Nature Communications perspective paper on causal discovery from time series
Together with co-authors, we recently published a Nature Communications perspective paper on causal discovery from time series. The perspective provides an overview of causal inference methods, identifies promising applications, and discusses methodological challenges (exemplified in Earth system sciences). I hope you find it useful for your work!
Causality benchmark platform www.causeme.net
In addition, we recently launched a causality benchmark platform www.causeme.net. The CauseMe platform provides ground truth benchmark datasets featuring different real challenges to assess and compare the performance of causal discovery methods. As a method developer, you can test your methods. As a method user, you can look up which causal methods are best suited for particular challenges. We need more ground truth datasets, contribute now!
Postdoc: Flexible topic related to the development of causal inference methods for time series (English ad).
The core methodological topics include graphical models, causal inference, nonlinear time series analysis, and deep learning via a close collaboration with the machine learning group at FSU Jena. But the methods are flexible and open for your ideas!
To support your international research experience, all positions have a generous travel budget for conferences and extended research stays. Currently, we have collaborators at Imperial College London, Oxford, Carnegie Mellon University, National Center for Atmospheric Research (NCAR), and California Institute of Technology.
- Master/PhD in (applied) mathematics, statistics, computer science, physics, or data science.
- Creativity and strong motivation to develop new algorithms and learning paradigms for using machine learning for climate science applications.
- Practical knowledge of the current state-of-the-art in machine learning.
- Desire and ability to work in an interdisciplinary team.
- Commitment and dedication to develop robust, working systems.
- Fluency in written and oral English.
- Strong programming expertise in Python, C and C++ and general knowledge in computer science.
All contracts will initially last three years. The salary is according to the German TVöD scale (100% E13 or E14) including social security and health insurance benefits. DLR is a family-friendly employer with flexible work-time models and promotes your professional development through a wide range of qualification and further training opportunities.
Contact me for any questions. You can submit your application including a CV and a cover letter summarizing your research experience, interests, relations to the research topic, and a contact for a recommendation letter by following the links given above. Applications will be accepted until the positions are filled.