Data Science of the Natural Environment

Lead Research Organisation: Lancaster University
Department Name: Mathematics and Statistics

Abstract

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.

Planned Impact

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 devepment 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).

Publications

10 25 50
 
Description Invited expert for Climate Change Citizens' Jury, Lancaster
Geographic Reach Local/Municipal/Regional 
Policy Influence Type Participation in a advisory committee
Impact Climate science expert for the 30 participants of Lancaster People's Jury on Climate Change, who were selected from the local general public. This involved briefing the participants on climate science and then addressing their questions related to the science, policy and future emissions. The process was instigated and funded by Lancaster City Council, and is being delivered by Shared Future CIC.
URL https://sharedfuturecic.org.uk/category/climate-change/
 
Description Use of ecological sampling design algorithm for national malaria programs (mosquito surveillance)
Geographic Reach National 
Policy Influence Type Implementation circular/rapid advice/letter to e.g. Ministry of Health
Impact The use of the ecological sampling design algorithm developed by us allows an optimisation of the entomological spatial sampling design for areas with limited prior information. This has been proof to improve accuracy in the estimates but also reduced costs in the logistics.
 
Description Detecting soil degradation and restoration through a novel coupled sensor and machine learning framework
Amount £811,651 (GBP)
Funding ID NE/T012307/1 
Organisation Natural Environment Research Council 
Sector Public
Country United Kingdom
Start 01/2020 
End 12/2022
 
Description Explainable AI for UK agricultural land use decision-making
Amount £43,151 (GBP)
Funding ID NE/T004002/1 
Organisation Natural Environment Research Council 
Sector Public
Country United Kingdom
Start 07/2019 
End 07/2020
 
Description Methodologically Enhanced Virtual Labs for Early Warning of Significant or Catastrophic Change in Ecosystems: Changepoints for a Changing Planet
Amount £203,419 (GBP)
Funding ID NE/T006102/1 
Organisation Natural Environment Research Council 
Sector Public
Country United Kingdom
Start 11/2019 
End 11/2020
 
Description 12th International Conference of the ERCIM Working Group on Computational and Methodological Statistics, UK 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact The event was organized by the ERCIM Working Group on Computational and Methodological Statistics (CMStatistics) and Birkbeck University of London.
I made a presentation on "Using Bayesian hierarchical models for uncertainty quantification in landscape problem".
Year(s) Of Engagement Activity 2019
URL http://www.cmstatistics.org/conferences.php
 
Description AI for Environmental Sciences, BAS, Cambridge 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact bringing together the various research disciplines (machine learning, environment, health, structural engineering etc) with decision makers from business and policy groups to discuss the application of data science techniques to environmental challenges.
Year(s) Of Engagement Activity 2019
URL https://www.bas.ac.uk/blogpost/ai-workshop-2019/
 
Description Attendance at CliMathNet conference 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Other audiences
Results and Impact Adam Sykulski attended and presented at the CliMathNet conference. CliMathNet is a network which aims to bring together Climate Scientists, Mathematicians and Statisticians to answer the key questions around Climate modelling (in particular understanding and reducing uncertainties in observation and prediction).
Year(s) Of Engagement Activity 2018
URL http://emps.exeter.ac.uk/climathnet/2018conferencereading/
 
Description Centre of Excellence in Environmental Data Science (CEEDS) Launch Event 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Other audiences
Results and Impact The event described the exciting new work of CEEDS and brought scientists of different disciplines together to contribute to the vision of CEEDS. The idea was to bring environmental and data scientists together to identify new ways to tackle environmental science problems using statistical methods. The workshop led to many useful discussions including the development of several grant proposal ideas, some of which were successful in the recent calls (E.g. Digital Environment and SPF).
Year(s) Of Engagement Activity 2019
 
Description Company visit - Rezatec 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Industry/Business
Results and Impact Rebecca Killick attended an exploratory workshop at Rezatec, a satellite imaging company.
Year(s) Of Engagement Activity 2018
 
Description DSNE Conference July 2019 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Other audiences
Results and Impact Conference organised by DSNE project, which included talks and discussions with project partners such as Met Office and Natural Resources Wales. The conference sparked questions and discussions and has led to discussions of further collaboration in the future.
Year(s) Of Engagement Activity 2019
URL https://www.lancaster.ac.uk/data-science-of-the-natural-environment/dsne-conference-2019-/
 
Description Geospatial/sampling teaching 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Professional Practitioners
Results and Impact The course was designed to provide spatial statistical skills (from sampling to mapping) to a group of 30 people of different background (Academics, technicians, health researchers, public health managers) in Riyadh, Saudi Arabia.

