Imperial College London Featured PhD Programmes
Gdansk University of Technology Featured PhD Programmes
Queen’s University Belfast Featured PhD Programmes

AI to the rescue of climate change, modelling air quality for cleaner urban planning


   School of Computing and Information Science

This project is no longer listed on FindAPhD.com and may not be available.

Click here to search FindAPhD.com for PhD studentship opportunities
  Dr L Babu Saheer, Dr J Zarrin  Applications accepted all year round  Self-Funded PhD Students Only

About the Project

Research Group

Computing, Informatics and Applications Research Group.

Proposed supervisory team

Dr Lakshmi Babu Saheer

Dr Javad Zarrin

Theme

Artificial Intelligence, Machine Learning, Data Science and Applications.

Summary of the research project

Climate change is the main challenge that humanity is facing today, threatening the existence of life on earth. Awareness campaigns and drastic steps towards bringing the situation under control have been initiated in every nook and corner of the world. Both developed and underdeveloped countries are working hard to tackle this problem. Artificial Intelligence has big potential to help mankind whereever (big) data is available to help build models and make predictions or provide prescriptive solutions. Such models for emissions, resources, energy consumption, etc have already been statistically worked out by specialist groups around the world to tackle climate change (UCL Energy Models, 2019).

(Climate change AI, 2019) is a classic example of such an initiative. There is big data available in the fields of energy consumption, transport, building & cities, carbon footprint, farming, climate change & prediction etc (Rolnick, et.al., 2019). It is hard to mine all this data in a reasonable time to get useful resources with mathematical models. The approach for this PhD would be to first identify the most useful and informative data for the identified topics of climate change and start to build machine learning models and methodologies to extract useful and relevant information in the form of predictions or prescriptions. Even though a lot of data is available for every field, it is very difficult to gather majority of these information in a structured useful format.

The topic proposed for this PhD would be to look at the parallel data on road traffic, emissions, air quality, vegetation and other related information like weather around UK or even specifically cities like London, or Cambridge. This can directly help us plan our cities and traffic routes or even come up with laws to keep our carbon footprint under control. This research needs traffic and air quality or emissions monitoring datasets and possibly auxiliary information on vegetation and other related areas that would directly impact air quality.

The traffic monitoring data in UK is available with different authorities like:

  1. Cambridgeshire county council
  2. Highways England data
  3. Traffic for London

Emissions monitoring data in UK is available with authorities like:

  1. London Air
  2. Government Monitoring
  3. Defra, UK Air
  4. Traffic for London

The challenge would be to map these different sources to come with parallel data to extract useful information through machine learning approaches like SVMs or Neural Networks (Nathan, et.al., 2016), (Massimiliano, et.al., 2013), (Robert, et.al., 2016), (Ioannis & William, 2015). Traffic for London seems to have usable parallel data for traffic and emissions and is known to publicly share this information to support research. This could be a starting point for this research, extending to other cities or more resources for further information. Initial research on this topic has revealed several challenges with this data including missing and inconsistencies data. The first step of this project might to design solutions for an effective data collection based on the initial studies of big data to build custom solutions and policies around transportation.

Using AI for climate change control through efforts like the traffic-emissions control and improving air quality through urban vegetation planning could be a major step forward to build upon strategies for tackling climate change based on big data available in various fields to build a sustainable future.

Where you'll study

Cambridge

Funding

This project is self-funded.

Details of studentships for which funding is available are selected by a competitive process and are advertised on our jobs website as they become available.

Next steps

If you wish to be considered for this project, you will need to apply for our Computer and Information Science PhD. In the section of the application form entitled 'Outline research proposal', please quote the above title and include a research proposal.


References

UCL Energy Models, 2019. Energy models at the UCL Energy Institute, https://www.ucl.ac.uk/energy-models/ [Accessed 25 November 2019]
Climate Change AI, 2019. Climate Change AI, https://www.climatechange.ai/ [Accessed 25 November 2019]
Rolnick, David, et.al., 2019. Tackling Climate change with Machine Learning, https://arxiv.org/pdf/1906.05433.pdf [Accessed on 25 November 2019]
Nathan Mundhenk, Goran Konjevod, Wesam A Sakla, and Kofi Boakye, 2016. A large contextual dataset for classification, detection and counting of cars with deep learning, European Conference on Computer Vision, pages 785–800. Springer.
Massimiliano Gastaldi, Riccardo Rossi, Gregorio Gecchele, and Luca Della Lucia, 2013. Annual average daily traffic estimation from seasonal traffic counts, Procedia-Social and Behavioral Sciences, 87:279–291.
Robert Krile, Fred Todt, and Jeremy Schroeder, 2016. Assessing roadway traffic count duration and frequency impacts on annual average daily traffic estimation, Technical Report FHWA-PL-16-012, Federal Highway Administration, Washington, D.C., United States.
oannis Tsapakis and William H Schneider, 2015. Use of support vector machines to assign short-term counts to seasonal adjustment factor groups, Transportation Research Record: Journal of the Transportation Research Board, (2527):8–17.
PhD saved successfully
View saved PhDs