气候模式/机器学习：PhD at DLR, Germany
学术
2024-10-02 17:07
比利时
the Department Earth System Model Evaluation and Analysis of the
Institute of Atmospheric Physics at the German Aerospace Center
(DLR-IPA) in collaboration with the Climate Modelling Department of the
Institute of Environmental Physics (IUP) at the University of Bremen
invites applications for 5-6 PhD positions in the field of improving
climate models and analysis with machine learning and spaceborne Earth
observations. The PhD candidates will be supervised by Prof. Veronika Eyring, head of
the department and Professor of Climate Modelling at the University of
Bremen. All PhD candidates will also be co-supervised by a leading
expert in this field from the ERC Synergy Grant “Understanding and
Modelling the Earth System with Machine Learning (USMILE,
https://www.usmile-erc.eu/)” or from another collaborating institution.
An extended research stay at the co-supervisor’s institution is envisaged. Based on the candidate’s experience and interest, PhD positions in the
following broad areas of research are available: (1) Developing and enhancing ML-based parametrizations for climate
models to reduce systematic errors and to enhance projection
capabilities with innovative ML methods (e.g., physical constraints,
eXplainable Artificial Intelligence, uncertainty quantification, causal
deep learning), (2) Developing data-driven equation discovery methods to learn
interpretable and physically consistent equations from high-fidelity
datasets to enhance understanding and representation of subgrid-scale
processes (e.g., clouds, convection) in climate models, (3) Developing and benchmarking foundation models for selected
climate modeling tasks,(4) Developing ML-techniques for improved understanding and detection
of extreme events, (5) Developing innovative methods, including ML, to enhance the
evaluation and analysis of climate models in comparison to observations
using the Earth System Model Evaluation Tool (ESMValTool,
https://esmvaltool.org/). At the DLR Institute of Atmospheric Physics and the University Bremen we
provide excellent facilities with opportunities to work with
world-renowned experts in the field of Earth system modelling, Earth
observations, and machine learning. The department develops an
ML-enhanced version of the Icosahedral nonhydrostatic (ICON) model
alongside an evaluation system (ESMValTool) that supports the
comprehensive evaluation of Earth system models in comparison to
observations and to other models participating in the Coupled Model
Intercomparison Project (CMIP).The ultimate goal is to improve climate models and projections with
machine learning and spaceborne Earth observations for actionable
climate science and technology assessments in aeronautics, space,
transport, and energy research. For further reference of our work,
please see the Veronika’s publications at
https://scholar.google.at/citations?user=Y3i87foAAAAJ&hl=de and our
Github repository at https://github.com/EyringMLClimateGroup/. Please submit your application including a letter of motivation
explaining your research interest for the selected topic, curriculum
vitae, publication list if available, documentation of academic degrees
and certificates, and two letters of reference here:
https://dlr.concludis.de/prj/shw/a9831611ac9fbe3751fad04d7b77fbe0_0/95386/Physicist_Mathematician_Computer_Scientist_or_similar_f_m_x.htm?b=0![]()
![]()
