Hidden Signals Beneath Our Feet: AI and Soil eDNA for Predicting Ecosystem Health and Drought Resilience - PhD via FindAPhD

Loughborough University

Loughborough, UK 🇬🇧

About the Project

Can multimodal and agentic AI reveal hidden signals in soil biodiversity and help predict ecosystem resilience to drought?

Led by Computer Science at Loughborough University, in partnership with Defra’s DNA Centre of Excellence, this PhD will develop AI methods to identify indicators of soil ecosystem health and predict responses to drought. Soil microorganisms support nutrient cycling, carbon storage and water regulation, making their resilience vital for environmental sustainability.

You will develop a unified AI framework integrating soil eDNA data from Defra’s Natural Capital and Ecosystem Assessment programme and Forest Research with soil measurements, climate, hydrological and spatial records. Multimodal learning will combine these data with ecological knowledge extracted from scientific literature and environmental reports to guide predictions of soil health and ecosystem responses to drought. AI agents will support evidence retrieval, analytical workflows and identification of knowledge gaps, recommending additional data or expert review where uncertainty is high. The framework will track uncertainty from data integration to prediction and address explainability and transferability across habitats and drought scenarios.

Outputs will support biodiversity monitoring, conservation, climate adaptation and sustainable land management. Training will cover multimodal learning, AI agents, uncertainty quantification, data engineering and GPU/HPC computing, complemented by eDNA methods, ecological interpretation and fieldwork opportunities. A Defra placement will provide experience translating AI research into environmental policy and practice.

94% of Loughborough’s research impact is rated world-leading or internationally excellent. REF 2021

Supervisors

Entry requirements

Applicants will normally need to hold, or expect to gain, at least a BSc 2:1 degree (or equivalent) or an appropriate Master’s degree in Computer Science or Engineering with good programming skills.

Applicants with strong programming skills and an interest in developing AI for environmental challenges are encouraged to apply.

English language requirements

Applicants must meet the minimum English language requirements. Further details are available on the International website.

Fees and funding

The studentship is offered on a competitive basis. The successful candidate will be funded for 3.5 years starting from October 2027. The studentship provides a tax-free stipend of £21,805 per annum for the duration of the studentship plus tuition fees at the UK rate and a Research Training Support Grant of £8,000. Further guidance about eligibility is available at UKRI Terms and Conditions.

Excellent international students (including EU) are eligible to apply and there will be a fee waiver in place covering the difference between Home and International fees for one successful candidate.

How to apply

  1. Complete a CENTA studentship application for 2027 intake form in Word format (available from the ‘Our project-based studentships’ section.
  2. All applications should be made online. Under programme name, select “Department of Computer Science, School of Science”. During the online application process, upload the CENTA studentship application form as a supporting document. Please quote “2027-LU05” when completing your online application.
  3. Application closing date is 23.59 (UK time) on Wednesday January 6 2027. Interviews for short-listed candidates are expected to be held sometime in the period Monday 1 – Friday 12 February 2027.

45 days remaining

Apply by 7 January, 2027

POSITION TYPE

ORGANIZATION TYPE

EXPERIENCE-LEVEL

DEGREE REQUIRED

Register for World Toilet Summit 2026 - Thailand - November 17-19, 2026