Sage is a cutting-edge cyberinfrastructure testbed funded by the NSF Office of Advanced Cyberinfrastructure to support AI research. The platform provides real-time environmental monitoring and AI-enabled edge computing at a national scale. By bringing advanced AI to the edge, where data is collected, full-resolution analysis, dynamic automation, and immediate actionable responses can be computed. Each Sage node includes a GPU and AI-optimized software stack connected to instruments such as infrared cameras, RGB cameras, LIDAR, and traditional sensors for air quality and wind, as well as LoRaWAN connected sensors for low-bandwidth measurements such as soil moisture. With over 100 Sage nodes deployed across 17 states, including fire-prone regions in the Western U.S., the platform supports rapid-response science and sustained observation of ecological systems, agriculture, urban environments, and weather-related hazards.

Read more at Support of AI for Fire Science.

On Sep 20th, 2024, the Sage team presented the Sage edge computing platform and self-supervised learning at the edge in the TAPIA conference (See the presentation slides). During the workshop, we met many academic professors, computer scientists, and students who were passionate about engaging with us and sharing their research challenges. We look forward to future collaborations with them!

Interested in running the Jupyter notebooks we demonstrated in the presentation? Check them out here:

• geospatial mapping notebook
• node performance plotting notebook

The Sage team is thrilled to kick off 2024 by introducing our new Sage Testbed!

Earlier this year, Sage computer science researchers and computational scientists from Argonne's Advanced Photon Source (APS) collaborated to answer the question: Can edge computing be used in X-ray beamline experiments to process high-volume and fast data streams for real-time decision making? Read more about the experiment here under Sage Science.

Hi, I am Pratool Bharti, an assistant professor in Computer Science department at Northern Illinois University (NIU). Before joining NIU, I worked for 2 years in a Florida based startup as a research and development manager. There, my role was to design and build computer vision and machine learning based yard management system that automatically tracks the vehicles inside a freight yard.