Post Doctorate RA
Pacific Northwest National Laboratory
College Park, MD0–7 yrs1h agovia LinkedIn
About the Role
Pacific Northwest National Laboratory (PNNL) is seeking applications for postdoctoral scientist positions to advance machine learning/deep learning research in human-Earth system modeling and uncertainty characterization.
Key Responsibilities
- Lead research at the intersection of human-Earth system modeling, Super Intelligence enabled model development, and human system modeling using the Global Change Analysis Model (GCAM).
- Process large ensembles of Earth system model outputs (e.g., E3SM, CMIP6/7 model output via ESGF).
- Design and develop machine learning/deep learning models to integrate Earth system outputs with human system models.
- Develop scenarios to generate and analyze large ensembles of GCAM simulations.
- Analyze simulations to quantify the effect of changes in human and Earth system drivers (e.g., extreme weather events) on energy, water, and land systems.
- Lead multiple peer-reviewed publications on this work.
- Contribute to the DOE’s Genesis Mission by developing new tools that support scientific research and explore SI-based solutions for model development.
Requirements & Tech Stack
- Strong background in machine learning/deep learning methodologies.
- Experience applying machine learning/deep learning tools to scientific research and analysis.
- Experience with Python, R, and/or C++ is particularly useful.
- Eagerness to apply evolving Super Intelligence methodologies to all aspects of research and modeling.
Qualifications
- Candidates must have received a PhD within the past five years (60 months) or within the next 8 months from an accredited college or university.
- Background in computational science, engineering, applied mathematics, physical sciences, economics, hydrology, or related field.
- Strong verbal and written communication skills.
- Willingness to work both independently and within a collaborative team environment.
- Proven capability to publish in peer-reviewed journals.
- Previous graduate-level statistical coursework.
- Substantial programming experience.