I'm Muthukrishnan, a Chemical Engineer with 5 years of experience in the energy industry. Welcome to my GitHub profile!

I spent five years in upstream oil & gas, working on process safety and exception-based surveillance for ExxonMobil assets. I'm now a graduate researcher at the University of Alberta, in the Laboratory for Advanced Separation Processes, working on adsorption-based carbon capture.

The way I learn a method is to implement it. The models I work with are published ones — column dynamics, IAST, extended Langmuir, LDF mass transfer, NSGA-II — so the theory isn't mine. What I do is build it, check it against the data in the papers, and make it something you can open and use.

A desktop app that simulates two-component, non-isothermal breakthrough in a packed column. Eleven published isotherm models, IAST or extended-Langmuir mixture equilibrium, five mass-transfer resistance models, solved with SUNDIALS CVODE.

Each preset says which paper its parameters came from, and the default case is checked against a measured breakthrough run. It runs entirely on your own machine — no account, no installer, no telemetry.

• Download for Windows or Linux
• Documentation
• Source and release notes

Smaller tools, each built to understand something properly. They run in your browser — nothing to install.

• Isotherm & IAST Explorer — fit twelve isotherm models, predict binary competitive adsorption via IAST, look at selectivity
• Paper Visualizer — a paper on CSS convergence, broken into its idea flow, mathematics and findings
• NSGA-II Optimization Reference — what I worked out while learning multi-objective optimisation with pymoo, applied to a capture cycle

👉 Open the apps

For the longer version — research, professional experience, and how to reach me:

👉 Visit my portfolio

• Python — NumPy, SciPy, SUNDIALS/CVODE, pandas, matplotlib, seaborn, plotly, bokeh, pymoo , scikit-learn
• MATLAB
• JMP
• HTML/CSS/JS

I'm an enthusiast here rather than a practitioner. I'm curious about what technical challenges could be solved by use of ML.

If you're starting out too, these are worth your time, in this order:

1. An Introduction to Statistical Learning — James, Witten, Hastie & Tibshirani. Free, and it makes everything after it easier.
2. Deep Learning with Python, 2nd ed. — François Chollet (Manning, 2021). Written by the author of Keras.
3. The Idiomatic Programmer — Learning Keras — a free handbook, for when you want to build something.

Feel free to reach out on LinkedIn or at contactmuthu@duck.com. Always happy to talk adsorption, carbon capture, or moving something out of a spreadsheet. Let's connect!

Thank you for visiting my GitHub profile! 🙏 Feel free to reach out if you have any questions or want to collaborate! 😊