Coventry University Featured PhD Programmes
University of Oxford Featured PhD Programmes
University of Bristol Featured PhD Programmes
University of Southampton Featured PhD Programmes
University of East Anglia Featured PhD Programmes

QUADRAT DTP: Automated soil profiling: identification of soil characteristics using Machine Learning and image analysis

Project Description

Soil properties, such as porosity, bulk density, soil water contact are subjected to change due to complex interacting process, including physical, chemical and biological process. A comprehensive characterization and prediction of soil properties could bring substantial benefits to agriculture security. Soil profiles contain a wealth of information about the character and properties of the soil. Interpretation of a soil profile requires the recognition and identification of many different characteristics, each of which contribute to the overall assessment of the soil’s ability to provide ecosystem services and its response to specific drivers. The expertise required to recognise soil characteristics and integrate them requires expertise and time. The use of Artificial Intelligence (AI) to interpret soil profile characteristics from profile imagery has been successful in estimating specific properties such as carbon content. The proposed work will develop a tool through the use of machine learning techniques least absolute shrinkage and selection operator (LASSO), to identify and predict properties of soil. The project will focus on (1) the recognition of specific diagnostic soil properties, (2) integration of diagnostic properties into an overall soil profile assessment, and (3) estimation of soil characterisation and ecosystem service provision.

Libraries of soil profile imagery exist at national and global scale, and many are freely available. The student will develop a database of soil profile images with associated properties and features and will attribute those properties and features to specific locations within the images. Statistical techniques will be used to recognise these properties and features within the profile images and integrating them into a whole-profile assessment and characterisation. A further level of Machine Learning algorithms will be developed and trained through assimilation of these data. The trained system will be tested and demonstrated using soil profile pits in the field, using a smartphone app developed as part of the project. In addition, it will participate as an entrant in soil judging contests as an additional way of promoting the work and demonstrating its effectiveness.


Training in the use of R for statistics and artificial intelligence at the James Hutton Institute and Aberdeen University. Training in field work practices and health and safety in the workplace at the Hutton Institute. Collaboration will take place with staff at James Hutton Institute who work on soil profile assessment and soil databasing and app development. This will enable the student to access additional materials for project development and will provide test cases for the software system. Dissemination to land managers and soil scientists globally will be achieved through the release of the tool as an app that will be free to download. The app will be integrated into engagement activities at various stakeholder events such as Open Farm Sunday and will be demonstrated at the International Soil Judging Contest and World Soil Congress in Glasgow in 2022.


Candidates should have (or expect to achieve) a minimum of a 2.1 Honours degree in a relevant subject. Applicants with a minimum of a 2.2 Honours degree may be considered providing they have a Distinction at Master’s level.


• Apply for Degree of Doctor of Philosophy in Geosciences
• State name of the lead supervisor as ‘Name of Proposed Supervisor’ on application
• State ‘QUADRAT DTP’ as Intended Source of Funding
• Select the to apply now

Funding Notes

This project is funded by the NERC QUADRAT-DTP and is available to UK/EU nationals who meet the UKRI eligibility criteria. Please visit View Website for more information.

The studentship provides funding for tuition fees, stipend and a research training and support grant subject to eligibility.

Email Now

Insert previous message below for editing? 
You haven’t included a message. Providing a specific message means universities will take your enquiry more seriously and helps them provide the information you need.
Why not add a message here
* required field
Send a copy to me for my own records.

Your enquiry has been emailed successfully

FindAPhD. Copyright 2005-2019
All rights reserved.