Data Science of the Natural Environment

We will develop a data science of the natural environment, deploying modern machine learning and statistical techniques to enable better-informed decision-making as our climate changes. While an explosion in data science research has fuelled enormous advances in areas as diverse as eCommerce and marketing, smart cities, logistics and transport, health and wellbeing, these tools have yet to be fully deployed in one of the most pressing problems facing humanity, that of mitigating and adapting to climate change. This project brings together world-leading statisticians, computer scientists and environmental scientists alongside an extensive array of key public and private stakeholder organisations to effect a step change in data culture in the environmental sciences.

The project will develop a new approach to data science of the natural environment driven by three representative grand challenges of environmental science: predicting ice sheet melt, modelling and mitigating poor air quality, and managing land use for maximal societal benefit. In each motivational challenge, there is already an extensive scientific expertise, with intricate models of processes at multiple scales. However this sophisticated modelling of system components is usually let down by naive integration of these components together, and inadequate calibration to observed data. The consequence is poor predictions with a high level of uncertainty and hence poorly-informed policy making. As new forms of environmental data become available, and the pressures on our natural environment from climate change increase, this gap is becoming a pressing concern, and we bring an impressive team to bear on the problem.

A key theme of the project is integration, developing a suite of novel data science tools which work together in a modular fashion, and with existing scientifically-informed process models. By building a team that spans the inter-disciplinary divisions between data and environmental scientists we can ensure the necessary interoperability of methods that is currently lacking. Working with the full range of stakeholder environmental organisations will enable continual co-design of the programme and training of end-user scientists to ensure a reduction of the skills gap in this area. The resultant culture shift in the data literacy of the environmental sciences will enable better decision-making as climate change places ever greater strains on our society.

We seek a coupling of cutting edge intellectual endeavour with a strong focus on impact. This work is supported by an impressive set of twenty-two partners that represent a who's who of the environmental community alongside key data science players:

Our partners include (contacts in brackets): the Environment Agency (Stuart Homann), Defra (Andy Stott), the Met Office (Vicky Pope, Alberto Arribas, Fiona O'Connor), JBA Trust (Rob Lamb), CEFAS (Jon Barry), the National Oceanography Centre (Kevin Horsburgh), the Centre for Polar Observation and Modelling (Andy Shepherd), British Antarctic Survey (David Vaughan), Natural England (Ruth Waters), Natural Resources Wales (Jim Latham), the Joint Nature Conservation Committee (Deborah Procter), the National Centre for Atmospheric Research (Jean-François Lamarque), the Scottish Government (Andrew Taylor), SEPA (Colin Gillespie), Jülich Forschungszentrum (Thomas Lippert), and the DAFNI Consortium (Jim Hall). In terms of health impacts, we also have the Asthma UK Centre for Applied Research as a partner (Aziz Sheik, Colin Simpson). Mike Berners-Lee (Small World Consulting) has a crucial role in translating science into policy. The RIDE Forum (Vicky Pope) - formerly LWEC - is on board to support outreach to the public sector. In terms of data science, we have Microsoft Research (Kenji Takeda), BT (Fraser Burton) and EDF (Hugo Winter) as partners. We also look forward to working closely with the Alan Turing and Farr Institutes, with links to both.

In approaching partners, we have observed a real hunger for more sophisticated data science methods tailored for the environment. The partners will be intrinsically folded into the research through the ongoing co-design of the project (continuing the process that started with the scoping of the motivating challenges). The key mechanism to support continual co-design is the use of an agile development methodology where we fold in the end user community as an intrinsic part of the development process, and this includes challenge and methodological workshops, supplemented by monthly show and tell sessions, where we get frequent feedback from different end user groups at key stages of the research.

The partners also support a multi-faceted impact strategy:

1. Impact on science and its organisation. We place significant emphasis on achieving a transformative impact on science by working closely with our partner organisations to achieve the necessary organisational culture shift towards one that embraces the full potential of data science and its role within a new kind of open, integrative and collaborative science. Key mechanisms: challenge themes, continuous co-design, workshops, our agile methodology and show and tell sessions.

2. Impact on training. We will address the acute skills shortages in environmental data science through the development of a new breed of researchers that understand both contemporary data science practices and the challenges of environmental science. We also place emphasis on training to amplify this impact to partner organisations and beyond. Key mechanisms: training events and online materials, summer schools.

3. Impact on policy. We also focus heavily on the role of data science to support the development of mitigation and adaptation policy, with this work being enhanced by associated research around data, trust and communication (as a planned PhD topic). We will also utilise Small World Consulting, JBA and the RIDE Forum in this translational work. Key mechanisms: policy workshops, secondments.

4. Impact on the public. We plan a number of public outreach events as part of the programme of research. Key mechanisms: Data Science Meetups, public lectures, Café Scientifique.

The combined contribution from the partners is £542,680. Further details of our impact strategy can be found in Pathways to Impact (also refer to letters of support).