Hello! I’m Chidinma.

I’m a computational mathematician, and I’m fascinated by the shape hidden inside data: the way a city’s neighborhoods connect, the way the eye responds to spaceflight, the way a student’s circumstances shape how they learn. I build methods that find that structure and explain it. I want methods whose behavior can be proved, measured, and understood, because a result no one can interpret is hard to act on.

My path here crossed an ocean and a few state lines. I grew up in Nigeria, studied mathematics and economics among the Green Mountains of Vermont, earned my master’s in Illinois, and came to North Carolina for my Ph.D. Through all of it, one aim has stayed the same: turn data into clear understanding, and clear understanding into better decisions.

Research Summary

I’m a Ph.D. candidate in Computational Mathematics at UNC Greensboro, working with Dr. Thomas Weighill, and I expect to graduate in May 2027. My dissertation asks a deceptively simple question. When a map shows clustering, is that pattern real, or is it an artifact of the scale we looked at?

Since the 1950s, the standard tool for this question, Moran’s I, has compared each place only with its immediate neighbors. I asked what happens if that comparison is allowed to keep going. The answer is a new measure, a diffusion distance built on Markov chains and optimal transport, which tracks how strongly a spatial pattern resists mixing across an entire region. Moran’s I is exactly its first step, so the new measure extends the classical one rather than replacing it.

I proved bounds and stability results for the diffusion distance. I also derived significance tests that need no random sampling, and tested the measure on the census-tract maps of 100 U.S. cities. There, it separates sharp local clustering from clustering that a city’s wider connectivity sustains. The work is available as a preprint (arXiv:2607.14880) and is being expanded for the SIAM Journal on Matrix Analysis and Applications.

The same question about scale led me into topological data analysis. As a co-mentor in UNCG’s NSF-supported Computational Statistics REU in 2025 and 2026, I helped two teams of undergraduates turn summer questions into real research. They developed new ways to compare the shape of datasets without being fooled by their size, and applied them to neural networks, pollution data, city demographics, and North Carolina redistricting. Four of those students are now co-authors on two manuscripts, one of them under review at the AAAI Conference on Artificial Intelligence.

My research also reaches toward space. Spaceflight-Associated Neuro-Ocular Syndrome (SANS) is a leading health risk for long missions. In the AI/ML Analysis Working Group of NASA’s Open Science Data Repository, I contribute to a project building a digital twin of how the retina responds to spaceflight.

Before UNCG, I earned my M.S. in Mathematics (Statistics and Operations Research) at Southern Illinois University Edwardsville, where my thesis proved new results for a leading shortest-path algorithm. I earned my B.A. in Mathematics, summa cum laude, at Castleton University (now Vermont State University). There I was named Best Graduating Student in Mathematics, and I later returned as keynote speaker at the 2021 commencement.