Deep learning for automated building damage assessment

​​Although humans cannot prevent natural disasters in most cases, timely responses can play a critical role in disaster relief and lifesaving. Rapid and accurate building damage assessment is required in humanitarian assistance and disaster response to carry out life-saving efforts. Automatic information extraction from high-resolution satellite sensor images collected from disaster-affected areas is imperative under time-critical situations and has the potential to greatly facilitate post-disaster assessment, but this remains an extremely challenging task for the state-of-the-art machine learning algorithms. 

​​This PhD project will explore in-depth the power of cutting-edge deep learning techniques in image understanding, segmentation, classification and change detection, and develop an accurate, reliable, automated solution to facilitate the challenging building damage assessment task based on paired pre- and post-disaster high-resolution satellite sensor images.  

​This project is part of an EPSRC-funded New Investigator Award expected to advance the state-of-the-art machine learning and remote sensing research with a focus on explainable artificial intelligence and computer vision. This project is in collaboration with research partners at the Lancaster University, University of Bristol, and University of Sheffield.

Open to both UK and international candidates.

Up to 30% of our UKRI-funded studentships can be awarded to candidates paying international rate fees. Find out more about eligibility.

You will need to meet the minimum entry requirements for our Computer Science PhD programme.

The candidate should be highly motivated and can engage in collaboration with good oral and written communication skills. Previous experience in machine learning, deep learning, computer vision and/or remote sensing are desirable but not essential as training will be provided.