Universiteit Leiden

nl en

Vacancy

Research scientific programmer, Automated machine learning for spatio-temporal Earth Observation datasets

Vacancy number
22-041
Function type
Non-academic staff
External/ internal
External
Location
Leiden
Placed on
25 January 2022
Closing date
28 February 2022 Vacancy closed

The Faculty of Science and Leiden Institute for Advanced Computer Science is looking for a: 
Research scientific programmer, Automated machine learning for spatio-temporal Earth Observation datasets
Vacancy number 22-041
 

Key responsibilities:
We are looking for an excellent candidate with a master’s degree in Artificial Intelligence, Computer Science or a closely related field to join a number of projects focused on improving the state of spatio-temporal machine learning for Earth Observation (EO) data. The successful candidate will perform research and publish results in scientific journals and conference proceedings, as well as, developing algorithms and construct benchmark datasets and software packages to share the result of research with other researchers or practitioners. There are plenty of training opportunities for the candidate to grow and develop professionally.
•    Automated machine learning and automated configuration of high-performance models for spatio-temporal EO datasets;
•    automated fusion of EO data acquired from multiple sources;
•    representation and transfer learning for EO datasets;
•    hybrid and physics-aware machine learning for EO data; 
•    automated counterfactual prediction and causal inference based on EO data;
•    automatic configuration of hybrid models for Earth Observation data;
•    creating large-scale benchmarks to support reproducible research on spatio-temporal machine learning from EO data.

Embedding:
This position is funded by a combination of research projects, including NWO-ENW Klein 1 Grant titled “Physics-aware Spatio-temporal Machine Learning for Earth Observation Data” by the Netherlands Organisation for Scientific Research, and is supported by European Space Agency (ESA), SRON Netherlands Institute for Space Research and the TAILOR European Network of Centres of Excellence in AI. Research is performed at the ADA group at the Leiden Institute for Advanced Computer Science (LIACS), where we pursue the development of AI (artificial intelligence) techniques that complements human intelligence. Our group is particularly well-known for its work on programming by optimisation (PbO) and automated machine learning (AutoML).  The work will be done in close collaboration with -and in part at-  SRON Netherlands Institute for Space Research who are experts in atmospheric satellite remote sensing and the co-Principal Investigator institute of the TROPOMI satellite instrument. Furthermore, there will be in collaboration with the European Space Agency (ESA), the main organisation in charge of the collection of EO data in Europe.

Goal:

During the past few years, the vision of creating the digital twin of Earth has been put forward to allow better decision support for addressing grand environmental challenges, such as global warming or nature conservation. Such a digital twin could be realised through designing models that fully capture the complex nature of interacting environmental processes on Earth. Using these models, we would be able to forecast and simulate the future state of the Earth before and after taking interventions. Developing machine learning models for such datasets will be a major step towards achieving this goal. Defining machine learning pipelines for such data is, however, an extremely challenging task. There are numerous decisions that need to be taken to create strong models (e.g., super-resolving low resolution images, fusing data from different satellites, dealing with issues such as noise, missing data and inconsistent sampling). Furthermore, there are limited amounts of labelled data for training models using standard supervised learning approaches. At the same time, the models developed next to producing accurate predictions need to be assessed based on their trustworthiness and support decision making. Our goal is to build upon recent advances in the area of automated machine learning to develop algorithmic solutions to automatically address these challenges in a data-driven manner.   The area of application will be in atmospheric science focusing on the use and exploitation of TROPOMI Sentinel-5P data for climate research.
 

Selection Criteria 
•    MSc in Artificial Intelligence, Computer Science, Data Science, or a closely related discipline
•    Strong programming skills
•    Experience with machine learning and data mining algorithms and tools
•    Familiarity with spatio-temporal pattern mining 
•    Familiarity with EO data and image processing is desirable
•    Knowledge of neural network frameworks (Torch, PyTorch, Tensorflow, Keras, etc.) is desirable. 
•    Strong command of the English language 
•    Willingness and proven ability to work independently, but also in the context of international collaborations

Research at our faculty
The Faculty of Science at Leiden University is a world-class faculty where staff and students work together in a dynamic international environment. It is a faculty where personal and academic development are top priorities. Our people are committed to expand fundamental knowledge by curiosity and to look beyond the borders of their own discipline; their aim is to benefit science, and to make a contribution to addressing the major societal challenges of the future. 
The research carried out at the Faculty of Science is very diverse, ranging from mathematics, information science, astronomy, physics, chemistry and bio-pharmaceutical sciences to biology and environmental sciences. The research activities are organised in eight institutes. These institutes offer eight bachelor’s and twelve master’s programs. The faculty has grown strongly in recent years and now has more than 2,300 staff and almost 5,000 students. We are located at the heart of Leiden’s Bio Science Park, one of Europe’s biggest science parks, where university and business life come together. 
For more information, see  https://www.universiteitleiden.nl/en/science and  https://workingat.leiden.edu/ 


Diversity
Leiden University is strongly committed to diversity within its community and especially welcomes applications from members of underrepresented groups.
Terms and conditions  
We offer a full-time position for initially one year. After a positive evaluation of the progress of the thesis, personal capabilities and compatibility the appointment will be extended by a further three years. Salary range from € 2,846,-  to €4,490  gross per month (pay scale 10, in accordance with the Collective Labour Agreement for Dutch Universities). 
Leiden University offers an attractive benefits package with additional holiday (8%) and end-of-year bonuses (8.3 %), training and career development and sabbatical leave. Our individual choices model gives you some freedom to assemble your own set of terms and conditions. Candidates from outside the Netherlands may be eligible for a substantial tax break. 
The candidate will be embedded in the Leiden University Graduate School of Science https://www.graduateschools.leidenuniv.nl/. Our graduate school offers several PhD training courses at three levels: professional courses, skills training and personal effectiveness. In addition, advanced courses to deepen scientific knowledge are offered by the research school.
 

Information 
Enquiries can be made to Dr. Mitra Baratchi. If you have any questions about the procedure, please contact Dr. Mitra Baratchi, m.baratchi@liacs.leidenuniv.nl 

Applications 
To apply for this vacancy, please send an email to jobs@liacs.leidenuniv.nl. Please ensure that you upload the following additional documents quoting the vacancy number:
•    Your curriculum vitae;
•    A motivation letter;
•    A link to (a draft of) your Master’s thesis, and other publications (if any);
•    The name of two references (who agreed to support the application).

Only applications received before 1-3-2022 can be considered.

This website uses cookies.  More information.