PhD Studentship – Machine Learning for mapping historic Hedgerow loss Ref: 4756

at University of Exeter
Published April 1, 2023
Location Exeter, United Kingdom
Category Machine Learning  
Job Type Scholarship  



Professor Leif Isaksen Digital Humanities Lab, University of Exeter

Dr Zeyu Fu, University of Exeter

Tom Dommett, National Trust

Hedgerow loss has been particularly marked since 1945.  Even between 1984-1993 it is believed as much as 160,000km of hedgerow was lost. Hedgerows play a critical role in supporting a range of plant, animal and insect species, including pollinators.

They provide vital habitat connectivity and can help to prevent soil erosion.  And they can also make a considerable contribution to carbon sequestration and storage through their biomass and the soils beneath them.  As a result, the creation of hedgerows is recognised as an important component of plans to address the twin crises of climate change and the decline in nature, alongside sustainable food production.

Hedgerows are also heritage assets in their own right, telling stories of land ownership, division and management, social and political change, and linking to intangible heritage of craft skills, folklore and traditional ecological knowledge.  They play an important role in defining the character of the landscape, and historically there were many different regionally distinctive hedging traditions and styles.  As a result it is typically more beneficial to replace a lost hedgerow – both for landscape character and for the avoidance of archaeological remains.

Historic Ordnance Survey (OS) mapping is typically used as a source to identify former hedgerows.  These may be identified as extant hedgerows, or as remnant fragmented hedgerows, isolated boundary trees, or linear arrangements of in-field trees.  Linear earthwork banks (upon which hedgerows were typically planted) which may be apparent in remote sensing data such as lidar, can also be used to locate former hedgerows. While historic OS mapping and lidar data can play a critical role, therefore, in helping us to understand hedgerow loss – and thereby supporting opportunities for hedgerow re-establishment – it has not been possible to analyse these vast pools of imagery at a national scale – though Historic Landscape Characterisation (HLC) and similar exercises at county level have, in some cases, recorded historic boundary loss or even distinctive hedgerow types.

The Countryside Survey of 1978 provides the first firm data on hedgerow extent and distribution for the UK.  This provides our current ‘baseline’ – but it is likely that this represents just a fraction of hedgerows present at the beginning of the 20th century.  Just how hedgey was the British countryside?  How hedgey could it be again?

Proposed research
Building on the principal of research previously commissioned by the National Trust to use machine learning to map historic orchards, is it possible to establish the historic extent of hedgerows in the UK in the early 20th century by applying machine learning approaches to historic mapping? How might these approaches be augmented by applying machine learning to other datasets (such as lidar), or combining the results with existing spatial data (such as biological survey records or HLC)? How can this greater understanding of hedgerow loss since the start of the 20th century inform our approaches to hedgerow restoration?

The proposed research will examine two ‘epochs’ of OS mapping, including from the late 19th or early 20th century, and from the mid-20th century, helping us to piece together hedgerow loss over time, until the first Countryside Survey data from 1978, and modern mapping of hedgerows.  These ‘timeslices’ of hedgerow mapping will help the National Trust to consider how hedgerow survival varied over time, as well as how it may have varied across different regions and countries.  What can hedgerow survival at different time periods and in different places tell us about habitat connectivity and biodiversity in the past?

The proposed Research will run alongside the National Trust’s annual ‘Blossom’ campaign, providing a huge potential audience for dissemination and engagement as the project progresses. This will also support opportunities to embed citizen science approaches alongside the use of machine learning, working with the crowd to verify and enrich results, including for instance in estimating hedgerow age through ‘Hoopers Rule’.

About the UKRI Centre for Doctoral Training in Environmental Intelligence

Our changing environment presents a series of inter-related challenges that will affect everyone’s future health, safety and prosperity. Environmental Intelligence (EI) is the integration of environmental and sustainability research with data science, artificial intelligence and cutting-edge digital technologies to provide the meaningful insight to address these challenges and mitigate the effects of environmental change.

One of the 16 UKRI AI CDTs launched in 2019, the CDT in Environmental Intelligence provides an interdisciplinary training programme for students covering the range of skills required to become a leader in EI:
• the computational skills required to analyse data from a wide variety of sources;
• expertise in environmental challenges;
• an understanding of the governance, ethics and the potential societal impacts of collecting, mining, sharing and interpreting data, together with the ability to communicate and engage with a diverse range of stakeholders.

The CDT cohort works and learns together, bringing knowledge, skills, and interests from a range of academic disciplines relevant to EI.  CDT students undertake training and professional development as a cohort, and regularly participate in seminars, symposia, and partner engagement activities including the annual CDT Environmental Intelligence Grand Challenge.  As part of the research community at the University of Exeter, CDT students benefit from networking with colleagues in the Institute for Data Science and Artificial Intelligence; the Global Systems Institute; and the Environment and Sustainability Institute.

Entry requirements

This award provides annual funding to cover Home tuition fees and a tax-free stipend.  For students who pay Home tuition fees the award will cover the tuition fees in full, plus at least £17,668 per year tax-free stipend.  Students who pay international tuition fees are eligible to apply, but should note that the award will not provide the international element of the tuition fees (approx £15,000 per annum).

International applicants need to be aware that you will have to cover the cost of your student visa, healthcare surcharge and other costs of moving to the UK to do a PhD.
The conditions for eligibility of home fees status are complex and you will need to seek advice if you have moved to or from the UK (or Republic of Ireland) within the past 3 years or have applied for settled status under the EU Settlement Scheme.

Entry requirements:

Applicants for this studentship must have
• obtained prior to the start of the PhD, a First or Upper Second Class UK Honours degree, or the equivalent qualifications gained outside the UK, in an appropriate area of science or technology, i.e. environmental, geographical, mathematical, or computer science study programme.
• a keen interest in environmental research
• some understanding of machine vision principles and/or spatial technologies
• sound numerical and computational experience
• If English is not your first language you will need to meet the required level (Profile A)  as per our guidance at
• some understanding of cartographic principles
• some understanding of environmental heritage
• some experience in coding languages (e.g. Python, Fortran, etc.)

How to apply

How to apply

In the application process you will be asked to upload several documents .
• CV
• Letter of application (outlining your academic interests and expertise, prior research experience and reasons for wishing to undertake the project).
• Transcript(s) giving full details of subjects studied and grades/marks obtained (this should be an interim transcript if you are still studying)
• Names of two referees familiar with your academic work. You are not required to obtain references yourself. We will request references directly from your referees if you are shortlisted.
• If you are not a national of a majority English-speaking country you will need to submit evidence of your proficiency in English.

Application deadline: 31 April 2023

Value: Home fees plus annual tax-free stipend of at least £17,668 in year 1. £10,000 (approx.) project budget for research and training.

Duration of award: 4 years