Turing TIN Data Study Group – February 2023

Learn more Add to Calendar 02/13/2023 09:00 AM 03/03/2023 05:00 PM Europe/London Turing TIN Data Study Group – February 2023 Location of the event
Monday 13 Feb 2023 - Friday 03 Mar 2023
Time: 09:00 - 17:00

Event type

Data Study Groups
Free- Virtual hackathon

Event series

Data Study Groups

Introduction

Stage 1: Precursor Stage (part-time, online)

•    The precursor stage will last one week in the run up to the 'event stage' (Monday 13 – Friday 17 February).

•    The maximum time commitment is 2.5 hours a day.

•    This includes online workshops, presentations and team building which will prepare participants for the 'event stage'.

Stage 2: Event Stage (full-time, online)

•    The 'event stage' will run virtually over two weeks (Monday 20 February – Friday 3 March).

•    The core working hours will be 9:00 - 17:00 GMT every weekday. However, flexibility will be demonstrated regarding those participating in different time zones.

•    Group work begins and continues throughout.

Applicants should be able to commit to the duration of the event. The Alan Turing Institute is committed to supporting individual circumstances, please do not hesitate to email [email protected] to discuss any reasonable adjustments.

Challenges

The challenges are: 

Global Witness

Identifying Unregulated Mining Sites using Historical Satellite Data 

Global Witness aims to use satellite imagery (Planet, Sentinel and Landsat) to detect the presence of specific types of unregulated and destructive mining of critical minerals. Their recent press release highlights some of the catastrophic impacts that unregulated mining has on the environment and people’s health, where the pollution caused by seeping chemicals into water bodies could take up to 100 years to clean-up. Their historical dataset makes use of both high- and low-resolution satellite imagery. The project aims to use state-of-the-art image-based machine learning techniques to identify places where unregulated mining may be occurring to address sustainability issues in one of the most significant sub-sectors of the mining industry for renewable transition. 

Keep Wales Tidy & Keep Scotland Beautiful 

Towards Data-Driven Litter-Free Streets 

Keep Wales Tidy (KWT) and Keep Scotland Beautiful (KSB) are both charities that are committed to working with local communities across the UK to protect our environment now and in the future. As their current methods of ensuring streets are being kept tidy and clear of litter are through validation surveys, this project aims to investigate the use of image-based machine learning to create a litter recognition model. The dataset includes a database of images of litter which KWT and KSB have collected. These images, alongside ethical and societal considerations, will be used to inform the charities of the feasibility of their collected images to classify an area’s cleanliness and also procedural improvements or changes for future data collections. 

National Oceanography Trust 

Towards a Deeper Understanding of Eddies using Machine Learning 

The National Oceanography Centre (NOC) is the UK's centre of excellence for oceanographic sciences. They are a national research organisation, delivering integrated marine science and technology from the coast to the deep ocean, and are one of the top five institutions of its kind in the world. 

This project aims to use state-of-the-art machine learning techniques on marine science satellite, remote sensing and robotic datasets to better understand, detect and track eddy currents. Understanding, detecting, and tracking of eddies contributes not only to the oceanic sciences directly, but also to the capabilities of NOC’s fleet of autonomous research vehicles, such as gliders and autonomous underwater vehicles (AUVs), that are actively used for these scientific studies. 

Useful knowledge areas for this challenge are likely to include experience with remote sensing, GIS systems, and routing problems, although experience with fluid dynamic modelling or other complex environment simulations would be a benefit.  

The John Muir Trust 

Defining Wild Places across the UK using Social and Physical Datasets 

This project aims to research innovative and objective methods for identifying wild places across the UK with the John Muir Trust. The Trust aims to develop a Wild Places Register to understand where wild places are in the UK, what defines them and what the value of wild places are to people across the UK. The Trust has also divided the four nations into units that are meaningful from a wild places perspective, using pre-existing data on biogeographic zones and landscape character assessments the Trust has identified 46 “wild place zones” across the UK. The dataset includes habitat maps and landcover maps from across the four nations of the UK, demographic data, satellite imagery, and data from a nationwide survey of the UK’s favourite wild places, due to take place in January.  

This is a new and exciting research area because the physical dataset has not yet been explored using computer vision and image-based machine learning techniques and the nationwide survey data on an extremely diverse group of peoples’ interpretation of “what is a wild place” can be perceived as very novel. 

Sustrans  

Towards Equitable Walking and Cycling Infrastructure for All 

At Sustrans we know that the benefits of walking, cycling, wheeling and healthy places aren’t experienced in the same way by everyone, and we are looking for data-driven solutions to help us deliver and drive more equitable provision of active travel infrastructure and interventions. A key question relates to how and whether people can access our projects, including the National Cycle Network. We would like to determine how accessible and permeable the National Cycle Network is, what the formal and informal access points are, as well as what data can help us understand about the quality of the routes for different users. We would further like to combine geospatial data with our count and survey data to see if we can understand how accessibility impacts on use and usability. 

About the event

What are Data Study Groups?

These are intensive 'collaborative hackathons' hosted at the Turing, which bring together organisations from industry, government and the third sector, with talented multi-disciplinary researchers from academia.

Organisations act as Data Study Group 'Challenge Owners', providing real-world problems and datasets to be tackled by small groups of highly talented, carefully selected researchers.
Researchers brainstorm and engineer data science solutions, presenting their work at the end of the week.

How to apply

Application is now closed.

Why apply?

The Turing's Data Study Groups are popular and productive collaborative events and a fantastic opportunity to rapidly develop and test your data science skills with real-world data. The event also offers participants the chance to forge new networks for future research projects and build links with The Alan Turing Institute – the UK’s national institute for data science and artificial intelligence.

It’s hard work, a crucible for innovation and a space to develop new ways of thinking.

Read reports from previous Data Study Groups to see challenges and outcomes.

FAQs

What if I am already part of the Turing community?

If you are employed by one of the Institute’s 13 university partners, please contact your University Liaison Manager – list available here – to make them aware of your application. They can provide support, answer questions and involve you as part of the Turing community at your university from now on.

If you are employed at a university that received a Turing Network Development Award, please contact your Award lead – list available here (scroll to the bottom of the page) – to make them aware of your application.

More FAQs for Data Study Group applicants.

Find out more

Learn more about being a DSG participant including FAQs

How to write a great Data Study Group application

Queries can be directed to the Data Study Group Team