Restored Saltmarsh Trajectories (Restored SMART): Machine Learning Evaluation of In Situ Saltmarsh Restoration Methods University of Reading in United Kingdom

The Restored Saltmarsh Trajectories (Restored SMART) PhD project at the University of Reading offers an exciting opportunity to advance research in saltmarsh restoration using cutting-edge machine learning and remote sensing techniques. Saltmarshes are vital coastal habitats that provide essential ecosystem services, including carbon storage and flood defence. However, nearly half of the world's saltmarshes have been lost or degraded due to human activities and climate change impacts such as land claim and sea level rise.

This project addresses the urgent need for effective restoration strategies by evaluating in situ saltmarsh restoration methods, which differ from the commonly studied managed realignment approach. In situ methods, such as brushwood fencing, coir rolls, sediment recharge, and vegetation transplanting, aim to restore saltmarshes locally and may overcome limitations like poor drainage and reduced biodiversity found in managed realignment sites.

The research will leverage machine learning and AI to analyze spatial data from satellite imagery, uncrewed aerial systems, and other remote sensing sources. By developing models to classify plant community composition, diversity, heterogeneity, and spatial structure, the project will provide new insights into the ecological trajectory and recovery of restored saltmarshes. The study will utilize pre-existing datasets, including biodiversity measurements collected by the supervision team, and assess temporal variability before and after restoration interventions.

Outcomes from this research will inform coastal managers and policymakers, enabling data-driven decisions to prioritize restoration investments and maximize ecological impact. The project includes collaboration with partners such as Natural Resources Wales and offers a placement opportunity of 3-18 months with an AI-INTERVENE project partner. Students will receive comprehensive training in applied AI, biodiversity, and transferable research skills, and will present their findings at national and international conferences.

Applicants should have a degree in Ecology, Geography, Environmental Science, or a related field. Those with backgrounds in mathematics or computer science are also encouraged to apply. UKRI funding is available for Home students, with international applicants required to cover the difference in fees. The application deadline is January 19, 2026.

For more information and to apply, visit the project page on FindAPhD or contact the University of Reading's AI-INTERVENE department.