Embracing data science in catalysis research

Nature Catalysis, Journal Year: 2024, Volume and Issue: 7(6), P. 624 - 635

Published: April 23, 2024

Language: Английский

---

Recent Advances in Coke Management for Dry Reforming of Methane over Ni-Based Catalysts

Catalysts, Journal Year: 2024, Volume and Issue: 14(3), P. 176 - 176

Published: March 1, 2024

The dry reforming of methane (DRM) is a promising method for controlling greenhouse gas emissions by converting CO2 and CH4 into syngas, mixture CO H2. Ni-based catalysts have been intensively investigated their use in the DRM. However, they are limited formation carbonaceous materials on surfaces. In this review, we explore carbon-induced catalyst deactivation mechanisms summarize recent research progress mitigating carbon deposition developing coke-resistant catalysts. This review emphasizes significance support, alloy, structural strategies, importance comprehending interactions between components to achieve improved catalytic performance stability.

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

---

Recent developments in the use of machine learning in catalysis: A broad perspective with applications in kinetics

Chemical Engineering Journal, Journal Year: 2025, Volume and Issue: unknown, P. 160872 - 160872

Published: Feb. 1, 2025

Language: Английский

---

Navigating challenges and opportunities of machine learning in hydrogen catalysis and production processes: beyond algorithm development

Journal of Energy Chemistry, Journal Year: 2024, Volume and Issue: 99, P. 223 - 252

Published: July 31, 2024

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

---

Interpretable Machine Learning for Accelerating Reverse Design and Optimizing CO₂ Methanation Catalysts with High Activity at Low Temperatures

Industrial & Engineering Chemistry Research, Journal Year: 2024, Volume and Issue: 63(33), P. 14727 - 14747

Published: Aug. 7, 2024

CO2 methanation represents a promising technological pathway for achieving efficient carbon dioxide resource utilization and mitigation of greenhouse gas emissions. However, the development catalysts with high activity at low temperatures (<250 °C) remains formidable challenge. To address time-consuming costly nature traditional catalyst methods, this study proposes an interpretable machine learning (ML)-assisted reverse design framework catalysts. This integrates advantages ML, interpretability analysis, multiobjective optimization methods to elucidate intricate interplay among compositions, preparation conditions, reaction parameters, activity. A data set containing 2777 points is established construct various ML models. After fine-tuning key hyperparameters four models, comprehensive comparison conducted evaluate their predictive performance. The light gradient boosting (LGBM) model demonstrates superior accuracy, attributed its minimal toot mean squared error less than 0.31 highest R2 value surpassing 0.90. An analysis ascertain most significant features impact on outputs optimal LGBM using postvalidation interpretation methods. It indicates that appropriately reducing active component content, first support calcination temperature, inert content are favorable reaction. Finally, coupled NGSA-III algorithm maximize conversion ratio CH4 selectivity in reactions. Three Ru- three Ni-based new have been successfully predicted recommended temperatures. In particular, optimized Ru–Ba/Cr2O3–SrO higher 97.04% 72.22%

Language: Английский

---

Enhancing Catalyst Performance Prediction with Hybrid Quantum Neural Networks: A Comparative Study on Data Consistency Variation

ACS Sustainable Chemistry & Engineering, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 31, 2025

Data consistency affects the robustness of machine learning-based models. Most experimental and industrial data have low consistency, leading to poor generalization performance. In this study, a hybrid Quantum Neural Network (hybrid QNN) with superior capabilities, was compared established learning models, including artificial neural networks decision-tree-based methods such as CatBoost XGBoost. We evaluated these models by predicting catalyst performance across different data-consistency scenarios using two sets: low-consistency preferential oxidation CO (PROX) high-consistency coupling methane (OCM) catalyst. The QNN performed better in both low- environments, demonstrating robust capabilities. regression tasks, achieved 6.7% lower mean absolute error (MAE) for PROX 35.1% MAE OCM least-performing model. Adaptability is crucial catalysis, where scarcity variability are common. Our research confirms potential comprehensive tool advancing design selection achieving high accuracy predictive power under diverse conditions.

Language: Английский

---

Interpretable physics-informed machine learning approaches to accelerate electrocatalyst development

Journal of Materials Informatics, Journal Year: 2025, Volume and Issue: 5(2)

Published: Feb. 26, 2025

Identifying exceptional electrocatalysts from the vast materials space remains a formidable challenge. Machine learning (ML) has emerged as powerful tool to address this challenge, offering high efficiency while maintaining good accuracy in predictions. From perspective, we provide brief overview of recent advancements ML for electrocatalyst discoveries. We emphasize applications physics-informed (PIML) models and explainable artificial intelligence (XAI) development, through which valuable physical chemical insights can be distilled. Additionally, delve into challenges faced by PIML approaches, explore future directions, discuss potential breakthroughs that could revolutionize field development.

Language: Английский

---

Studying the regeneration cycles of nickel-containing catalysts during high temperature gasification and prediction model fitting

Biomass and Bioenergy, Journal Year: 2025, Volume and Issue: 197, P. 107745 - 107745

Published: March 8, 2025

Language: Английский

---