Milto Miltiadou

University of Exeter is advertising a fully funded PhD in Computer Science / Machine Learning with Earth Observation for forest-related applications . The project sits in the Department of Computer Science, Faculty of Environment, Science and Economy, and is linked to DASOS’ Vision Group and the Centre for Environmental Intelligence . The research focuses on advancing algorithms for large-scale Earth Observation and LiDAR data to improve forest monitoring. The project highlights methodological work in machine learning , including feature engineering, representation learning, classification, regression, anomaly detection, change analysis, and uncertainty quantification. It also mentions the use of multi-sensor datasets such as Sentinel-1, Sentinel-2, GEDI lidar, BIOMASS, and NISAR, with interest in foundation models and temporal modelling. Applicants must choose one application area and write a 300-word proposal on how innovative algorithms can address it. The listed themes are: characterising forest variation near pre-Columbian earthworks in the Amazon, predicting mixed-forest composition and intra-variability in Europe, or quantifying forest plantation damage and supporting recovery after cyclones or tropical storms in New Zealand. Eligibility: applicants should have, or be about to obtain, a First or Upper Second Class UK Honours degree or equivalent in Computer Science, Data Analysis, or Mathematics. Candidates from Geography, Remote Sensing, or Forest Ecology may also be considered if they show strong computing skills. English language proficiency is required where applicable. Funding: the studentship covers Home or International tuition fees and provides an annual tax-free stipend of at least £21,805 for 3.5 years. The post notes that international students must cover visa, healthcare surcharge, and relocation costs. Deadline: 17 August 2026. Interviews are expected in the weeks commencing 24 or 31 August 2026. Applicants should apply via the University of Exeter portal, upload the required documents, and quote reference 5898 .