the platform, enable the fine tuning of the system and the models with our policy partners, and release outputs to GLA, TfL, and the public domain via our APIs.
Organisers
Collaborators
Researchers and collaborators
Sueda Ciftci
Research Assistant/Research Software Engineer, University of Warwick
