Recent advances in catalyst design, performance, and challenges of metal-heteroatom-co-doped biochar as peroxymonosulfate activator for environmental remediation

Environmental Research, Journal Year: 2024, Volume and Issue: 252, P. 118919 - 118919

Published: April 16, 2024

Language: Английский

---

Advancing electrocatalytic reactions through mapping key intermediates to active sites via descriptors

Chemical Society Reviews, Journal Year: 2024, Volume and Issue: 53(14), P. 7392 - 7425

Published: Jan. 1, 2024

Descriptors play a crucial role in electrocatalysis as they can provide valuable insights into the electrochemical performance of energy conversion and storage processes. They allow for understanding different catalytic activities enable prediction better catalysts without relying on time-consuming trial-and-error approaches. Hence, this comprehensive review focuses highlighting significant advancements commonly used descriptors critical electrocatalytic reactions. First, fundamental reaction processes key intermediates involved several reactions are summarized. Subsequently, three types classified introduced based catalysts. These include d-band center descriptors, readily accessible intrinsic property spin-related all which contribute to profound behavior. Furthermore, multi-type that collectively determine also Finally, we discuss future envisioning their potential integrate multiple factors, broaden application scopes, synergize with artificial intelligence more efficient catalyst design discovery.

Language: Английский

---

Automatic feature engineering for catalyst design using small data without prior knowledge of target catalysis

Communications Chemistry, Journal Year: 2024, Volume and Issue: 7(1)

Published: Jan. 12, 2024

The empirical aspect of descriptor design in catalyst informatics, particularly when confronted with limited data, necessitates adequate prior knowledge for delving into unknown territories, thus presenting a logical contradiction. This study introduces technique automatic feature engineering (AFE) that works on small datasets, without reliance specific assumptions or pre-existing about the target catalysis designing descriptors and building machine-learning models. generates numerous features through mathematical operations general physicochemical catalytic components extracts relevant desired catalysis, essentially screening hypotheses machine. AFE yields reasonable regression results three types heterogeneous catalysis: oxidative coupling methane (OCM), conversion ethanol to butadiene, three-way where only training set is swapped. Moreover, application active learning combines high-throughput experimentation OCM, we successfully visualize machine's process acquiring precise recognition design. Thus, versatile data-driven research key step towards fully automated discoveries.

Language: Английский

---

A machine learning framework for accelerating the development of highly efficient methanol synthesis catalysts

Journal of Energy Chemistry, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Language: Английский

---

Interpretable machine learning framework for catalyst performance prediction and validation with dry reforming of methane

Applied Catalysis B Environment and Energy, Journal Year: 2023, Volume and Issue: 343, P. 123454 - 123454

Published: Nov. 9, 2023

Conventional methods for developing heterogeneous catalysts are inefficient in time and cost, often relying on trial-and-error. The integration of machine-learning (ML) catalysis research using data can reduce computational costs provide valuable insights. However, the lack interpretability black-box models hinders their acceptance among researchers. We propose an interpretable ML framework that enables a comprehensive understanding complex relationships between variables. Our incorporates tools such as Shapley additive explanations partial dependence values effective preprocessing result analysis. This increases prediction accuracy model with improved R2 value 0.96, while simultaneously expanding catalyst component variety. Furthermore, case dry reforming methane, we tested validity recommendation through dedicated experimental tests. outstanding performance has potential to expedite rational design catalysts.

Language: Английский

---

Catalysis in the digital age: Unlocking the power of data with machine learning

Wiley Interdisciplinary Reviews Computational Molecular Science, Journal Year: 2024, Volume and Issue: 14(5)

