PhD Position in Computer Vision Applied to Natural Hazards

Improving our understanding of the mechanisms that govern debris flow motion is a core research topic in the Chair of Engineering Geology at ETHZ. As part of this, the group collects and analyses an unprecedented set of field datasets. The collected data includes timelapse point clouds, video imagery, as well as auxiliary data including environmental parameter timeseries. This data is then processed to derive high temporal and spatial resolution estimates of displacement, velocity, strain and surface change, as well as the driving mechanisms. A large foundational dataset has already been collected, and presents a unique opportunity for making new insights into debris-flow processes. You will develop advanced algorithms to process this data, with a focus on optical flow and object detection. You will interpret the results to better understand debris flow mechanisms. You will also contribute to the maintenance and upkeep of the monitoring systems. Additionally, you will be given significant support to develop your own research ideas and apply for third party funding. Contributions to teaching within the Engineering Geology group are also expected.

The Engineering Geology group at ETH Zurich (Prof. Jordan Aaron) is seeking a motivated and creative doctoral student who specializes in computer vision. We are an enthusiastic and collaborative research group with many opportunities for multi-disciplinary cutting edge research in engineering geology. ETH Zurich is one of the world’s leading universities specialising in science and technology. We are renowned for our excellent education, cutting-edge fundamental research and direct transfer of new knowledge into society. Over 30,000 people from more than 120 countries find our university to be a place that promotes independent thinking and an environment that inspires excellence.

• Masters degree in Computer Vision, Data Science, Computer Science, Mechatronics, Remote Sensing, Engineering Geology or other related discipline

• Demonstrated expertise and interest in machine learning and computer vision algorithms is necessary, with an emphasis on object tracking, optical flow and sensor fusion

• Knowledge of rock mechanics, soil mechanics and/or landslide processes is considered beneficial

• Prior experience with point cloud processing is an asset

• Ability to work independently

• Strong written and oral communication skills in English