This is the repository of Module 7- Testing the viability of carbon capture with AI of the CEAD 2024 | Reduction of carbon footprint in industry and beyond.
This repository contains the exercise data, assignment and auxiliary functions created for this course. Two exercises are available; they have the same aim but cover different cases: the first refers to the high gas flow rate case, and the second to the low gas flow rate case. At the end of the course, an extensive solution to the exercise will be updated as well.

• Assignment_Group1.pdf: The assignment to be completed by the 1^st group.
• experimental_dataset_1.csv: The data for the model training in assignment 1.
• Assignment_Group2.pdf: The assignment to be completed by the 2^nd group.
• experimental_dataset_2.csv: The data for the model training in assignment 2.
• utils.py: Python file containing all the auxiliary functions used during the exercise.

This repository is open to contribution. If you want to contribute, create a new pull request or open a new issue using the tools available on GitHub.

This repository's data and code are only for didactical use. They were created in-silico without any lab experiments but report the actual trends between input and output. Therefore, we discourage their use for commercial or research purposes.

Prof. Leblebici talk: Can you take CO2 out of the athmosphere?
Use of monoethanolamine (MEA) for CO2 capture in a global scenario: Consequences and alternatives
Carbon dioxide capture using liquid absorption methods: a review
Artificial intelligence enabled carbon capture: A review

If you want more information about the exercise, don't hesitate to contact Ulderico Di Caprio or Prof. M.Enis Leblebici. Moreover, you can open an issue by asking your questions.