NOAA’s Satellite and Information Services (NESDIS) Joint Venture Partnerships (JVP) published a concept study, authored by Orion Space Solutions (Orion) under a JVP Broad Agency Announcement contract awarded in September 2022, that concludes NOAA’s diverse base of users would benefit from deployment of a next-generation Earth observation digital twin data ground processing and dissemination system powered by machine learning.
Orion prototyped how an Earth observation digital twin can provide valuable real-world insights to NOAA data products and services users by “enabling the kind of last-mile insights NOAA's diverse user base requires” to interact with NOAA’s enormous data catalog. Orion’s concept study can be downloaded here. Joint Venture exploration of new capabilities is not a commitment to exploit those capabilities in a future NOAA mission.
The Orion award specifically sought to examine digital twin data ground processing and dissemination systems to streamline environmental observation from a variety of sensors in various orbits.
Digital twin technology produces a digital simulation of a real, physical system – in this case, NOAA’s understanding of weather and Earth system science – for testing, modeling, and exploration. Working in a digital twin environment allows researchers to rapidly build and examine a wide variety of potential weather scenarios.
Orion’s concept study examined the use of machine learning and advanced software to prototype an automated Earth observational data processing, analysis, and visualization system for use by weather forecasters, scientists, and other users of NOAA data and information.
Through partnerships with the commercial sector, other public agencies, and research institutions, JVP pursues innovation and new ideas to develop the next generation of remote sensing and data systems. The JVP awards fund pilot and demonstration projects that explore the feasibility of emerging instrument and spacecraft technology, ground systems, and mission concepts.
The Orion study made several recommendations for a potential digital twin of Earth observational data processing:
- Use of open-source software tools, processes and engines that meet standards set by the geospatial community.
- Use of open-source formats for data storage and streaming, with a preference for the Open Geospatial Consortium 3D Tiles format. This format can store nearly every data set encountered with capability for continued growth and customization.
- Use of web-based software tools for viewing data to avoid the need for downloading client software.
- Automation of the data processing pipeline, including integration, to continually deliver information as it becomes available.
- Leave source scientific data in original, container format, with a second visualization data format stored as modeled data points embedded in a hierarchical grid format for efficient storage and streaming while maintaining scientific fidelity.