Quantifying Landslide Impacts across Europe using AI

This PhD asks: To what extent are landslide impacts represented in current European disaster-loss assessments, and how does this influence our understanding of multi-hazard risk?

The student will develop scalable artificial intelligence and Earth Observation methods for multi-temporal landslide detection and mapping across Europe. Using open data, including Sentinel-1 and Sentinel-2 satellite observations, the research will test how reliably models transfer across contrasting geomorphological and environmental settings. The student will quantify uncertainty, completeness and detection bias; reconstruct the approximate timing and extent of landslide occurrence; and develop validation strategies suitable for continental-scale application. The resulting harmonised inventory will be integrated with exposure, vulnerability and disaster-loss information to estimate impacts on infrastructure, populations and economic assets.

The project will also examine how landslide impacts are represented when they form part of compound or cascading rainfall-flood-landslide events, including how uncertainty in the landslide inventory propagates into impact estimates. Its outputs will strengthen the evidence base for assessing the contribution of landslides to European disaster impacts and multi-hazard risk.

The student will be based at King’s College London and work within an interdisciplinary research environment spanning artificial intelligence, Earth Observation, geospatial data science, landslide and multi-hazard science, and impact modelling.

This is a CASE studentship undertaken in partnership with the British Geological Survey (BGS). During a placement of at least three months at BGS, the student will work with specialists in landslide inventories, validation, Earth Observation and operational geological-survey practice. BGS has extensive experience in rapid geohazard assessment, scientific advice and satellite-supported disaster response, including more than a decade of support for the International Charter “Space and Major Disasters.” The student will explore how the methods and landslide-information products developed through the PhD could support inventory creation, rapid assessment and disaster-response organisations.

Supervisors:

• Faith Taylor
• Lorenzo Nava
• Alessandro Novellino
• Ekbal Hussain

Funding Notes:

Fully funded place including home (UK) tuition fees and a tax-free stipend at UKRI rates. Additional funding to cover full overseas fees is available for a maximum of 6 studentships.

Enquiries email name and address:

TREES.Admissions@ucl.ac.uk

Application Web Page:

https://www.trees-dla.ac.uk/apply