• Advisors: Dr. Ben Schenkel (CIWRO/NSSL) and Dr. Thomas Galarneau (NSSL)
• Developing a radar-based hail climatology for the contiguous United States using machine learning

• Developed a probabilistic ML, radar-based hail size classification algorithm, utilizing C++ and Python.
• Contributed to the development of a large dataset of storm characteristics via radar analysis, aiding CIWRO and NOAA NSSL researchers in developing an ML algorithm for tornado prediction.
• Participated in the PERiLS, DELTA, and HAILSTONE research field campaigns with the NOAA X-POL (NOXP) mobile radar team, mobile mesonet probe team, and hail imaging probe team respectively.
• Supported several NOAA Hazardous Weather Testbed (HWT) experiments as both a participant [Spring Forecasting Experiment (SFE) x2] and assistant [Probabilistic Hazard Information (PHI) Prototype Experiment; Radar Convective Applications (RCA) Experiment], evaluating experimental products and forecasting techniques alongside federal research partners and facilitating the assessment of warning guidance tools for severe convective hazards as one of the only undergraduates involved.

• Evaluated the utility of hourly mesoscale analysis products used by forecasters as guidance for short-term predictions of severe convective hazards across the nation.
• Completed research project on the evaluation of diagnostic composite indices and environmental parameters for conditional hail size classification from the SPC’s real-time RAP-based gridded surface objective analysis (SFCOA) scheme.
• Developed a probabilistic tree-based machine learning (ML) algorithm for conditional hail size classification using environmental parameters from SFCOA.
• Manipulated and analyzed large gridded datasets, including GEMPAK-based SFCOA, RAP, MRMS MESH, Storm Data reports, and netCDF-based environment data, using Python.
• Shadowed SPC forecasters during active shifts, gaining insights into the operational decision-making process and R2O opportunities.

• Performed case studies for severe convective storm (SCS) perils using Python, R, and SQL in understanding atmospheric and policy characteristics influencing loss from claims.
• Analyzed SCS peril trends with Power BI to understand potential loss exposure in portfolio.
• Created Python GUI application used by employees to automate and streamline SQL workflows.

• Minor: Mathematics
• GPA: 3.98/4
• Related coursework: calculus, differential equations, statistics, chemistry, physics, programming, machine learning, and communication.

.

Personal weather forecasting website maintained in high school.