Published: Sept. 1, 2024

Abstract The design and discovery of new improved catalysts are driving forces for accelerating scientific technological innovations in the fields energy conversion, environmental remediation, chemical industry. Recently, use machine learning (ML) combination with experimental and/or theoretical data has emerged as a powerful tool identifying optimal various applications. This review focuses on how ML algorithms can be used computational catalysis materials science to gain deeper understanding relationships between properties their stability, activity, selectivity. development repositories, mining techniques, tools that navigate structural optimization problems highlighted, leading highly efficient sustainable future. Several data‐driven models commonly research diverse applications reaction prediction discussed. key challenges limitations using presented, which arise from catalyst's intrinsic complex nature. Finally, we conclude by summarizing potential future directions area ML‐guided catalyst development. article is categorized under: Structure Mechanism > Reaction Mechanisms Catalysis Data Science Artificial Intelligence/Machine Learning Electronic Theory Density Functional

Language: Английский

---

An auto-configurable and interpretable ensemble learning framework for optimal catalyst design of green methanol production via Bayesian optimization

Journal of Cleaner Production, Journal Year: 2025, Volume and Issue: 488, P. 144666 - 144666

Published: Jan. 1, 2025

Language: Английский

---

Achieving Digital Catalysis: Strategies for Data Acquisition, Storage and Use

Angewandte Chemie International Edition, Journal Year: 2023, Volume and Issue: 62(30)

Published: May 31, 2023

Heterogeneous catalysis is an important area of research that generates data as intricate the phenomenon itself. Complexity inherently coupled to function catalyst and advance in knowledge can only be achieved if this complexity adequately captured accounted for. This requires integration experiment theory, high quality control, close interdisciplinary collaboration, sharing metadata, which facilitated by application joint management strategies. Viewpoint Article first discusses potential a digital transition research. Then, summary current status terms infrastructure heterogeneous presented, defining various types (meta-) data, from synthesis functional analysis. Finally, already implemented working concept for local acquisition storage introduced benefits further development directions use are discussed.

Language: Английский

---

A mini review on the applications of artificial intelligence (AI) in surface chemistry and catalysis

Tenside Surfactants Detergents, Journal Year: 2024, Volume and Issue: 61(4), P. 285 - 296

Published: April 29, 2024

Abstract This review critically analyzes the incorporation of artificial intelligence (AI) in surface chemistry and catalysis to emphasize revolutionary impact AI techniques this field. The current examines various studies that using techniques, including machine learning (ML), deep (DL), neural networks (NNs), catalysis. It reviews literature on application models predicting adsorption behaviours, analyzing spectroscopic data, improving catalyst screening processes. combines both theoretical empirical provide a comprehensive synthesis findings. demonstrates applications have made remarkable progress properties nanostructured catalysts, discovering new materials for energy conversion, developing efficient bimetallic catalysts CO 2 reduction. AI-based analyses, particularly advanced NNs, provided significant insights into mechanisms dynamics catalytic reactions. will be shown plays crucial role by significantly accelerating discovery enhancing process optimization, resulting enhanced efficiency selectivity. mini-review highlights challenges data quality, model interpretability, scalability, ethical, environmental concerns AI-driven research. importance continued methodological advancements responsible implementation

Language: Английский

---

Hybrid Quantum Neural Network Model with Catalyst Experimental Validation: Application for the Dry Reforming of Methane

ACS Sustainable Chemistry & Engineering, Journal Year: 2024, Volume and Issue: 12(10), P. 4121 - 4131

Published: Feb. 23, 2024

Machine learning (ML), which has been increasingly applied to complex problems such as catalyst development, encounters challenges in data collection and structuring. Quantum neural networks (QNNs) outperform classical ML models, artificial (ANNs), prediction accuracy, even with limited data. However, QNNs have available qubits. To address this issue, we introduce a hybrid QNN model, combining parametrized quantum circuit an ANN structure. We used the sets of dry reforming methane reaction from literature in-house experimental results compare models. The exhibited superior accuracy faster convergence rate, achieving R2 0.942 at 2478 epochs, whereas achieved 0.935 3175 epochs. For 224 points previously unreported literature, enhanced generalization performance. It showed mean absolute error (MAE) 13.42, compared MAE 27.40 for under similar training conditions. This study highlights potential powerful tool solving catalysis chemistry, demonstrating its advantages over

Language: Английский

---