STATEMENT OF WORK.pdf

STATEMENT OF WORK

1. Objective/Requirements Membership to the Spatiotemporal Thinking, Computing, and Applications Center (STC)m which is a National Science Foundation (NSF) Industry/University Cooperative Research Center (I/UCRC) program at George Mason University. The STC will provide unique opportunities to research the application of artificial intelligence and machine learning software and hardware capabilities as applied to Earth Science applications. In addition, the membership enables access to other research being funded by all Government and Industry members of the I/UCRC.

2. Characteristics, Scope, and Specs The mission of the STC is in direct alignment with the overall mission of NASA and specifically with the goals of the Advanced Information Systems Technology (AIST) Program in the Earth Technology Office (ESTO, Code 407). NASA's AIST Program identifies, develops, and supports adoption of software and information systems, as well as novel computer science technologies expected to be needed by the Earth Science Division in the 5-10-year timeframe. STC’s research interests are very much aligned with several AIST projects, especially projects related to the development of analytic frameworks for GreenHouse Gases (GHG), e.g., utilizing Machine Learning and Atmospheric models. This makes it an ideal partnership to explore new methods for supporting Earth science. In addition, the STC provides access to other research being funded across Government and industry partners within the STC; research that is both unique to the STC and relevant to AIST. No other NSF funded center or group of universities provides such a group of focused research opportunities centered around developing these unique solutions for science.

Systematically Study AI/ML in Air Quality Analysis: Continue systematically investigate the application of AI/ML and geospatial techniques for predicting and simulating greenhouse gases (eps. methane CH4 and carbon dioxide) using various datasets from in-situ to satellite.

Create Open-Source AL/ML Toolkit: Develop an adaptable ML toolkit for atmospheric analysis, designed for integration and support the AIST AQACF and FireAlarm projects to enhance air quality research and forecasting capabilities towards digital twins.

Curate Pollutant Datasets: Compile a comprehensive training dataset for GHG with accurately quantified uncertainties, supporting Earth science digital twins and ML research.

Promote STEM Education: Initiate outreach to involve high school and community college students in DT and atmosphere research through hands-on AI/ML projects to train the future workforce.

Contribute to the AIST ESDT architecture evolution, esp., on advanced computing, data fusion and uncertainty aspects

3. Place of Performance George Mason University Fairfax VA

4. Period of Performance

August 1, 2024 – July 31,2025.