Interpretable machine learning for materials discovery: Predicting CO2 adsorption properties of metal–organic frameworks

Yukun Teng, Guangcun Shan

APL Materials 2024 article cited by 28

Source Open-access PDF More in Engineering & Materials

importance 6/10 ai assisted Machine Learning in Materials Science carbon capture stage: research

Problem

Screening millions of hypothetical metal–organic frameworks to find ones with high CO2 adsorption capacity is computationally expensive.

Why it matters

Identifying high-capacity CO2 adsorbents is key to carbon capture at industrial scale.

What the AI did

Machine learning combined with molecular simulations was trained on a hypothetical MOF dataset using 23 structural and 765 calculated features to predict CO2 adsorption at different pressures, with feature-importance ranking for interpretability.

Results

Calculated features improved ML prediction accuracy by 15%–20%; pore size and molecular structure ranked most critical at all pressures.

Impact

Enables faster ML-guided screening of millions of MOF structures for CO2 capture candidates.

Record

Venue	APL Materials
Published	2024
Work type	article
Authors	Yukun Teng, Guangcun Shan
Citations	28 (OpenAlex, at import time)
References	53
Model or method	not stated in source
Organization	not stated in source
Primary source	https://doi.org/10.1063/5.0222154
Open access	gold
Keywords	metal-organic frameworks, CO2 adsorption, machine learning, interpretability, materials discovery

Importance rating

6 / 10

significant — thousands to millions affected

ML-guided screening of millions of MOFs for high-capacity CO2 adsorbents supports carbon capture at industrial scale; 15-20% accuracy gain and interpretable features, but impact on capture deployment not yet shown.

Basis: inferred. Judged from the source text, which gives no explicit scale. Stated scale: millions of MOF structures screened. Method and limits.

More in Engineering & Materials

#	Paper	Year	Citations	Importance
1	Scaling deep learning for materials discovery Amil Merchant, Simon Batzner, Samuel S. Schoenholz, Muratahan Aykol, G...	2023	1,471	8
2	Application of Machine Learning in Material Synthesis and Property Prediction Guannan Huang, Yani Guo, Ye Chen, Zhengwei Nie	2023	165	7
3	Machine learning-guided discovery of ionic polymer electrolytes for lithium metal batteries Kai Li, Jifeng Wang, Yuanyuan Song, Ying Wang	2023	115	7
4	Machine Learning for Structural Health Monitoring of Aerospace Structures: A Review Gennaro Scarselli, Francesco Nicassio	2025	44	7
5	Power System Transient Stability Assessment Based on Machine Learning Algorithms and Grid Topology Mihail D. Senyuk, Murodbek Safaraliev, Firuz Kamalov, Hana Sulieman	2023	42	7