The Joint Centre builds upon current Environmental Intelligence research and expertise at both the University of Exeter and Met Office. Current projects include:
GreenSight
This UKRI funded project uses AI to twin satellite imagery of Green Belt land in the UK with climate models in the Met Office to better predict the instance and spread of wild fires.
Machine Learning for UK Rivers and Waterways
JCEEI Researcher Remy Vandaele has received funding to continue his work to use Computer Vision and CCTV to automatically identify when sluice gates in local rivers have become blocked with rubbish- saving time and improving river quality. Remy’s work on blockage classification has been published in the Journal of Hydroinformatics (available here), and his work on trash segmentation has been accepted at the British Machine Vision Conference 2024 (available soon).
Upskilling our Climate Scientists
The JCEEI are supporting the University of Exeter to deliver training in Machine Learning to over 100 Met Office staff by April 2025. This exciting project, funded by the Transatlantic Data Science Academy and delivered through the Met Office College, is called the ‘Machine Learning Foundation’ and will deliver research led education both in online and in person formats to ensure the Met Office remains at the cutting edge of climate research.
RotorSense
Researchers from the Met OƯice and University of Exeter are collaborating to improve forecasts of rotor clouds and winds – a type of turbulent, low-level wind pattern that forms in mountainous or hilly terrain. Rotors make landing helicopters in uneven terrain particularly challenging so this project uses LIDAR data (3D terrain mapping) and machine learning to improve aviation safety
Local Data; Global Plankton
Plymouth Marine Lab and IBM are teaming up with the JCEEI to gather local data on phtyo plankton and carbon in the ocean to improve geospatial foundation models. This work will create a key capability for more accurate carbon and climate modelling.
Habitat ID
Natural England monitor and classify habitats, for instance as ‘Coniferous Woodland’, ‘Heathland’ or ‘Lowland Meadow’. The JCEEI are working with them to develop an application that will use photos, potentially from citizen scientists, and a checklist to automatically identify and record these.
UK Climate Prediction Chat Bot
We have developed a chat bot to provide accurate evidence-based answers about climate change to the general public and journalists. This capability ensures the Met Office can provide 24/7 factual responses drawing on a curated archive of peer reviewed papers. This tool counters misinformation and by drawing on a verified source of information does not struggle with the inaccuracies many untrained chat bots such as Chat GPT are associated with. The Chat Bot provides reliable answers in plain English and is easily used by the wider general public including schools.
AI for Pollen
To measure pollen levels scientists have previously needed to visually identify each specimen under the microscope. A JCEEI team, in partnership with Swansea University have used computer vision to automatically detect the most common grass pollens, improving the speed and accuracy of pollen reports and opening up the potential to map historic pollen specimens against climate data and model the impact of climate change on flora.
CLIMAR®
Framework for quantifying and visualising the risks associated with environmental and climatic change.
Data Science and AI used to integrate data on each component to create decision-ready information.
Visualise results in a form that is accessible to a range of audiences policy makers, industry, general public.
Air Quality Digital Twin (AQDT)
The Air Quality Digital Twin (AQDT) is a collaborative project between the JCEEI and the University of Manchester to develop a prototype digital service that reliably replicates air quality and personal exposures to pollutants.
In the UK, exposure to poor air quality is one of the biggest environmental threats to public health. Clean air guidelines are currently based on ambient concentrations of pollutants, yet these do not consider the exposure experienced by individuals. In addition to the underlying hazard, the health risk due to poor air quality should also account for the individual’s personal exposure and vulnerability.
In this project, we will create an air quality digital twin demonstrator as an interactive web-based user interface. This will display estimates of personal exposure and model how it can be affected by changes to the underlying demographics or emissions profiles in an urban environment. The work will exemplify how environmental intelligence can be used to provide meaningful insight for improved decision strategies against exposure to poor air quality in the city of Manchester.
Renewing biodiversity through a people-in-nature approach (RENEW)
The RENEW project is led by a collaboration between the University of Exeter and the National Trust, and funded by NERC. The JCEEI will utilise its expertise to act as the core ‘technical engine’ of RENEW. The JCEEI team will integrate data science and AI capability within the different RENEW work streams, providing a computational ecosystem that will enable data integration and advanced data science and AI methodologies to be applied at scale.
The RENEW computational ecosystem will also act as a host for web-based dashboards, tools and apps. It will facilitate the co-development of bespoke tools and datasets together with accessible interfaces, apps and dashboards. The result will be an interactive ‘Biodiversity dashboard’ containing a suite of visualisation tools that will provide a unified route to data and information and to highlight the outputs of the analytic work within RENEW in a form that can feed directly into decision making processes and inform business and investment decisions that impact UK biodiversity, particularly those that affect land-use.
Decision support under climate uncertainty for energy security and net zero
Working with the University of Edinburgh, Imperial College London and the University of Warwick we are developing data science and AI methods to quantify uncertainty in frequency of extreme weather effects on future power systems, and for policy and planning decision support against a background of uncertain climate.
Funded by the Alan Turing Institute, this project will develop decision support methodology relating to vital societal issues of decarbonisation and adapting to effects of climate change.
Climate Resilience Demonstrator (CReDo)
Delivered through the government funded National Digital Twin programme, CReDo will develop, for the first time in the UK, a digital twin across energy, water and telecoms networks to provide a practical example of how connected data can improve climate adaptation and resilience.
The CReDo project looks specifically at the impact of flooding caused by climate change on energy, water and telecoms networks. It demonstrates how those who own and operate them can use secure information sharing, across sector boundaries, to mitigate the effect of flooding on network performance and ensure reliable service delivery to customers.
Impact of Climate Change on Agriculture: Building the next generation models to support resilient agricultural policy
We are building an integrated national crop modelling framework, using currently available models and data to allow the testing and development of new policies or management practices prior to implementation. This modelling framework will support interventions aimed at ensuring the UK’s continued food security.
Environmental Monitoring: Blending satellite and surface data
Delivering the intelligent fusion of data from satellite and in-situ surface sensors to help understand our changing planet. We are developing reproducible and interpretable methods to increase scientific understanding, build tools to help environmental measurement planning, and provide the underpinning tools for intelligent real-time monitoring.
GAPH On-line: Breathing Clean Air
Our innovative work in developing the Data Integration Model for Air Quality (DIMAQ), enabled us to give the WHO access to accurate information on population-exposures to fine particulate matter air pollution for every country, even those for which there are no recognised monitoring networks.
