Machine Learning & Software Development for Sustainable Chemistry
Publication Date
December 31, 2025
Creator
Abstract
Sustainability represents one of the most pressing challenges for chemical synthesis in the 21st century. Traditional methods often rely on non-sustainable practices, including the use of chemicals that are harmful to human health and the environment. Significant efforts have been made to improve the sustainability of chemical synthesis and finding greener synthetic routes is a common aim for researchers.
Digitalisation presents an opportunity to embed intelligent tools into the workflows of chemists. Many academic researchers continue to use paper lab notebooks, highlighting the need for accessible electronic laboratory notebooks (ELNs) tailored to their needs. Machine learning can be used to create predictive models from high-quality data, offering a powerful approach to enhancing these tools.
In this thesis, software tools for sustainable chemistry are explored, and machine learning theory and its application to chemistry is introduced and exemplified. The development of the AI4Green ELN and the integration of machine learning models with an accompanying sustainability assessment is described. Integrating software and machine learning tools for sustainable chemistry directly into the ELN can help chemists measure and improve their sustainability without requiring duplicated data entry. The ELN captures reaction data in a structured, machine-readable format, facilitating the development of additional tools and modernising research data management.
Item Type
ethesis
Thesis Type
PhD
Supervisors
Subjects (LC)
Associated Schools / Departments
School of Chemistry
eprints ID
81528
UoN Repository URI
Except where otherwise noted, this item's license is described as
File(s)![Thumbnail Image]()
Name
Machine Learning & Software Development for Sustainable Chemistry.pdf
Type
Full-text
Description
Examined
Size
3.65 MB
Format
Adobe PDF
Checksum (MD5)
1630a571a13537e137d9226ce50536aa