I'm interested in the ways that data science and machine learning can be used to make the world safer and cleaner. At the moment, I'm especially interested in how these principles can be applied to the rapidly growing offshore wind industry. Offshore windfarms produce terabytes of data each year and there are many open questions concering how we can use this data to best predict and avoid dangerous catastrophic failures and keep wind energy production as a viable clean energy source.

I approach these questions from a Bayesian perspective and am currently exploring how tools such as factored and heierarchical hidden Markov models can be used to monitor the health of offshore turbines. I like to collaboarte with engineers to use a combination of physics based and machine learning models.

Stay tuned for updates on projects related to ML and offshore wind.

Expository Notes

Here are some expository notes I've written on topics related to hidden Markov modeling:

• Inference and imputation for hidden Markov models with hybrid state outputs