Design and prediction of metal organic framework-based mixed matrix membranes for CO2 capture via machine learning

Guan, Jian; Tan, Huachun; Liu, Wei; Feng, Fan; Japip, Susilo; Li, Jiali; Wu, Jing; Wang, Xiaonan; Zhang, Sui

doi:10.1016/j.xcrp.2022.100864

Cited by 52 publications

(34 citation statements)

References 46 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Despite that there are still many challenges, we believe that with the rapid development of materials science and reticular chemistry, an increasing number of MOF materials processing enhanced molecular recognition ability will be discovered and applied to efficient C 3 H 6 /C 3 H 8 separation. The recent empirical pieces of evidence also show that the combination of MOFs with other novel separation agents such as covalent organic frameworks may open another bright avenue to improve gas separation. , Moreover, the newly developed computational techniques like machine learning have exhibited great potential to facilitate the screening of MOF candidates and also guide materials’ synthesis. − On the basis of these considerations, it is convincing that MOFs may be implemented for the practical separation of C 3 H 6 and C 3 H 8 in the near future.…”

Section: Discussionmentioning

confidence: 99%

Recent Advances in the Development of Metal–Organic Frameworks for Propylene and Propane Separation

Ding

Zhang

2022

Energy Fuels

Self Cite

View full text Add to dashboard Cite

Separation of propylene (C3H6) and propane (C3H8) is a vital step for the manufacture of high-purity C3H6 as an important energy source and critical raw material in the petrochemical industry. Due to their similar sizes and properties, the separation of C3H6 and C3H6 is challenging and currently relies on energy-intensive cryogenic distillation. Metal–organic framework (MOF)-assisted adsorptive separation and membrane-based separation are revolutionary energy-saving technologies that can enable efficient gas purification under mild conditions. This review presents the current progress in C3H6/C3H8 separation achieved with MOFs and MOF-based membranes. The different separation mechanisms (including equilibrium separation, kinetic separation, gate-opening effect, molecular sieving, and combination of them) along with the materials design principles that contribute to benchmark C3H6/C3H8 separation are discussed. Diverse creative strategies for the fabrication of high-quality MOF membranes (both continuous membranes and mixed-matrix membranes) to surpass the tradeoff between selectivity and gas permeability are summarized. Lastly, this review also outlines the major challenges and opportunities of MOFs to be used for practical C3H6/C3H8 separation.

show abstract

Section: Discussionmentioning

confidence: 99%

Recent Advances in the Development of Metal–Organic Frameworks for Propylene and Propane Separation

Ding

Zhang

2022

Energy Fuels

Self Cite

View full text Add to dashboard Cite

show abstract

“…In this case, these external factors must be taken as necessary descriptors and participate in the model training process. By processing importance analysis, the model tells users whether these external factors play crucial or marginal roles in the CO 2 separation process (Guan et al, 2022). If a crucial role is identified, the specific effects of experimental conditions can be investigated in detail via ML-based approaches, and if a marginal role is found, the experimental conditions can be generally excluded in the subsequent prediction of CO 2 capture performances.…”

Section: Technical Backgroundsmentioning

confidence: 99%

“…Fighting against climate change, with emphasis on the over-accumulated issue of carbon dioxide (CO 2 ) in the air, is one of the most predominant challenges facing carbonintensive energy industries and the environmental community in the 21st century (Guan et al, 2022). Compared to preindustrial times before the 1750 s, the CO 2 concentration in the troposphere has increased from ~280 ppm to ~400 ppm, with an annual increase of approximately 1 ppm (Pera-Titus 2014; Oschatz and Antonietti 2018).…”

Section: Introductionmentioning

confidence: 99%

A critical review on machine-learning-assisted screening and design of effective sorbents for carbon dioxide (CO2) capture

et al. 2023

View full text Add to dashboard Cite

Effective carbon dioxide (CO2) capture plays indispensable roles in closing the global carbon cycle, serving the sustainable production of energy, and achieving the grand 1.5 °C goal by 2050. Considering the diversity and complexity of CO2 capture materials, machine learning has stepped into this field years ago and become a powerful tool that promotes the screening and design of involving parameters. From these perspectives, this critical review firstly summarizes the technical backgrounds for the applications of ML-based methods in CO2 capture. Then, through categorizing the materials into two major groups, that is, adsorbents (containing metal organic frameworks, carbonaceous materials, polymers, and zeolites) and absorbents (involving ionic liquids, amine-based absorbents, and deep eutectic solvents), the applications of this effective tool in relevant areas are scrutinized. The major concerns remain to be further addressed are derived based on the above discussions, namely 1) the development of consistent and integrated databases, 2) the wise digitalization of inherent properties of materials, and 3) the validation of the accuracy of ML-derived results under practical scenarios. The main purpose of this critical review is bridging the previous achievements and further developments of ML-assisted design of CO2 capture techniques.

show abstract

“…Machine learning (ML) is an emerging data-driven method that can predict nonlinear relationships, especially in systems with complex and unclear physical mechanisms. − It has been applied in the membrane fields for predicting the water permeability and salt pass rate of thin-film nanocomposite reverse osmosis membranes and the performances of polyelectrolyte membranes . More recently, it has been used to guide the design of novel membranes for nanofiltration and carbon capture. − However, most existing ML models are natively single-task models and are unable to learn the underlying correlations between output variables. Artificial neural network (ANN) is a promising class of algorithms that inherently support multitask regression problems .…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Guided Polyamide Membrane with Exceptional Solute–Solute Selectivity and Permeance

Deng

Luo

Imbrogno

et al. 2022

Environ. Sci. Technol.

Self Cite

View full text Add to dashboard Cite

Designing polymeric membranes with high solute−solute selectivity and permeance is important but technically challenging. Existing industrial interfacial polymerization (IP) process to fabricate polyamide-based polymeric membranes is largely empirical, which requires enormous trial-and-error experimentations to identify optimal fabrication conditions from a wide candidate space for separating a given solute pair. Herein, we developed a novel multitask machine learning (ML) model based on an artificial neural network (ANN) with skip connections and selectivity regularization to guide the design of polyamide membranes. We used limited sets of lab-collected data to obtain satisfactory model performance over four iterations by introducing human expert experience in the online learning process. Four membranes under fabrication conditions guided by the model exceeded the present upper bound for mono/divalent ion selectivity and permeance of the polymeric membranes. Moreover, we obtained new mechanistic insights into the membrane design through feature analysis of the model. Our work demonstrates a ML approach that represents a paradigm shift for high-performance polymeric membranes design.

show abstract

Design and prediction of metal organic framework-based mixed matrix membranes for CO2 capture via machine learning

Cited by 52 publications

References 46 publications

Recent Advances in the Development of Metal–Organic Frameworks for Propylene and Propane Separation

Recent Advances in the Development of Metal–Organic Frameworks for Propylene and Propane Separation

A critical review on machine-learning-assisted screening and design of effective sorbents for carbon dioxide (CO2) capture

Machine Learning Guided Polyamide Membrane with Exceptional Solute–Solute Selectivity and Permeance

Contact Info

Product

Resources

About