Methodologically Enhanced Virtual Labs for Early Warning of Significant or Catastrophic Change in Ecosystems: Changepoints for a Changing Planet

Virtual labs are emerging as a key component in the construction of future digital environments, particularly to abstract over the complexities of the underlying distributed networks of sensors and associated computational infrastructure. We define a virtual lab as a transdisciplinary collaboration space hosted in the cloud (public/private/hybrid) that allows stakeholders to access a range of data, analytical methods and assessment tools (e.g. visualisation tools and/or statistical tools), and to execute these analyses using the elastic capacity of a cloud. In the environmental science community, most existing virtual labs focus on the problem of integrating often complex and heterogeneous data. We seek to significantly advance the state-of-the-art by enhancing virtual labs with sophisticated methodological capability, embracing state-of-the-art data science techniques to assist in the societally-relevant interpretation of these data.

This is a bold and broad vision and, to make this feasible in a year, we elect to work with a particular family of data science techniques, that is, changepoint detection methods, designed to identify fundamental changes and anomalous behaviour in data, typically within time-series, but also applicable across space and time and to complex, multivariate problems.

This feasibility study will therefore bring together a cross-disciplinary team working on virtual labs, changepoint methods and evidence for impacts of global environmental change on ecosystem structure and function. Our approach will foster a deep, cross-disciplinary dialogue through workshops, enhanced by rapid prototyping of virtual labs to stimulate thinking about what is possible/desirable w.r.t. ecosystem early warning methods.

The project will build on the rich, complex, multi-faceted data available from the Environmental Change Network (ECN), that offers detailed multivariate 25-year long data sets for a range of ecosystems in the UK. We seek to understand the role of data science, including, but not limited to changepoint detection, in the construction of environmental early warning alert systems capable of operating at a variety of scales, from catchments to global planetary level systems.

The proposed research is well balanced between cutting edge research and impact on stakeholders and the greater environmental community. Impact is very important to us, and in this document we present a multi-faceted Pathways to Impact strategy intended to deliver the following impact goals:

1. To influence future generations of virtual labs nationally and internationally in terms of embracing data science methodologies;
2. To place virtual labs and data science methodologies at the heart of future digital environment research and practice;
3. To demonstrate and evaluate the role of changepoints (in isolation or in combination with other data science techniques) in supporting environmental decision makers in offering early warning indicators of significant or catastrophic change, and hence enabling early interventions in terms of mitigation or adaptation strategies;
4. To build momentum and an associate community interested in constructing environmental early warning systems operating at different scales;
5. To contribute our considerable expertise and additional insights from this project into enhancing multidisciplinary and inter-disciplinary research and innovation (MIDRI).

We plan a series of mechanisms to ensure that we engage with our partners and beneficiaries throughout the project, with this engagement being fundamentally woven into the research methodology.

Firstly, we plan two workshops to be held in month 2 and month 12 respectively. The first workshop is internal, involving the investigators and associated research staff from Lancaster University and CEH, together with representatives of our partners. The second workshop is external and will involve all the constituents from the first workshop together with invitees from our identified beneficiaries including the Digital Environment community.

An agile methodology will be adopted in the project with virtual lab development being broken into a series of 2-month sprints with show and tell sessions organised at the end of each sprint. This approach is known to be highly effective in maximising partner engagement and ensuring that the final solutions are tailored careful to the needs of beneficiaries.

Our Centre of Excellence in Environmental Data Science (CEEDS) is an important vehicle to disseminate the results both externally, e.g. through our planned annual conference, and internally as we work closely with a range of environmental scientists in CEH and the Lancaster Environment Centre.

We believe that having a strong Digital Environment community is important and look forward to working with the champions and greater community through community meetings/events, and also offer to host a community meeting. There is also an important people dimension as well, as we train researchers to have the cross-disciplinary skills to contribute to Digital Environments.

Finally, we will adopt an open science policy within this project and all data, software and papers available as open assets. The project will also maintain a strong website presence coupled with a social media strategy.