The Eisaman Lab for Carbon Removal and Clean Technologies in the Department of Earth & Planetary Sciences and the Yale Center for Natural Carbon Capture (YCNCC) at Yale University is seeking a highly motivated postdoctoral researcher to work on an interdisciplinary project at the intersection of ocean and climate modeling, machine learning, and artificial intelligence. The successful candidate will collaborate with an interdisciplinary team of oceanographers, climate scientists, and machine learning researchers to develop and apply novel machine learning techniques to improve simulations of the ocean and climate system. The goal of the research effort is to better quantify the uncertainty of ocean model forecasts used for the Measurement, Reporting, and Verification (MRV) of Ocean Alkalinity Enhancement (OAE) approaches to Carbon Dioxide Removal (CDR).
Key responsibilities
- Develop and implement machine learning algorithms to parameterize subgrid-scale processes in ocean and climate models
- Apply deep learning and other AI methods to emulate complex model parameterizations and accelerate climate simulations
- Analyze large datasets from ocean models, satellite observations, and field experiments using statistical and machine learning tools
- Identify relationships between model biases and uncertainties
- Publish research findings in leading journals
- Present results at scientific conferences
- Participate in the mentoring of graduate and undergraduate students
Requirements
- PhD in physical oceanography, climate science, computer science, machine learning and artificial intelligence, or related fields.
- Strong background in ocean and/or climate modeling. Experience with common community models (e.g. POP, MITgcm, CESM, etc.).
- Experience with climate and ocean modeling datasets (e.g., ECCO, GLODAP, etc.)
- Proficiency in machine learning frameworks (e.g., TensorFlow, PyTorch, sklearn, etc.) and languages (Python, C )
- Knowledge of deep learning and neural networks, generative adversarial networks, time series predictive methods such as LSTMs, Bayesian machine learning methods, and statistical learning
- Excellent writing and oral communication skills
- Ability to work collaboratively in an interdisciplinary team
- Record of publishing high-impact journal papers
Preferred Qualifications
- Experience with Bayesian emulation and hierarchical models
- Experience with uncertainty quantification and bootstrapping or Markov Chain Monte Carlo (MCMC) methods
- Experience with or knowledge of operations research and optimization methods (e.g., convex optimization, nonlinear methods, integer programming, etc.) and associated tools such as Gurobi or Python packages like “or-tools”
- Knowledge of Physics-informed NN frameworks such as SimGAN or NVIDIA’s Modulus
- Programming experience in or ability to learn Fortran / C
Logistics
-
This two-year postdoc position is available immediately. Competitive salary and benefits offered commensurate with experience. Our lab provides a dynamic, intellectually stimulating environment and opportunities for career development.
-
To apply, email a cover letter, CV, research statement, and contact details for 3 references to matthew.eisaman@yale.edu Review of applications will begin immediately and continue until the position is filled.