Intro to Scientific Machine Learning, Summer 2022

As part of a graduate course, I was introduced to various scientific machine learning methods. Some of the highlights of the course are shown below. The Jupter notebooks can be accessed on my github:

Analyzing Uber Pickup Data using K-means Clustering

Using open source data from Kaggle, new york pickups were split into subregions to be further optimized.

Counting Celestial Objects

By applying gaussian mixture, and then applying bayesian information criterion to identify the number of components, stars and celestial objects were observed in pictures from the hubble space telescope.

Guassian Process

Using gaussian process CO2 levels in Hawaii sourced from the National Oceanic and Atmospheric Administration (NOAA) were mapped.