A PhD student as been funded by the National Health Laboratory of Saudi Arabia to work on vector borne diseases in Saudi Arabia (Luigi Sedda main supervisor). The student is currently doing the PhD in Spatial Epidemiology at Lancaster University.
Year(s) Of Engagement Activity 2018
URL http://chicas.lancaster-university.uk/people/omar.html
 
Description International invited speaker Italy 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Postgraduate students
Results and Impact This was a seminar for Academics at the University of Salento in Italy. I am now collaborating with them in order to improve bio-geostatistical models for distribution of vectors and diseases.
Year(s) Of Engagement Activity 2018
 
Description Invited Session International conference 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Professional Practitioners
Results and Impact This was an invited and funded (by the Entomological Society of America) session within the 2018 ESA, ESC and ESBC Joint Annual Meeting: Crossing Borders: Entomology in a Changing World. The session was well attended and debate carried over after the session.

The interest in this session produce requests from two international scientists to join the framework of the current award.
Year(s) Of Engagement Activity 2018
URL https://www.entsoc.org/event-calendar/2018-esa-esc-and-esbc-joint-annual-meeting-entomology-2018
 
Description Invited speaker (International Workshop) 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Other audiences
Results and Impact Presentation given on methods for modelling complex systems, such as landscape decisions, including how uncertainty effects decision-making, which sparked debate and capacity building with groups undertaking similar modelling initiatives in South Korea and other parts of Asia
Year(s) Of Engagement Activity 2019
 
Description Invited to teach a course on "Spatio-temporal analysis of infectious diseases" by the Department of Applied Mathematics, Fundação Getúlio Vargas University (Brazil). 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Postgraduate students
Results and Impact The workshop allowed students to learn and apply geostatistical methods and geospatial analyses in R. Most of them are interested to use these methods in their projects or future research.
Year(s) Of Engagement Activity 2020
URL https://emap.fgv.br/sites/emap.fgv.br/files/modelos_estocasticos_espaco-temporais_0.pdf
 
Description Isaac Newton Institute scoping workshop "Evidence Based Decisions for UK Landscapes - Rural and Urban Land use, Coastal and Inland Waters" 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact Evidence Based Decisions for UK Landscapes - Rural and Urban Land use, Coastal and Inland Waters, 17-18 September 2018, Isaac Newton Institute, Cambridge (David Leslie, Gordon Blair and Paula Harrison attended). Paula Harrison gave the keynote "Integrated Modelling of Landscapes to Understand Cross-Sectoral Interactions, Synergies and Trade-offs under Scenarios of Environmental Change". The outcome is a planned INI programme for July 2019, developing mathematical tools to assist in land use decision making.
Year(s) Of Engagement Activity 2018
 
Description Machine Learning Autumn School 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach International
Primary Audience Postgraduate students
Results and Impact participated in the Autumn School on Machine Learning held in Tbilisi, Georgia, October 3-11, 2019. The school was organised by the International Black Sea University with the support of Shota Rustaveli National Science Foundation of Georgia (SRNSFG). The audience of the autumn school was BSc, MSc and PhD students, researchers as well as industry professionals. The school included 7 courses on machine learning techniques and applications presented by top research leaders in the domain.
Year(s) Of Engagement Activity 2019
URL https://cte.ibsu.edu.ge/autumn/
 
Description Mathematical and statistical challenges in landscape decision-making, Isaac Newton Institute for Mathematical Sciences, Cambridge, UK 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Professional Practitioners
Results and Impact The one-month event brought together top researchers and practitioners such as those interested in agriculture, forestry, water resources and biodiversity,
with mathematicians, statisticians and computer scientists expert in system modelling, uncertainty quantification and decision making to discuss recent developments in landscape decision-making. I gave a talk on "Uncertainty quantification in high-dimensional landscape problems using Bayesian hierarchical models"
Year(s) Of Engagement Activity 2019
URL https://www.newton.ac.uk/event/ebd
 
Description Mathematics of Deep Learning at the Isaac Newton Institute on 23 May 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Industry/Business
Results and Impact one day event aimed to bring people from academia and industry together to discuss the science and mathematics behind deep learning and data science.

