Improve computational and data analytics capabilities for Earth system science

The goal of CISL’s research activities is to sustain progress in Earth system science by combining powerful supercomputing resources with innovative, outstanding computational and data science research. CISL helps transform geoscience by aligning its computational resources with the research objectives of NCAR’s other laboratories and the requirements of data-centric science.

CISL’s research portfolio advances data-centric research, applies machine learning and statistical methods to high-performance-scale problems, and uses techniques and tools from computational science to refactor applications and algorithms for better performance and portability on existing and emerging high-performance computing systems. These focus areas not only support NCAR’s science mission, they also have broad applicability across the geosciences and beyond.

CISL tackles the challenges of developing new data-centric approaches by combining numerical models with observations through data assimilation, interpreting heterogeneous data, and quantifying the uncertainty in predictions in ways that are useful for decision making and policy. CISL’s new Analytics and Integrative Machine Learning (AIML) group provides a core capability and focal point for simplifying, enhancing, and accelerating traditional HPC tasks by harnessing machine learning and advanced statistical techniques. These areas range from modeling, model verification, forecasting, and enhanced data analytics to using machine learning to optimize the operation of HPC systems themselves. Finally, CISL adapts computational science methods and tools to speed code optimization and porting, enabling NCAR to exploit new technologies such as graphics coprocessors (GPUs).

Our research portfolio is guided by the NCAR strategic plan. Data science research supports NCAR’s strategic imperative of improving predictions of weather and climate and better estimating their impact. Our research also furthers strategic efforts in community model development. CISL research on the use of emerging architectures and technologies, such as GPUs and machine learning techniques, plays a central role in yet another imperative: developing new computational resources.

CISL’s research is enhanced by a robust set of ongoing partnerships. These partnerships take the form of NCAR joint appointments; long-term research and development projects that include resource investments by vendor, industry, university, and research laboratory partners; and recurring workshops, symposia, hackathons, and other training events that focus on fostering understanding and use of emerging technologies and techniques within the community.

This work is supported by NSF Core funding and other sources as specified in the following sections.