Seminar & Colloquium
[세미나: 3월 22일(금), 오후 2시] Ph.D. Hyunsoo Park, Imperial College London
Title
Application of Machine Learning in Metal-Organic Frameworks
Speaker
Ph.D. Hyunsoo Park, Imperial College London
* Education
- 2020. 3. ~ 2023. 8. Ph.D., Department of Chemical and Biomolecular Engineering, KAIST
- 2018. 3. ~ 2020. 2. M.S., Department of Chemical and Biomolecular Engineering, KAIST
- 2011. 3. ~ 2017. 8. B.S., Department of Energy and Chemical Engineering, UNIST
* Experience
- 2023. 9. ~ current Research Associate, Imperial College London
- 2022. 5. ~ 2022. 1. Visiting doctoral student, EPFL
| Date | Friday March 22nd , 2024
| Time | 14:00 ~
| Venue | 33동 331호
[Abstract]
Metal-Organic Frameworks (MOFs), which are a class of crystalline nano-porous materials, have received a great amount of attention in recent years for their wide applications such as energy storage, gas separation and storage, catalysis, sensor, etc. This is due to their excellent properties such as large surface area, high chemical/thermal stability, and tunability. These materials are composed of tunable molecular building blocks through covalent bonds or metal ions (or clusters) via coordination interaction. They can, in principle, be synthesized in an infinite number of combinations. Recently, machine learning has seen rapid development in a wide range of applications, in particular, language and vision. Concurrently, a considerable amount of research has been conducted on the application of machine learning in the field of crystalline porous materials. In particular, identifying structure-property relationships and inverse design via machine leaning has the potential to accelerate the discovery of optimal materials with desired property when exploring the vast chemical space of porous materials. This presentation will discuss about developing machine learning models predicting various properties of porous materials such as synthesizability, gas uptake, diffusivity, and band gap and inverse design of MOFs with desired properties using reinforcement learning.
First, a positive-unlabeled learning algorithm was developed to predict synthesizability of MOFs given synthesis conditions as inputs. To this end, synthesis conditions of MOFs were collected from scientific literature using the developed text-mining code. The algorithm successfully predicted successful synthesis in 83.1 % of the synthesized data in the test set. Second, a Transformer architecture, which has been considered the dominating neural network architecture in language models, was introduced for universal transfer learning in MOFs which enables transfer learning across various properties of MOFs. That is, MOFTransformer which is a multi-modal Transformer encoder pre-trained with 1 millon hypothetical MOFs was developed. This multi-modal model utilizes integrated atom-based graph and energy-grid embeddings to capture both local and global features of MOFs, respectively. By fine-tuning the pre-trained, it achieves state-of-the-art results for predicting across various properties. Third, a reinforcement learning framework was developed for inverse design of MOFs with desired properties, our motivation being designing promising materials for the important environmental application of direct air capture of CO2 (DAC). We demonstrate that the reinforcement learning framework can successfully design MOFs with critical characteristics important for DAC.
These approaches present a new pathway for understanding the underlying relationships between various classes of porous materials, paving the way toward a more comprehensive understanding and design of porous materials.
| Host | 한승우 교수(02-880-1541)