I am a PhD candidate at the University of Kansas (graduating May 2026) working at the intersection of data science and geoscience. I specialize in building machine learning pipelines for complex, messy natural datasets, from deep-sea sediment cores to SEM imagery.

My technical toolkit includes Python (scikit-learn, PyTorch, Pandas), statistical modeling, and computer vision. I've applied unsupervised learning algorithms (GMM, K-means, DBSCAN) to classify sediment deposits from sparse core measurements, and built an end-to-end deep learning pipeline using Meta's Segment Anything Model for automated mineral grain segmentation, which I open-sourced on GitHub. During industry internships at Occidental and Civitas Resources, I developed Python ETL (Extract, Transform, Load) pipelines to integrate heterogeneous geoscience datasets and created Spotfire analytics tools that informed well placement, well spacing and completion design decisions.

What sets me apart is my ability to combine quantitative rigor with domain expertise. I understand the geology behind the data, which helps me build models that are not just statistically sound but scientifically meaningful. I'm drawn to roles where I can apply transferable data science skills to high-impact problems in exploration, climate, or environmental science.

I welcome collaboration and discussion. Feel free to reach out.