Architecting Metal–Organic Frameworks at Molecular Level toward Direct Air Capture

Journal of the American Chemical Society, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 7, 2025

Escalating carbon dioxide (CO2) emissions have intensified the greenhouse effect, posing a significant long-term threat to environmental sustainability. Direct air capture (DAC) has emerged as promising approach achieving net-zero future, which offers several practical advantages, such independence from specific CO2 emission sources, economic feasibility, flexible deployment, and minimal risk of leakage. The design optimization DAC sorbents are crucial for accelerating industrial adoption. Metal-organic frameworks (MOFs), with high structural order tunable pore sizes, present an ideal solution strong guest-host interactions under trace conditions. This perspective highlights recent advancements in using MOFs DAC, examines molecular-level effects water vapor on capture, reviews data-driven computational screening methods develop molecularly programmable MOF platform identifying optimal sorbents, discusses scale-up cost DAC.

Language: Английский

---

Rise of machine learning potentials in heterogeneous catalysis: Developments, applications, and prospects

Chemical Engineering Journal, Journal Year: 2024, Volume and Issue: 494, P. 152757 - 152757

Published: June 2, 2024

Language: Английский

---

Metal–Organic Framework Stability in Water and Harsh Environments from Data-Driven Models Trained on the Diverse WS24 Data Set

Journal of the American Chemical Society, Journal Year: 2024, Volume and Issue: 146(29), P. 20333 - 20348

Published: July 10, 2024

Metal-organic frameworks (MOFs) are porous materials with applications in gas separations and catalysis, but a lack of water stability often limits their practical use given the ubiquity water. Consequently, it is useful to predict whether MOF water-stable before investing time resources into synthesis. Existing heuristics for designing MOFs generality limit diversity explored chemistry due narrowly defined criteria. Machine learning (ML) models offer promise improve predictions require data. In an improvement on previous efforts, we enlarge available training data prediction by over 400%, adding 911 labels assigned through semiautomated manuscript analysis curate new set WS24. The additional shown ML model performance (test ROC-AUC > 0.8) diverse both harsher acidic conditions. We illustrate how expanded can be used previously developed activation combination genetic algorithms quickly screen ∼10,000 from space hundreds thousands candidates multivariate (upon activation, water, acid). uncover metal- geometry-specific design rules robust MOFs. this work, which disseminate easy-to-use web interface, expected contribute toward accelerated discovery novel, such as direct air capture treatment.

Language: Английский

---

Machine learning for the advancement of membrane science and technology: A critical review

Journal of Membrane Science, Journal Year: 2024, Volume and Issue: 713, P. 123256 - 123256

Published: Sept. 3, 2024

Machine learning (ML) has been rapidly transforming the landscape of natural sciences and potential to revolutionize process data analysis hypothesis formulation as well expand scientific knowledge. ML particularly instrumental in advancement cheminformatics materials science, including membrane technology. In this review, we analyze current state-of-the-art membrane-related applications from perspectives. We first discuss foundations different algorithms design choices. Then, traditional deep methods, application examples literature, are reported. also importance both molecular membrane-system featurization. Moreover, follow up on discussion with science detail literature using data-driven methods property prediction fabrication. Various fields discussed, such reverse osmosis, gas separation, nanofiltration. differentiate between downstream predictive tasks generative design. Additionally, formulate best practices minimum requirements for reporting reproducible studies field membranes. This is systematic comprehensive review science.

Language: Английский

---

From Data to Discovery: Recent Trends of Machine Learning in Metal–Organic Frameworks

JACS Au, Journal Year: 2024, Volume and Issue: 4(10), P. 3727 - 3743

Published: Sept. 12, 2024

Renowned for their high porosity and structural diversity, metal-organic frameworks (MOFs) are a promising class of materials wide range applications. In recent decades, with the development large-scale databases, MOF community has witnessed innovations brought by data-driven machine learning methods, which have enabled deeper understanding chemical nature MOFs led to novel structures. Notably, is continuously rapidly advancing as new methodologies, architectures, data representations actively being investigated, implementation in discovery vigorously pursued. Under these circumstances, it important closely monitor research trends identify technologies that introduced. this Perspective, we focus on emerging within field MOFs, challenges they face, future directions development.