The workshop featured talks from leading academics, as well as researchers from industry and provided a wide perspective on the many facets of modern data science.
Year(s) Of Engagement Activity 2019
URL https://gateway.newton.ac.uk/event/ofbw46
 
Description Partner's event 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Policymakers/politicians
Results and Impact We invited our project partners to a workshop at Lancaster University / CEH to present the project and find out from the partners how best to engage with them going forward.
Year(s) Of Engagement Activity 2019
 
Description Royal Society of Chemistry public talk on "Air quality and climate change" 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Public/other audiences
Results and Impact Invited public lecture on air quality and climate change as part of the Royal Society of Chemistry's northwest region programme. The event was sold out (~50 attendees) and there was a lot of discussion and questions during and after the talk, including from audience members who expressed that their understanding had increased and views on pollution and climate change had changed. There was particular engagement with attending sixth form and year 11 students, who expressed an intensified interest in the issues discussed and environmental change in general. The slides were shared with an attending teacher from that school, who used them in their teaching.
Year(s) Of Engagement Activity 2018
 
Description Royal Society of Chemistry public talk on Oceans 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Regional
Primary Audience Public/other audiences
Results and Impact Public lecture on Oceans and Data Science at the Storey in Lancaster. Hosted by the Royal Society of Chemistry
Year(s) Of Engagement Activity 2019
URL https://www.rsc.org/events/detail/41393/oceans
 
Description Scottish Seminar on Formal Modelling, Verification, and Synthesis 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Other audiences
Results and Impact participated in Scottish Seminar on Formal Modelling, Verification, and Synthesis - a SICSA-funded Workshop co-located with QEST 2019. The International Conference on Quantitative Evaluation of Systems (QEST) is the leading forum on quantitative evaluation and verification of computer systems and networks, through stochastic models and measurements. The aim of the seminar is to bringing together researchers interested in formal modelling, verification and synthesis applied to computer systems and networks, to address current challenges and relevant questions, to communicate and share their experiences on formal approaches to qualitative or quantitative evaluation of systems.
Year(s) Of Engagement Activity 2019
URL http://www.dcs.gla.ac.uk/research/formalmethods/sfmoves/
 
Description Session organised on AI for the environment (Natural Capital Initiative Summit) 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Other audiences
Results and Impact Session organised on "AI for the environment" at the Natural Capital Initiative Summit on "Valuing our Life Support Systems" in London, which consisted of talks and debate around the potential of AI approaches to deliver natural capital solutions to practitioners and policy-makers
Year(s) Of Engagement Activity 2019
 
Description Shaping the Development of the UKCEH UK-SCAPE Data Science Framework Workshop 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Other audiences
Results and Impact UKCEH held an event to share progress on the development of the Data Science Framework (DSF) to explore community expectations for the DSF and gain feedback on whether the DSF will meet their needs. Part of this feedback is on the application and development of DataLabs for use in the DSF.
Year(s) Of Engagement Activity 2019
 
Description Summer school visit by pupils from Lytham St Annes 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Schools
Results and Impact A summer school visit by school pupils from Lytham St Annes. We focused on activities related to climate change, data science, and programming.
Year(s) Of Engagement Activity 2019
 
Description Talk at Gordon's School, Surrey 
Form Of Engagement Activity A talk or presentation
Part Of Official Scheme? No
Geographic Reach Local
Primary Audience Schools
Results and Impact Talk on atmospheric chemistry and climate change given to Gordon's School, Wokingham, Surrey. This was as part of a series to introduce students to different careers and what they involve. The talk was followed by a reception where there was an excellent discussion with pupils, their parents/carers and teachers, particularly how the students might pursue careers in research. The school reported that the "talk .... was fantastic and exactly what we should be doing," and that it was "the best nod to academic scholarship that [we are] yet to see."
Year(s) Of Engagement Activity 2019
 
Description Workshop (Environmental Data Science) 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Other audiences
Results and Impact Workshop at Alan Turing Institute on exploring collaborative opportunities between the computer and environmental sciences, which sparked discussions and ideas around new collaborations and innovations in environmental data science
Year(s) Of Engagement Activity 2019
 
Description Workshop at DEFRA 
Form Of Engagement Activity Participation in an activity, workshop or similar
Part Of Official Scheme? No
Geographic Reach National
Primary Audience Policymakers/politicians
Results and Impact Department for Environment, Food and Rural Affairs group Science and Analysis Conference entitled "Science and Analysis for a Changing Future". Provided input into policy, and built connections for further collaboration.
Year(s) Of Engagement Activity 2018