4 Projects Selected for the Inaugural Internet2/Microsoft Azure Accelerator Cohort
By Amanda Tan - Internet2 Research Engagement Program Manager
Estimated reading time: 4 minutes
Internet2 CLASS and Microsoft Azure recently launched its Accelerator for Research Program. The program provides the opportunity for the research community Internet2 serves to explore the power of cloud computing, leverage the vast array of data science tools and services that Azure provides, and ultimately arrive at better and faster scientific results.
For the inaugural cohort (Fall 2022), the program solicited applications targeted at migrating Artificial Intelligence (AI), Machine Learning (ML), and Image Analysis workloads from on-premise infrastructure to the cloud. Four projects were selected from the 14 submitted and received a $5,000 award in Azure credits (administered through CloudBank). The selected projects will also benefit from the technical expertise of Azure-certified solutions architects and have the opportunity to showcase and share their work with the community.
|Hear About Their Findings|
|Teams from these four Internet2/Azure Accelerator for Research projects will showcase their final findings and cloud-optimized research workflows in a virtual presentation on Dec. 7, 2022, 9 – 11 a.m. PT / 12 – 2 p.m. ET|
|Reserve a spot at the final presentation|
- Dr. Yifeng Cui and his team at the University of California, San Diego (UCSD), in partnership with the San Diego Supercomputing Center (SDSC), look to improve earthquake resilience through scaling seismic simulations and taking advantage of Microsoft Azure to expand computational throughput. Further, the project aims to document the continuous integration and delivery process of the computational infrastructure to be made for broad use by the Southern California Earthquake Center (SCEC) community modeling environments. (Project: Accelerating Earthquake Simulation on Microsoft Azure; Team: Yifeng Cui, Akash Palla, Haochen Wang, Qinghua Zhou)
- Dr. Jose L. Agraz, a postdoctoral fellow at the University of Pennsylvania, is working to enhance the detection and characterization of breast cancer whole-slide-images (WSIs). More specifically, the detection of cancer at the cell level in a large area of tissue and processing large amounts of WSIs makes machine-learning algorithms an indispensable pathologist’s tool, and Dr. Agraz’s research utilizes the computational power of Microsoft Azure to demonstrate a novel color normalization method as the solution for breast cancer WSI color normalization bias with reproducible and accurate results. (Project: Breast Cancer H&E stain color normalization. A step closer towards Universal Unbiased Whole-Slide Image Color Normalization; Team: Jose Agraz, Alex Grunfeld, Andrew Chen, Robert Pozos)
- Dr. Shima Abadi hopes to advance her group’s expertise in managing large datasets and building cloud-native ML workflows. Distributed Acoustic Sensing (DAS) is a new technology that transforms telecommunication fiber optic cables into dense sensor arrays. Using this sensing technology for ocean monitoring could be a major breakthrough in conservation since it enables researchers to continuously monitor a vast area of the ocean (~100 km) with a single device (interrogator) that is attached at one end of the fiber optic cable on shore. (Project: Distributed Acoustic Sensing for Ocean Monitoring (DAS); Team: Shima Abadi, Alexander Douglass)
- Anna Mikkelsen and her colleagues at the University of Hawaiʻi at Mānoa’s Climate Resilience Collaborative will use Azure credits and technical expertise to build a shoreline detection framework that is unparalleled in organization and efficiency. The project makes use of a myriad of satellite imagery sources ranging from high- to low-resolution (e.g., Landsat 8, Sentinel-2, Planet Labs, etc.), ML models, and Azure compute and data storage to build a comprehensive database of satellite and airborne imagery of Hawaii’s beaches. (Project: CSTSI: coastal surveillance of Hawaii’s shorelines through satellite Imagery; Team: Anna Mikkelsen, Richelle Moskvichev, Erica Ta, Joel Nicolow)