Related Experiment Video
Updated: Jan 2, 2026
11:27
Synthesis and Characterization of Functionalized Metal-organic Frameworks
Published on: September 5, 2014
49.0K
Machine Learning Enabled Tailor-Made Design of Application-Specific Metal-Organic Frameworks.
Xiangyu Zhang1, Kexin Zhang1, Yongjin Lee1
1School of Physical Science and Technology , ShanghaiTech University , Shanghai 201210 , China.
ACS Applied Materials & Interfaces
|December 11, 2019
Summary
This study introduces a novel computational approach for designing advanced nanoporous materials, specifically metal-organic frameworks (MOFs). This method efficiently creates custom MOFs for applications like methane storage and carbon capture.
Area of Science:
- Materials Science
- Computational Chemistry
- Nanotechnology
Background:
- Exploring the vast chemical space of nanoporous materials is a significant challenge.
- High-throughput screening methods face limitations due to costly simulations and the need for effective material descriptors.
Purpose of the Study:
- To develop a computational approach for the tailor-made design of metal-organic frameworks (MOFs).
- To overcome the limitations of traditional screening-based methods in materials discovery.
Main Methods:
- Combines Monte Carlo tree search (MCTS) with recurrent neural networks (RNNs).
- Focuses on a computational, rather than purely screening-based, approach to materials design.
Main Results:
- Demonstrated significant efficiency in designing novel MOFs for methane storage.
- Successfully designed promising MOFs for carbon capture applications.
Conclusions:
- The developed approach offers an efficient alternative to traditional screening for designing functional nanoporous materials.
- The methodology is adaptable to various applications by modifying the reward function for specific performance targets.
