Postdoc in Foundation models for accommodating Earth Observation
Earth Observation (EO) data presents a unique set of exceptional opportunities and challenges for machine learning research. The vast diversity of ecosystems, petabyte-scale data volumes, continuous coverage across multiple spectral bands, and substantial seasonal and diurnal variations pose significant hurdles. Furthermore, the varying spatial and temporal resolutions create complexities that necessitate innovative solutions. We are seeking a highly motivated postdoctoral researcher to conduct research on foundation models for accommodating Earth Observation. The position is funded by a Villum Foundation grant for the Earth-INN project to Assistant Professor Ankit Kariryaa.
Potential research topics include, but are not limited to:
- Stable diffusion and invertible neural networks for satellite image to image translation
- Exploring the novel self-supervised methods on multi-source, multi-scale Earth Observation data
- Developing computationally efficient algorithms that large scale Earth Observation
The successful candidate will be based at the Department of Geosciences and Natural Resource Management at the University of Copenhagen and will work primarily with Ankit Kariryaa. Their main duty will be to conduct novel research in the aforementioned areas, collaborate with other members in the research group, and publish findings in leading venues such as CVPR, ICCV, ECCV, NeurIPS,ICML, Science, Nature, and Nature Communication among other venues. Additional responsibilities may include collaborating with other research groups internationally and domestically as well as participating in other related duties as needed.
Inquiries about the position can be made to Ankit Kariryaa, ankit@ign.ku.dk
Further information on the Department can be found at: ign.ku.dk/english/
The position is open from 1 March 2025 or as soon as possible thereafter. The length of the employment is 2 years.
The University wishes our staff to reflect the diversity of society and thus welcomes applications from all qualified candidates regardless of personal background.
Position requirements:
- (Required) PhD degree in computer science, statistics, mathematics, GIS or similar.
- (Required) Experience with some aspects of self-supervised learning, or stable diffusion.
- (Required) Good programming skills in Python.
- (Required) High level of motivation with the ability to conduct independent research by identifying key problems and driving projects to completion.
- (Required) Proven skills in writing high-quality research papers and delivering effective presentations.
- (Optional) Experience with Earth Observation data and GIS tools.
- (Optional) Familiarity with some aspects of compute efficient deep learning.
Terms of employment
The position is covered by the Memorandum on Job Structure for Academic Staff.
Terms of appointment and payment accord to the agreement between the Ministry of Finance and The Danish Confederation of Professional Associations on Academics in the State.
Negotiation for salary supplement is possible.
The application, in English, must be submitted electronically by clicking APPLY NOW below.
Please include
- Curriculum vitae
- Diplomas (Master and PhD degree or equivalent)
- Research plan – description of current and future research plans
- Complete publication list
- Separate reprints of 3 particularly relevant papers
The deadline for applications is 11 December 2024, 23:59 GMT +1.
After the expiry of the deadline for applications, the authorized recruitment manager selects applicants for assessment on the advice of the Interview Committee.
You can read about the recruitment process at employment.ku.dk/faculty/recruitment-process/
Interviews are expected to be held late January 2025, via zoom.
Københavns Universitet giver sine knap 10.000 medarbejdere muligheder for at udnytte deres talent fuldt ud i et ambitiøst, uformelt miljø. Vi sikrer traditionsrige og moderne rammer om uddannelser og fri forskning på højt internationalt niveau. Vi søger svar og løsninger på fælles problemer og gør ny viden tilgængelig og nyttig for andre.