Syllabus

Syllabus#

06-642: Data Science and Machine Learning in Chemical Engineering

Spring 2026 · Half Semester · Carnegie Mellon University

Instructor#

Professor John Kitchin
Department of Chemical Engineering
jkitchin@cmu.edu

Course Description#

This course introduces data science and machine learning techniques with applications to chemical engineering problems. We emphasize practical implementation in Python, focusing on tools and methods that are directly applicable to research and industrial practice.

Topics include:

  • Data manipulation with NumPy and Pandas

  • Regression and classification with scikit-learn

  • Dimensionality reduction and clustering

  • Ensemble methods (Random Forests, Gradient Boosting)

  • Uncertainty quantification

  • Model interpretability

Learning Objectives#

By the end of this course, students will be able to:

  1. Load, clean, and manipulate data using Pandas

  2. Visualize data effectively using Matplotlib

  3. Build and evaluate regression models

  4. Apply cross-validation and regularization to prevent overfitting

  5. Use ensemble methods for improved predictions

  6. Perform clustering and dimensionality reduction on complex datasets

  7. Quantify uncertainty in model predictions

  8. Interpret machine learning models to extract scientific insights

Schedule#

Week

Lectures

Topics

1

00, 01

Introduction, NumPy

2

02, 03

Pandas Intro, Intermediate Pandas

3

04, 05

Dimensionality Reduction, Linear Regression

4

06, 07

Regularization, Nonlinear Methods

5

08, 09

Ensemble Methods, Clustering

6

10, 11

Uncertainty Quantification, Interpretability

7

—

Project work

Grading#

Component

Weight

Assignments (12)

30%

Participation

20%

Project

50%

Late policy#

Assignments will be accepted up to three days after the due date. After that a grade of 0 will be assigned. Exceptions to this must be requested and approved in advance of the assignment deadline.

Assignments#

There is one assignment per lecture module.

Project#

The project is an opportunity to apply course techniques to a problem of your choice. Projects should:

  • Address a real chemical engineering or scientific problem

  • Include proper validation and uncertainty quantification

  • Be presented in a well-documented notebook

Grade Scale#

Grade

Percentage

A

≥ 95%

A-

90-94%

B+

83-89%

B

76–82%

B-

70-76%

C+

60-69%

C

50–59%

R

< 50%

Required Software#

  • Python 3.10+

  • Jupyter Notebook or JupyterLab

  • Required packages: numpy, pandas, matplotlib, scikit-learn, pycse, shap, xgboost

See the Introduction lecture for installation instructions.

Academic Integrity#

You are encouraged to discuss concepts with classmates, but all submitted work must be your own. Code copied from external sources must be cited. Using AI assistants (e.g., ChatGPT, Claude) is permitted for learning and debugging, but you must understand and be able to explain all code you submit.

Accommodations#

If you have a disability and require accommodations, please contact the Office of Disability Resources as soon as possible.

Getting Help#

  • Office hours: TBD

Contents