Biography

I am a data scientist and Ph.D. candidate in Data Science at the University of Texas at El Paso, specializing in functional data analysis, machine learning, and uncertainty quantification. My research focuses on developing statistical and AI-driven methods to model complex, high-dimensional data, with applications ranging from Bayesian calibration to biomedical signals such as continuous glucose monitoring. With a strong foundation in mathematics and statistics, I hold a Master’s degree in Mathematics and Finance from the University of Essex, where my thesis explored Bayesian mortality forecasting using non-informative priors and time series analysis. I also earned a B.Sc. in Statistics from the University of Cape Coast. I bring experience in building neural network surrogates, Bayesian calibration frameworks, and advanced regression models, alongside practical expertise in Python, R, SQL, and data visualization tools such as Power BI. I enjoy bridging theory and application, translating data-driven insights into actionable solutions while communicating results clearly to technical and non-technical audiences.

Academic Status

PhD Student - 4th

Research Area/Department

Data Science; Machine Learning/AI

Major/Specialty

Data Science / Statistics

Degrees Earned or in Progress

Phd Data Science - May 2026 expected MS Mathematics - Nov 2020 BS Statistics - May 2016

Academic Preparation

Data Mining Statistical Inference Advanced Algorithm R/Python programming

Research/Publications

K. A. Ohene-Obeng and K. Maupin, Scientific Machine Learning for Surrogate Modeling, in Computer Science Research Institute Summer Proceedings 2024, M. B. P. Adams, T. A. Casey, and B. W. Reuter, eds., Technical Report SAND2024-16688O, Sandia National Laboratories, 2024, pp. 394–408. https://www.sandia.gov/app/uploads/sites/210/2024/12/CSRI-2024-proceedings_Final.pdf#page=402

Research/Academic Interests

My research interests lie at the intersection of functional data analysis (FDA), machine learning, and uncertainty quantification (UQ), with a focus on developing statistical approaches for modeling complex, high-dimensional systems. I am particularly interested in applying FDA and Bayesian methods to domains where data arise in continuous form, such as healthcare, physics, and aerodynamics. Broadly, my academic goal is to advance methodological developments in FDA while ensuring they translate into interpretable, computationally efficient, and impactful solutions across science and engineering.

Computational and Data Science Areas

Applied Mathematics; Artificial Intelligence and Intelligent Systems; Condensed Matter Physics; Health Sciences; Informatics, Analytics and Information Science; Statistics and Probability

Motivation

I once had the privilege of participating in the Sustainable Research Pathways (SRP) program, which led me to an internship at Sandia National Laboratories. That experience was transformative. At Sandia, I worked alongside a diverse group of scientists and engineers who not only mentored me in advanced methods but also broadened my perspective on how inclusive, collaborative research communities can thrive. The projects I was exposed to during that time directly inspired my current dissertation topic, which builds on functional data analysis and uncertainty quantification in physics-based modeling. What excites me about this program is the opportunity to extend that foundation. I know firsthand how powerful SRP can be in creating sustainable connections, between students, faculty, and professionals and it continues to shape careers long after the summer ends. This time, I hope to both contribute more meaningfully to NSF NAIRR projects and to deepen my role within the community, learning from and working with others who bring diverse backgrounds and perspectives. For me, participating again means more than just technical growth. It is a chance to give back, to strengthen the inclusive network that helped me, and to continue building science that is innovative, collaborative, and impactful.

Lightning Talk Title

Functional Data Analysis for Uncertainty Quantification and Model Calibration

Keywords (Maximum 20 words)

Machine Learning; Deep Learning; Uncertainty Quantification; Functional Data Analysis; Bayesian Inference;