Data Science of the Natural Environment: A Research Roadmap

Gordon S Blair,Paul J Young,Peter Henrys,Emma Eastoe,Amber Leeson,Susan Jarvis,John Watkins

doi:10.3389/fenvs.2019.00121

Gordon S Blair, Paul J Young + Show 5 more

Open Access

https://doi.org/10.3389/fenvs.2019.00121

Copy DOI

Abstract

Data science is the science of extracting meaning from potentially complex data. This is a fast moving field, drawing principles and techniques from a number of different disciplinary areas including computer science, statistics and complexity science. Data science is having a profound impact on a number of areas including commerce, health and smart cities. This paper argues that data science can have an equal if not greater impact in the area of earth and environmental sciences, offering a rich tapestry of new techniques to support both a deeper understanding of the natural environment in all its complexities, as well as the development of well-founded mitigation and adaptation strategies in the face of climate change. The paper argues that data science for the natural environment brings about new challenges for data science, particularly around complexity, spatial and temporal reasoning, and managing uncertainty. The paper also describes a case study in environmental data science which offers up insights into the promise of the area. The paper concludes with a research roadmap highlighting ten top challenges of environmental data science and also an invitation to become part of an international community working collaboratively on these problems.

Highlights

Data science is emerging as a major new area of study, having significant impacts on areas as diverse as eCommerce and marketing, smart cities, logistics and transport, and health and well-being (Dhar, 2013; Provost and Fawcett, 2013)
Summary of uncertainty challenges Reifying uncertainty as a first class entity in all aspects of environmental science related to data and models; Providing a framework to support reasoning about uncertainty; Developing data science techniques to deal with epistemic uncertainties including emergent events and surprises emanating from the underlying complexity of the systems being observed or modeled; Based on uncertainty and other contextual information, seek adaptive strategies for sampling and model execution
Building on our analyses and experiences documented above, we present a research roadmap for data science for the natural environment in terms of a top 10 set of research challenges7

Summary

INTRODUCTION

Data science is emerging as a major new area of study, having significant impacts on areas as diverse as eCommerce and marketing, smart cities, logistics and transport, and health and well-being (Dhar, 2013; Provost and Fawcett, 2013). The paper draws on experience from a strategic partnership between the Data Science Institute (DSI) at Lancaster University and the Centre of Ecology and Hydrology (CEH) to create a world-leading Centre of Excellence in Environmental Data Science (CEEDS). We argue that the potential for environmental data science is enormous and understanding, and managing the impact of, environmental change is a grand challenge for the emerging subject of data science. Before developing this argument further, we look more closely at the nature of the environmental sciences

A Focus on the Natural Environment

A Data Science of the Natural Environment?

A RESEARCH ROADMAP

CONCLUDING REMARKS