KU Leuven

We are hiring a postdoc to join the Earthmapps team at KU Leuven in the ClimaVision project.

The EarthMapps research group is dedicated to assessing land-atmosphere interactions on a landscape scale through the utilization of multi-source satellite imagery and models. Our primary goal is to develop and implement innovative methodologies, including machine learning, to comprehensively evaluate the impact of climate change on ecosystem dynamics, the cryosphere, the hydrological cycle, sea level rise, and other key Earth processes. To bridge the gap between cutting-edge data and technology and their meaningful scientific applications, our team focuses on big data solutions and machine learning approaches. In this pursuit, we actively participate in the development of methodologies aimed at facilitating the generation of digital twins of the Earth. Our technological endeavors converge at the interface of multi-source satellite imagery, diverse models (e.g., climate, vegetation, ice sheets), and machine learning. Within this integrated framework, our aim is not only to assess Earth's surface properties but also to comprehend their intricate spatio-temporal response to climate variations. By continuously developing and seamlessly integrating innovative methodologies, we strive to contribute significantly to the broader understanding of the Earth's complex systems and their responses to the challenges posed by a changing climate.

Homepage: https://earthmapps.io/

Are you passionate about applying AI to tackle climate challenges in polar regions? Do you want to work at the intersection of deep learning, remote sensing, and climate science? We invite applications for a fully funded postdoctoral position at KU Leuven, where you'll develop physically informed super-resolution models to improve climate projections over Antarctica. This project offers access to cutting-edge satellite data, high-performance computing, and collaboration with leading experts in climate modeling and machine learning. Join us in advancing climate resilience through innovative AI-driven downscaling!

The postdoc project will pioneer the use of physically informed deep learning techniques to downscale regional climate models (RCMs) over Antarctica. The goal is to improve the spatial resolution and physical consistency of key climate variables such as Surface Mass Balance (SMB) and surface melt, which are critical for understanding ice sheet stability and sea level rise. This postdoc will be central to developing and applying super-resolution methods that integrate remote sensing data and geophysical constraints (elevation, albedo, etc.) into climate downscaling frameworks.

Interested candidates should submit the following documents:

- CV (including Msc grading transcripts) and, if available, a link to the PhD thesis, published papers, publicly available code (e.g. GitHub), etc.

- Motivation Letter, including your earliest possible start date.

- References: Names and contact details of two referees (no letters required at this stage).

For more information please contact: stef.lhermitte@kuleuven.be.

You can apply for this job no later than November 04, 2025 via https://www.kuleuven.be/personeel/jobsite/jobs/60565099 and the included application button