Researcher, builder, and persistent question-asker.

Why this work

I’m drawn to problems where the data is messy, the stakes are real, and a technically impressive result is not enough on its own. Weather prediction is exactly that kind of problem.

My research explores how artificial intelligence and machine learning can assist forecasting. I care about building systems that are reproducible, evaluating them honestly, and translating the results into something another researcher—or eventually a forecaster—can use.

How I like to work

I tend to move between research questions and the infrastructure needed to answer them: data pipelines, long-running experiments, evaluation tools, and the small pieces of automation that make the next iteration better than the last.

This site is a place to share that work as it develops, without pretending unfinished work is finished.