Distributed Computation of Persistent Homology from Partitioned Big Data

This peer-reviewed conference publication was produced as part of graduate research conducted at the University of Cincinnati College of Engineering and Applied Science.

The paper addresses a major scalability challenge in topological data analysis by distributing persistent homology computations across partitioned datasets. The approach reduces computational bottlenecks while maintaining topological fidelity.

The work demonstrates how high-performance computing techniques can make advanced topological methods practical for large-scale scientific and industrial applications.