CIRES/PSD Machine Learning for Improved Weather Forecasts (Post-Doc)
The skill of weather forecasts has improved steadily over the past four decades as the results of better forecasting models, better and more numerous observations, more efficient use of observations through data assimilation, and more refined after-the-fact correction of forecasts based on historical errors. Machine learning techniques, exploiting the explosive growth of knowledge, tools, and software, are now the basis for many corrections. The University of Colorado’s Cooperative Institute for Research in Environmental Sciences (CIRES) and the Physical Sciences Division (PSD) at the NOAA Earth System Research Lab in scenic Boulder, Colorado, seeks an enthusiastic and capable Postdoc to help us tighten up this loop and use machine learning to make forecasts that require less correction.
The Postdoc will work with world leaders in data assimilation and ensemble forecasting to improve forecasts by machine-learning short-term forecast error and forecast uncertainty, with the aim of applying those error corrections in-line to improve ensemble forecasts. The requirement to improve probabilistic forecasts - not only the average error but the chaotic variability - makes this an especially challenging and exciting application. This is a real-world application: the project will use NOAA’s next-generation global forecasting system. Our group is tightly linked to the National Weather Service and effective corrections could be affecting national weather forecasts within a few years.
Who We Are
At CIRES, the Cooperative Institute for Research in Environmental Sciences, more than 800 environmental scientists work to understand the dynamic Earth system, including people’s relationship with the planet. CIRES is a partnership of NOAA and the University of Colorado Boulder, and our areas of expertise include weather and climate, changes at the Earth’s poles, air quality and atmospheric chemistry, water resources, and solid Earth sciences. Our vision is to be instrumental in ensuring a sustainable future environment by advancing scientific and societal understanding of the Earth system.
Physical Sciences Division website:
The Postdoctoral researcher will work with NOAA and CIRES scientists at PSD to develop machine learning corrections for ensemble forecasts with NOAA’s prototype global weather forecasting system. Tasks will include replaying the forecasts model against operational analyses on high-performance computing systems to develop a long history of incremental analysis updates, using machine learning to predict the analysis corrections based on the model state, and assessing the degree to which probabilistic forecast skill can be improved by applying the corrections.
What You Should Know
The project is funded for two years with some possibility for extensions.
CIRES commits to inclusive excellence by advancing equity and diversity in all that we do. We are an Affirmative Action/Equal Opportunity employer, and particularly encourage applications from members of historically underrepresented racial/ethnic groups, women, individuals with disabilities, veterans, LGBTQ community members, and others who demonstrate the ability to help us achieve our vision of a diverse and inclusive community.
This position will be rostered in CIRES at the University of Colorado Boulder, but will be physically situated in the David Skaggs Research Center, 325 Broadway, Boulder, CO 80305. If you are the selected finalist you will be required to pass a federal laboratory background clearance for site access.
What We Can Offer
- A relevant PhD degree is required for this role.
- Experience in ensemble forecasting, data assimilation, and machine learning.
- Candidate must be comfortable working in Python and familiar with ensemble forecasting concepts.
- Candidate must be competent in using high-performance computing to produce large datasets with a global weather forecasting model.
What we would like you to have
- An ideal candidate would have experience with machine learning.
- Be Challenged. Be Impactful. Be Boulder.
The University of Colorado offers excellent benefits, including medical, dental, retirement, paid time off, tuition benefit and ECO Pass. The University of Colorado Boulder is one of the largest employers in Boulder County and offers an inspiring higher education environment. Learn more about the University of Colorado Boulder.
To apply, please submit the following materials:
- Resume or CV.
- Cover letter addressed to the Search Committee briefly describing your qualifications, professional goals, and specific interest in this position.
- List of 3 references: the names, professional titles, and contact information of those who are familiar with your qualifications and work history.
- If you are selected as the finalist, we will contact you through email and request that you submit 1 name and email of a reference who will be asked to submit a letter of recommendation. This information will be kept confidential and viewable only by the search committee.
This position will remain open until filled.
Note: Application materials will not be accepted via email. For consideration, applications must be submitted through CU Boulder Jobs.