Exploring Materials Synthesis Conditions via Large Language Model
Are you interested in leveraging the computational power to reveal the secret of materials synthesis? Join us to learn the state-of-the-art data analysis techniques and large language models!
Project description
Metal-organic frameworks (MOFs) are a novel class of nanoporous materials that have attracted significant attention due to their facile tunability in structure and chemistry. MOFs have already been widely explored and show promise in addressing global challenges such as slowing down climate change, curing diseases, and improving energy efficiency. While MOFs can be easily constructed in silico by combining different metal nodes and organic linkers, the synthesis of novel MOFs has been a major challenge. The choice of synthesis conditions has largely relied on experimentalists’ intuition so far, thus slowing materials discovery.
In this project, the student will develop advanced natural language processing tools, such as those based on state-of-the-art large language models (LLMs), to reveal the secret of MOF synthesis by analyzing a large amount of literatures. This is a chance to learn how to use latest AI and machine learning to help solve outstanding challenges in science and engineering.
Join our team and let’s help accelerate the new materials synthesis and production to save the planet!
Project outcome
The student will gain valuable skills and knowledge in computer science, machine learning, and large language models, in the context of nanoporous materials and chemical engineering. They will also develop strong communication skills through presentations in group meetings and one-on-one meetings with the advisor. If the project is successful, the student will have the chance to publish their research outcome in professional journals and present their work at local symposiums or national conferences. The student will have the chance to collaborate with top-notch experimental researchers from UB and other universities to solve challenging real-world problems.
Project details
| Length of commitment | Longer than a semester; 6-9 months |
| Start time | Anytime |
| In-person, remote, or hybrid? | Hybrid Project |
| Level of collaboration | Individual student project |
| Benefits | Academic credit |
| Who is eligible | All undergraduate students who have experience in basic coding (e.g., Python) skills. Students showing a strong interest in machine learning, large language models, and computational chemical science are preferred. |
Project mentor
Kaihang Shi
Assistant Professor
Department of Chemical and Biological Engineering
Phone: (716) 645-2615
Email: kaihangs@buffalo.edu
Start the project
- Email the project mentor using the contact information above to express your interest and get approval to work on the project. (Here are helpful tips on how to contact a project mentor.)
- After you receive approval from the mentor to start this project, click the button to start the digital badge. (Learn more about ELN's digital badge options.)
Preparation activities
Once you begin the digital badge series, you will have access to all the necessary activities and instructions. Your mentor has indicated they would like you to also complete the specific preparation activities below. Please reference this when you get to Step 2 of the Preparation Phase.
If the student has no previous experience with Python, they should also be familiar with the basics of Python coding. The student should also learn basics about large language model (e.g., GPT4), how it works, and what models are currently available.
The student should also learn basics about metal-organic framework.
Keywords
Computer Science and Engineering, Chemical and Biological Engineering, Department of Materials Design and Innovation, machine learning, large language model, LLM, ChatGPT, GPT