Massachusetts Institute of Technology, Institute for Data, Systems, and Society
Position ID:
MIT-IDSS-PDA [#31956]
Position Title:
Postdoctoral Associate
Position Type:
Postdoctoral
Position Location:
Cambridge, Massachusetts 02139, United States of America
Subject Area:
Appl Deadline:
2026/06/30 23:59:59 (posted 2026/04/16)
Position Description:
Position Description
Position Overview: The Postdoctoral Associate will work under the direction of Prof. Sherrie Wang to develop deep learning methods for hyper-local weather forecasting with uncertainty quantification. The position is supported by a NASA-funded project focused on probabilistic downscaling of global weather models using satellite re-mote sensing, generative AI models, and conformal prediction. The research integrates numerical weather prediction (NWP) outputs, weather station observations, and satellite data to generate accurate, uncertainty-aware local forecasts for applications in disaster response and energy systems.Principal Duties and Responsibilities (Essential Functions):
• Develop and implement machine learning models for local weather forecasting and uncertainty quantification, in-cluding probabilistic and generative approaches.
• Integrate and analyze heterogeneous datasets, including numerical weather prediction outputs, weather station ob-servations, and satellite remote sensing data.
• Design and run experiments to evaluate model performance and generalization across locations and conditions.
• Contribute to the preparation of manuscripts, technical reports, and presentations for scientific and sponsor-facing dissemination.
• Collaborate with project team members and external partners to align research with application needs in energy and disaster response.
• Mentor graduate and undergraduate students and contribute to a collaborative research environment.
• Participate in project meetings and related research activities as needed.
Supervision Received: Reports to Prof. Sherrie Wang.
Supervision Exercised: No direct reports.
Requirements: Ph.D. in computer science, electrical engineering, atmospheric science, or a related field with a strong background in machine learning, statistical modeling, or geospatial data analysis.
Required experience includes:
• Experience with deep learning methods for spatiotemporal data
• Experience working with large-scale datasets, ideally including remote sensing or weather/climate data
• Strong programming skills in Python and experience with ML frameworks
• Familiarity with uncertainty quantification methods
Preferred qualifications:
• Experience with diffusion models or generative AI methods
• Background in Earth science, weather forecasting, or environmental data analysis
• Experience integrating heterogeneous data sources (e.g., satellite imagery, numerical models, and in-situ observations)
Please submit all application materials through academicjobs.
This is a 24-month position with a possibility of renewal based on the availability of funding.
Salary Range: $71,000 - $90,000
MIT is an equal opportunity employer. We strongly encourage applications from individuals from all identities and backgrounds. All qualified applicants will receive equitable consideration for employment based on their experience and qualifications and will not be discriminated against on the basis of race, color, sex, sexual orientation, gender identity, pregnancy, religion, disability, age, genetic information, veteran status, or national or ethnic origin. View MIT Policy on Non Discrimination and EEOC’s Know Your Rights. Employment is contingent upon the completion of a satisfactory background check, including possible verification of any findings of misconduct (or pending investigations) from prior employers.
Application Materials Required:
Submit the following items online at this website to complete your application:
- Cover letter
- Curriculum Vitae
- Research statement
- Two or more reference letters (to be submitted online by the reference writers on this site
)
And anything else requested in the position description.
Further Info: