Developing Distributed High-performance Computing Capabilities of an Open Science Platform for Robust Epidemic...

Area of Science:

• Computational epidemiology
• Scientific computing
• Public health informatics

Background:

• The COVID-19 pandemic accelerated scientific collaboration but exposed limitations in utilizing advanced computing systems.
• Researchers faced challenges in accessing scalable computing, adapting models, sharing data, and ensuring result reproducibility.

Purpose of the Study:

• To present the goals, requirements, and initial implementation of OSPREY, an open science platform designed for robust epidemic analysis.
• To address identified capability gaps in applying high-performance computing (HPC) to model complex social systems.

Main Methods:

• Developed OSPREY, an open science platform featuring an integrated, algorithm-driven HPC workflow architecture.
• Implemented federated HPC resource coordination with secure, automated access.
• Incorporated scalable and fault-tolerant task execution, an asynchronous API, a multi-language approach, and efficient wide-area data management.

Main Results:

• Demonstrated a prototype implementation of OSPREY.
• Showcased the platform's ability to coordinate tasks across federated HPC resources.
• Validated scalable, fault-tolerant execution and efficient data management for epidemic analysis.

Conclusions:

• OSPREY provides a robust solution for epidemic analysis by integrating advanced computing capabilities.
• The platform facilitates collaboration and overcomes computational barriers faced during public health crises.
• Open-source availability of OSPREY code promotes further development and application in scientific research.