University of Michigan
Postdoctoral Research Fellowship - Artificial Intelligence in Weather Prediction
University of Michigan, Ann Arbor, Michigan, us, 48113
Postdoctoral Research Fellowship - Artificial Intelligence in Weather Prediction and Climate Modeling
2 weeks ago Be among the first 25 applicants
University of Michigan provided pay range This range is provided by University of Michigan. Your actual pay will be based on your skills and experience — talk with your recruiter to learn more.
Base pay range $60,000.00/yr - $65,000.00/yr
How to Apply A cover letter is required for consideration for this position and should be attached as the first page of your resume. The cover letter should address your specific interest in the position and outline skills and experience that directly relate to this position.
Should you have any questions regarding the application process, please contact the sponsoring faculty of this position, Dr. Tiantian Yang, at Dr. Yang's current email [email protected] (primary contact before Dec 31, 2025), with a carbon copy to Dr. Yang's University of Michigan email address [email protected] (primary contact after Jan 1st, 2026).
Job Summary The University of Michigan's School for Environment and Sustainability (SEAS) and Dr. Tiantian Yang's research group are seeking a highly motivated Postdoctoral Research Fellow in Artificial Intelligence (AI) and Deep Learning (DL) for Extreme Weather Prediction, Climate Adaptation, Flood Forecasting, and Water Resources Planning. The successful candidate will conduct cutting‑edge research at the intersection of AI/DL modeling, hydrological sciences, and weather/climate sciences, with a focus on applications to extreme weather forecasting (hurricanes, severe storms, floods, and water‑related natural hazards), climate adaptation, and streamflow/flood forecasting from watershed to global scales.
This position will involve developing, applying, and benchmarking advanced AI/DL architectures (e.g., physically-informed AI/DL models, state-space models, spatiotemporal transformers, diffusion models, foundation models and/or Large Language Processing Models) to improve prediction and decision support for weather extremes impacts and water and energy resources planning. The postdoc will collaborate with interdisciplinary teams across SEAS, climate and weather centers, agency partners, etc., and will contribute to advancing climate resilience and sustainable water management.
Additional responsibilities include mentoring graduate students, co-authoring high-impact publications, contributing to competitive grant proposals, engaging with agency and community partners, and presenting research at major conferences.
Benefits
Generous time off
A retirement plan that provides two-for-one matching contributions with immediate vesting
Many choices for comprehensive health insurance
Life insurance
Long-term disability coverage
Flexible spending accounts for healthcare and dependent care expenses
Responsibilities
30% - Conduct research on AI/DL-based extreme weather forecasting, climate modeling, hydrologic forecasting, and flood prediction at watershed to global scales.
30% - Develop research about the integration of physically-informed AI/DL models with climate and hydrologic datasets (e.g., reanalysis, satellite, and observational networks).
20% - Prepare high-quality publications, present results at leading conferences, and contribute to interdisciplinary workshops.
15% - Contribute to grant proposals and collaborative research project development.
5% - Mentor graduate students and engage in community/agency outreach and stakeholder engagement.
Required Qualifications
Expertise in one or more of the following DL architectures: Convolutional Neural Networks (CNNs), Long Short-Term Memory Networks (LSTMs), State-Space Models, Diffusion Models, Transformers, and/or Graph Neural Networks (GNNs).
Knowledge of Physically-Informed or Physically-Aware AI/DL Architectures, i.e., machine learning models explicitly constrained by physical laws (e.g., conservation of mass, momentum, or energy) or designed to integrate physics-based models and data-driven learning for improved interpretability and generalization.
Familiarity with high-performance computing (HPC), cloud platforms, or GPU clusters.
Demonstrated ability to work collaboratively in interdisciplinary and cross-agency teams.
U-M EEO Statement The University of Michigan is an equal employment opportunity employer.
#J-18808-Ljbffr
University of Michigan provided pay range This range is provided by University of Michigan. Your actual pay will be based on your skills and experience — talk with your recruiter to learn more.
Base pay range $60,000.00/yr - $65,000.00/yr
How to Apply A cover letter is required for consideration for this position and should be attached as the first page of your resume. The cover letter should address your specific interest in the position and outline skills and experience that directly relate to this position.
Should you have any questions regarding the application process, please contact the sponsoring faculty of this position, Dr. Tiantian Yang, at Dr. Yang's current email [email protected] (primary contact before Dec 31, 2025), with a carbon copy to Dr. Yang's University of Michigan email address [email protected] (primary contact after Jan 1st, 2026).
Job Summary The University of Michigan's School for Environment and Sustainability (SEAS) and Dr. Tiantian Yang's research group are seeking a highly motivated Postdoctoral Research Fellow in Artificial Intelligence (AI) and Deep Learning (DL) for Extreme Weather Prediction, Climate Adaptation, Flood Forecasting, and Water Resources Planning. The successful candidate will conduct cutting‑edge research at the intersection of AI/DL modeling, hydrological sciences, and weather/climate sciences, with a focus on applications to extreme weather forecasting (hurricanes, severe storms, floods, and water‑related natural hazards), climate adaptation, and streamflow/flood forecasting from watershed to global scales.
This position will involve developing, applying, and benchmarking advanced AI/DL architectures (e.g., physically-informed AI/DL models, state-space models, spatiotemporal transformers, diffusion models, foundation models and/or Large Language Processing Models) to improve prediction and decision support for weather extremes impacts and water and energy resources planning. The postdoc will collaborate with interdisciplinary teams across SEAS, climate and weather centers, agency partners, etc., and will contribute to advancing climate resilience and sustainable water management.
Additional responsibilities include mentoring graduate students, co-authoring high-impact publications, contributing to competitive grant proposals, engaging with agency and community partners, and presenting research at major conferences.
Benefits
Generous time off
A retirement plan that provides two-for-one matching contributions with immediate vesting
Many choices for comprehensive health insurance
Life insurance
Long-term disability coverage
Flexible spending accounts for healthcare and dependent care expenses
Responsibilities
30% - Conduct research on AI/DL-based extreme weather forecasting, climate modeling, hydrologic forecasting, and flood prediction at watershed to global scales.
30% - Develop research about the integration of physically-informed AI/DL models with climate and hydrologic datasets (e.g., reanalysis, satellite, and observational networks).
20% - Prepare high-quality publications, present results at leading conferences, and contribute to interdisciplinary workshops.
15% - Contribute to grant proposals and collaborative research project development.
5% - Mentor graduate students and engage in community/agency outreach and stakeholder engagement.
Required Qualifications
Expertise in one or more of the following DL architectures: Convolutional Neural Networks (CNNs), Long Short-Term Memory Networks (LSTMs), State-Space Models, Diffusion Models, Transformers, and/or Graph Neural Networks (GNNs).
Knowledge of Physically-Informed or Physically-Aware AI/DL Architectures, i.e., machine learning models explicitly constrained by physical laws (e.g., conservation of mass, momentum, or energy) or designed to integrate physics-based models and data-driven learning for improved interpretability and generalization.
Familiarity with high-performance computing (HPC), cloud platforms, or GPU clusters.
Demonstrated ability to work collaboratively in interdisciplinary and cross-agency teams.
U-M EEO Statement The University of Michigan is an equal employment opportunity employer.
#J-18808-Ljbffr