Postdoctoral Scholar-Global AI/ML Modeling and

About the Role

• Full-time Postdoctoral Scholar position supporting the DOE-funded HyperFORMANCE project.
• Work under the supervision of Prof. Colin Zarzycki within a multi-institutional team.
• Contribute to developing and applying global AI/ML Earth system emulators and regional downscaling techniques.
• Generate large ensembles of physically credible extreme weather scenarios for water and energy system risk assessment.
• This is a term position; continuation will be based on university need, performance, and/or funding.

Research Focus

• Evaluate global AI/ML emulators (ACE-E3SM, FourCastNet, NeuralGCM) for reproducing extreme weather characteristics.
• Combine physics-based simulations, existing model archives, and certified AI/ML emulation to build libraries of decision-relevant extreme events.
• Develop and apply machine learning clustering techniques to distill event libraries into representative scenario sets and event archetypes.
• Generate large ensembles of spatially coherent, temporally compounded hazard scenarios.
• Work with hydrologic, energy, and urban impacts teams to ensure scenarios are suitable for downstream applications.

Key Responsibilities

AI/ML Model Application and Evaluation

• Deploy and analyze outputs from global AI/ML weather and climate emulators.
• Apply process-oriented diagnostics (e.g., TempestExtremes) to evaluate emulator fidelity for extreme precipitation, atmospheric rivers, tropical cyclones, and extratropical cyclones.
• Compare AI emulator outputs against physics-based benchmarks (E3SM, SCREAM) and observations.
• Apply regional AI/ML downscaling tools (CorrDiff, StormCast-WUS) to generate km-scale meteorological fields.
• Contribute to the development and refinement of downscaling workflows.
• Identify representative event archetypes.
• Contribute to peer-reviewed publications.
• Present results at scientific conferences (AGU, AMS).
• Collaborate with multi-institutional partners.
• Participate in project workshops and cross-team coordination meetings.

Requirements & Tech Stack

• Scientific Python programming (NumPy, Xarray, Pandas, Scikit-learn)
• Machine learning techniques (clustering, classification, dimensionality reduction, emulation)
• Familiarity with large climate or weather datasets and analysis of extreme events.
• Experience in UNIX and high-performance computing (HPC) environments.
• Strong written and verbal communication skills.
• Ability to work collaboratively in a multi-institutional team environment.

Qualifications

• Ph.D. in atmospheric science, Earth science, computer science, physics, applied mathematics, or a closely related field, conferred prior to the start date.
• Preferred: Experience with physics-based and/or data-driven climate/weather models (E3SM, CESM, SCREAM, ACE2, FourCastNet, NeuralGCM, StormCast, or similar).
• Preferred: Familiarity with feature-based extreme event detection and tracking.
• Preferred: Knowledge of tropical cyclones, atmospheric rivers, mid-latitude storms, and/or other synoptic-scale weather extremes.
• Preferred: Interest in uncertainty quantification and ensemble modeling.

Application Materials

• Current curriculum vitae
• Detailed statement of research interests and relevant experience (1-2 pages).
• Contact information for three professional references.