Associate Research Scientist

The National Science Foundation-funded Learning the Earth with Artificial intelligence and Physics (LEAP) Science and Technology Center (STC), https://leap.columbia.edu/, a large multi-institutional center effort meant to improve climate projections using novel artificial intelligence for better climate adaptation, invites applications for two Associate Research Scientist (ARS) positions in the fields of climate science and data science.

In your application materials, please indicate to which project you are applying, or rank your preference if you are interested in applying for more than one. Applications will be reviewed on a rolling basis, but applications received by April 15th are guaranteed to receive consideration.

Associate Research Scientist: global atmospheric modeling and machine learning
Columbia Req #132403

Description:
Columbia Engineering, the Fu Foundation School of Engineering and Applied Science at Columbia University in the City of New York invites applications for an Associate Research Scientist in the field of global atmospheric modeling and machine learning, under the supervision of Greg Elsaesser at Columbia University/NASA GISS and Brian Medeiros at NSF NCAR (National Center for Atmospheric Research). The position is part of the National Science Foundation-funded Learning the Earth with Artificial intelligence and Physics (LEAP) Science and Technology Center (STC), https://leap.columbia.edu/, a multi-institutional center effort meant to improve climate projections using novel artificial intelligence for better climate adaptation. This position will be based at NCAR in Boulder, Colorado.

The goal of this project is to build key connections that enable results from machine learning activities developed within LEAP to be incorporated and evaluated in the atmospheric component of the Community Earth System Model (CESM). This work is expected to proceed in two parallel efforts that will be coordinated by the incumbent. The first builds on ongoing work and focuses on conducting and analyzing perturbed physics ensembles with the Community Atmosphere Model (CAM) to quantify sensitivity of the simulated climate to parameter choices. Machine learning approaches will be applied to provide actionable information about parameter sensitivity and optimization for specific climatic targets. By applying parameter estimation techniques within the development version of CAM, this project will inform model development in real time. This ARS will work with LEAP and NCAR scientists to build the workflows that allow for rapid production, analysis, and emulation of PPEs and to disseminate findings to CESM developers and the wider research community. The second, equally important, aim of the project is to establish more general support and coordination of LEAP-developed machine learning activities, including conducting and analyzing experiments using ML-based parameterizations and emulators as well as explorations of methods to generate high-quality training data sets for additional ML-based schemes. 

The ARS will closely collaborate with members of the Atmospheric Modeling and Predictability Section in the Climate and Global Dynamics Laboratory at NCAR as well as with graduate students, postdocs, and other staff within LEAP.

The applicant should have a background in atmospheric modeling, atmospheric science, or closely related fields, and ideally should have significant experience in machine learning or statistics. 

One of LEAP’s goals is to increase the diversity in climate science and data science. We welcome and encourage applications from individuals of all backgrounds and identities. We are committed to building a diverse and inclusive community and believe that a variety of perspectives and experiences is essential to advancing our research and mission.

Minimum Qualifications:
A Ph.D. in Atmospheric Science, Data Science, Computer Science, Physics, Earth System Science or a directly related discipline is required by the start of the appointment.
Strong programming skills are a requirement.

Preferred Qualifications:
Post-doctoral experience and demonstrated experience in Earth System Science, Data Science, or similar.
Fluency in Python.
Familiarity with Fortran.
Advanced experience in machine learning.
Demonstrated experience in statistical/mathematical analyses of model output and/or observational datasets.
Experience running and analyzing global climate simulations on high performance computing platforms
Excellent command of the English language (verbal and written) and strong communication skills are desired.

Application Instructions:
Please apply via the Columbia University website: https://academic.careers.columbia.edu/#!/132403?keywords=leap&sortKey=keywordScore

Applications must include: (a) curriculum vitae (b) statement of research (optional) (c) names of at least three references who may be asked to provide letters.

Associate Research Scientist - Land Modeling and Machine Learning
Columbia Req #132421

Description:
Columbia Engineering, the Fu Foundation School of Engineering and Applied Science at Columbia University in the City of New York invites applications for an Associate Research Scientist in the field of land modeling and machine learning, under the supervision of Pierre Gentine at Columbia University and David Lawrence at the National Center for Atmospheric Research (NCAR). The position is part of the National Science Foundation-funded Learning the Earth with Artificial intelligence and Physics (LEAP) Science and Technology Center (STC), https://leap.columbia.edu/, a multi-institutional center effort meant to improve climate projections using novel artificial intelligence for better climate adaptation. The position will be based at NCAR in Boulder, Colorado.

The aim of this project is to develop an open-source process for systematic parameter estimation for the Community Land Model (CLM), drawing on domain expertise from CLM scientists and machine learning emulation and optimization methodologies.  Full complexity land models like CLM include a large number of parameters that influence the biophysical and biogeochemical processes that determine fluxes and states predicted by the model. Prior studies have demonstrated that important emergent properties of the land system (e.g., CO2 fertilization of plants or runoff response to temperature or precipitation perturbations) exhibit strong parametric uncertainty.  A successful methodology to estimate parameter values and uncertainty in these parameter values has promise to reduce uncertainty in Earth System model simulations of terrestrial carbon, water, and energy responses to and impacts on climate change.  A second, equally important, aim of this project is to establish more general support and coordination of land-oriented LEAP ML-based parameterization development and parameter optimization activities.  This will include conducting and analyzing CLM experiments using new ML-based parameterizations and optimal parameter settings and contributing to the integration and testing of these developments into the broader CESM effort.

The ARS will closely collaborate with members of the Terrestrial Sciences Section in the Climate and Global Dynamics Lab at NCAR as well as with graduate students, postdocs, and other staff within LEAP.

The applicant should have a background in land modeling and terrestrial science, and ideally should have advanced experience in machine learning or statistics. 

One of LEAP’s goals is to increase the diversity in climate science and data science. We welcome and encourage applications from individuals of all backgrounds and identities. We are committed to building a diverse and inclusive community and believe that a variety of perspectives and experiences is essential to advancing our research and mission.

Qualifications:
Minimum Qualifications
Strong programming skills are a requirement.

Preferred Qualifications
A Ph.D. in Data Science, Computer Science, Physics, Earth System Science or a directly related discipline, or equivalent experience.
Fluency in Python.
Advanced experience in machine learning.
Demonstrated experience with large-scale models.
Excellent command of the English language (verbal and written) and strong communication skills are desired.

Application Instructions:

Please apply via the Columbia University website: https://academic.careers.columbia.edu/#!/132421?keywords=leap&sortKey=keywordScore
Applications must include: (a) curriculum vitae (b) statement of research (optional) (c) names of at least three references who may be asked to provide letters.