Data Science for Chemical and Materials Engineers. 3 credits, 3 contact hours

Catalog description

Prerequisites: BS degree in Chemical, Mechanical, Electrical or Biomedical Engineering, or in Physics or Chemistry. This is a course for graduate level students in chemical engineering, materials engineering, pharmaceutical engineering, or a related discipline. The focus is on the use of data science techniques to solve problems in chemical engineering. We will first discuss the Python programming language and how it can be used to manipulate, clean, explore, and visualize scientific datasets using the pandas package. We will the cover statistics and probability as it applies to engineering problems; this includes conditional probability, probability distributions, hypothesis testing, and Bayesian inference. Basic supervised machine learning models will be introduced, including linear and logistic regression, decision trees and random forest, and support vector machines. Students will then learn different analytical techniques and how to combine all of these skills to solve engineering problems involving large amounts of data and make predictions. Finally, we will cover how to access data and create your own datasets; topics include databases (including relational databases such as SQL) and basic data mining and web scraping. Applications of these methods will be demonstrated in chemical engineering (e.g., optimization and controls, sensor analysis), materials engineering (e.g., structural databases and property selection), and pharmaceutical engineering (e.g., drug selection). Students will gain hands-on experience in implementing and utilizing these various methods through computational laboratory assignments and reports and a semester-long engineering design project.