The application of machine learning to understand the dynamics of soil structure - Doctor of Philosophy thesis abstract

Aug 2, 2026

Machine learning and artificial intelligence are transforming industries and everyday life, enabling more efficient analysis of complex scientific data. Soil structure is vital for soil health but is dynamic, difficult to measure, and crucial for agricultural studies and improvement. X-ray computed tomography offers non-destructive imaging, producing large datasets that are often underused. This research evaluates machine-learning methods to extract pore-network and seasonal trends, improving prediction of soil type, water content, and tillage treatment.

LanguageEnglish

CategoryResearch & Report

FormatPDF

Pages162

Reading Time6 h 48 min

AccessFree to download

Abstract

Keywords

Acknowledgements

Abbreviations and acronyms

List of Tables

List of Figures

1. Introduction

1.1 General Introduction

1.2 Research Justification

1.3 Methodological Approach

1.4 Aims and Objectives

1.5 Thesis Outline

2. Developments in machine learning in soil science and its applications alongside X-ray Computed Tomography

The application of machine learning to understand the dynamics of soil structure By Caroline Roy, BSc. (Hons) Thesis submitted to the University of Nottingham for the degree of Doctor of Philosophy Abstract Machine learning and artificial intelligence are quickly changing the world. Just a few years ago, these concepts usually provoked visions of theoretical fiction. However, now they are becoming commonplace across a vast array of industries and even in our daily lives. Soil structure is a very important factor in soil health and has strong applications in agricultural studies and improvement. It is also a dynamic, complex, and very hard-to-measure component. Scientific advancements which improve the accessibility of soil structure quantifications are of great importance and benefit to the soil science community. X-ray Computed Tomography (X-ray CT) is a non-destructive and noninvasive technique for observing and analysing soil structure. It has been used in soil science for several years for various tasks, leading to a large volume of data to be analysed. A lot of this data is often discounted, due to the extreme volumes produced. Machine learning allows for high-throughput data processing, unrestricted by human processing and labour limitations. Data processing and analysis via machine learning algorithms might also notice new trends or patterns in the data that would not be noticed with human analysis. This means that machine learning algorithms could be the perfect solution to take a deeper dive into the data collected from X-ray CT, get more information out of the data, and potentially find new patterns. Soil structure can vary greatly due to the soil composition, weather conditions (temperature, rain, or lack thereof), crops, compaction, tillage management and the biodiversity in the soil. In recent years there has been a lot of interest in zero tillage, as part ofa series of measures usually deployed under the banner of conservation or regenerative agriculture and how it may be beneficial over conventional tillage. This research looks at how the tillage practices impact the soil structure and in particular the pore network, and how these properties may vary over a growing season. Different machine learning techniques are looked at and applied to demonstrate how machine learning can be used alongside X-ray CT images and soil data to improve processes and observe new information. Ultimately, the large volume of data produced by X-ray CT make excellent training datasets for machine learning algorithms. The neural networks demonstrated were mostly successful at identifying and predicting soil type, water content and tillage treatment based on soil structure. Shortcomings could be overcome by increasing the volume and variation of training data, as well as making use of more advanced machine learning techniques such as multi-resolution networks. Keywords Tillage, Zero Tillage, X-ray Computed Tomography, Soil Structure, Pore Network, Machine Learning Acknowledgements I would like to express my deepest appreciation to Prof. Sacha Mooney and Prof. Tony Pridmore for their invaluable and constant patience, feedback, and support. Sacha for all your guidance and support throughout extension requests and the help you provided during the difficult times I faced completing this thesis. I’m extremely grateful to Dr. Mohammadreza Soltaninejad, without you I reckon I’d still be having issues with my code. Additionally, this project would not have been possible without the generous support from BBSRC, who financed my research. Special thanks to Dr. Atkinson, for all the support with the X-ray CT equipment and specialist software, as well as some great mental health walks around campus. Prof. Andrew French was incredible with helping me through final corrections and making me feel like my work mattered. Thanks also to Dr Cooper, for being a friendly face when I first started, and always being happy to hel

FAQs

Why is soil structure important and difficult to measure?

Soil structure strongly influences soil health and is central to agricultural research. It is dynamic, complex, and hard to quantify, making accessible measurements essential.

How does X-ray computed tomography support soil-structure studies?

X-ray computed tomography provides non-destructive, non-invasive observations of soil structure and generates large volumes of image data for analysis.

What machine learning outcomes are reported in the study?

Neural networks are largely successful at identifying and predicting soil type, water content, and tillage treatment from soil-structure information, with improvements suggested through larger and more varied training datasets and more advanced architectures.

Aug 2, 2026

Upload by Theodora