Language: Английский

---

Assessing Exchange-Correlation Functionals for Heterogeneous Catalysis of Nitrogen Species

The Journal of Physical Chemistry C, Journal Year: 2024, Volume and Issue: 128(27), P. 11159 - 11175

Published: July 1, 2024

Increasing interest in the sustainable synthesis of ammonia, nitrates, and urea has led to an increase studies catalytic conversion between nitrogen-containing compounds using heterogeneous catalysts. Density functional theory (DFT) is commonly employed obtain molecular-scale insight into these reactions, but there have been relatively few assessments exchange-correlation functionals that are best suited for catalysis nitrogen compounds. Here, we assess a range ranging from generalized gradient approximation (GGA) random phase (RPA) formation energies gas-phase species, lattice constants representative solids several common classes catalysts (metals, oxides, metal-organic frameworks (MOFs)), adsorption intermediates on materials. The results reveal choice van der Waals correction can surprisingly large effect increasing level does not always improve accuracy This suggests selection should be carefully evaluated basis specific reaction material being studied.

Language: Английский

---

High‐Throughput Computational Screening‐Driven Porous Material Discovery for Benchmark Propylene/Propane Separation

Advanced Functional Materials, Journal Year: 2024, Volume and Issue: unknown

Published: Oct. 4, 2024

Abstract Separating propylene (C 3 H 6 ) from propylene/propane /C 8 mixture using energy‐efficient adsorption is industrially important, but due to the lack of universal pore features, rational selection a suitable adsorbent in ocean porous materials tough task. In this study, comprehensive work on discovery high‐performance C separation adsorbents carried out by utilizing advantages high‐throughput computational screening (HTCS). First, based HTCS data mining CoRE MOF 2019 and Tobacco 3.0 database, target material, Cd‐HFDPA, screened out. Second, electrostatic potential (ESP) analysis shows that Cd‐HFDPA has obvious characteristics high affinity for according ESP matching, which further confirmed isotherms, Ideal Adsorbed Solution Theory selectivity, enthalpy analyses, breakthrough experiments. Finally, an industrial two‐bed pressure swing process proposed its productivity energy consumption are compared with other benchmark materials.

Language: Английский

---

A physics-informed cluster graph neural network enables generalizable and interpretable prediction for material discovery

Research Square (Research Square), Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 6, 2025

Machine learning (ML) plays a pivotal role in the development of functional materials, which graph neural networks (GNNs) have shown improved performance by utilizing representation atoms and bonds to effectively characterize materials. However, it remains challenging achieve efficient, robust interpretable predictions due limited integration domain knowledge. In this study, we propose leveraging local structure short-range atomic interactions materials using cluster improve performance. This physics-informed network (CG-NET) significantly enhances computational efficiency through sampling strategy. Importantly, incorporating pseudo nodes as neighbors at boundaries, maintain bonding coordination environment, enhancing prediction accuracy. We further demonstrate CG-NET’s remarkable accuracy across diverse material systems properties reveal its superior interpretability generalizability with extensive experiments. Our work highlights importance integrating domain-specific scientific knowledge into design generalizable ML framework. The CG-NET could be extended other graph-based accelerate while reducing cost.

Language: Английский

---

Data-Driven Prediction of Structures of Metal–Organic Frameworks

Journal of Chemical Information and Modeling, Journal Year: 2025, Volume and Issue: unknown

Published: Feb. 10, 2025

Crystal structure prediction (CSP) has proven to be an effective route for the discovery of new materials. Nonetheless, ab initio techniques employed CSP metal-organic frameworks (MOFs) cannot scaled a high-throughput mode. Here, we propose data-driven method addressing current needs computational MOF discovery. Specifically, coarse-grained neural networks were implemented predict underlying net topology. The models showed satisfactory performance, which was next enhanced via limitation applicability domain.

Language: Английский

---

Applied Artificial Intelligence in Materials Science and Material Design

Advanced Intelligent Systems, Journal Year: 2025, Volume and Issue: unknown

Published: March 2, 2025

Materials science has traditionally relied on a combination of experimental techniques and theoretical modeling to discover develop new materials with desired properties. However, these processes can be time‐consuming, resource‐intensive, often limited by the complexity material systems. The advent artificial intelligence (AI), particularly machine learning, revolutionized offering powerful tools accelerate discovery, design, characterization novel materials. AI not only enhances predictive properties but also streamlines data analysis in like X‐Ray diffraction, Raman spectroscopy, scanning probe microscopy, electron microscopy. By leveraging large datasets, algorithms identify patterns, reduce noise, predict behavior unprecedented accuracy. In this review, recent advancements applications across various domains science, including synchrotron studies, microscopies, metamaterials, atomistic modeling, molecular drug are highlighted. It is discussed how AI‐driven methods reshaping field, making discovery more efficient, paving way for breakthroughs design real‐time analysis.

Language: Английский

---