Leveraging machine learning engineering to uncover insights into heterogeneous catalyst design for oxidative coupling of methane

Nishimura, Shun; Li, Xinyue; Ohyama, Junya; Takahashi, Keisuke

doi:10.1039/d3cy00596h

Cited by 4 publications

(2 citation statements)

References 55 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Literature or Hybrid Data. In the work conducted by Nishimura et al (2023), 191 the team explored a BO-based approach for optimizing oxidative coupling of methane, utilizing data sets compiled from published literature and highthroughput screening data, starting with 3335 data points across three cycles. Their methodology showed gradual improvement in C2 yields demonstrated through the synthesis of catalysts, but also highlighted challenges in avoiding spatial shrinkage in prediction fields.…”

Section: Comparison With Doementioning

confidence: 99%

From Characterization to Discovery: Artificial Intelligence, Machine Learning and High-Throughput Experiments for Heterogeneous Catalyst Design

Benavides-Hernández,

Dumeignil

2024

ACS Catal.

View full text Add to dashboard Cite

This review paper delves into synergistic integration of artificial intelligence (AI) and machine learning (ML) with highthroughput experimentation (HTE) in the field of heterogeneous catalysis, presenting a broad spectrum of contemporary methodologies and innovations. We methodically segmented the text into three core areas: catalyst characterization, data-driven exploitation, and data-driven discovery. In the catalyst characterization part, we outline current and prospective techniques used for HTE and how AI-driven strategies can streamline or automate their analysis. The data-driven exploitation part is divided into themes, strategies, and techniques that offer flexibility for either modular application or creation of customized solutions. In the data-driven exploration part we present applications that enable exploration of areas outside the experimentally tested chemical space, incorporating a section on computational methods for identifying new prospects. The review concludes by addressing the current limitations within the field and suggesting possible avenues for future research.

show abstract

Section: Comparison With Doementioning

confidence: 99%

From Characterization to Discovery: Artificial Intelligence, Machine Learning and High-Throughput Experiments for Heterogeneous Catalyst Design

Benavides-Hernández,

Dumeignil

2024

ACS Catal.

View full text Add to dashboard Cite

show abstract

“…The inconsistencies of literature-reported data (missing data, mass balance errors), not only pose an obstacle to reproducibility but are shown to result in poorly trained regression models to predict reaction performance that register prediction outliers on literature data with C2 yields greater than 30%. For instance, the support vector regression trained on literature-mined data for OCM chemistry to predict C2 yields has R 2 ∼ 05 − 0.6, which is not impressive, because of which catalyst candidates discovered by it when used as a surrogate in Bayesian optimization lacks diversity in predicted materials, with a narrow field around La 2 O 3 derivatives, and a maximum C2 yield of ∼ 15-16% [20]. To ensure reliability of the database used to propose catalyst candidates for OCM chemistry, HTE data has been used with informatics tools for visualization, supervised ML and catalyst networks to uncover patterns among dynamically evolving factors like catalyst synthesis, composition and operating conditions on reaction performance [21].…”

Section: Of 20mentioning

confidence: 99%

Model-Based Catalyst Screening and Optimal Experimental Design for the Oxidative Coupling of Methane

Puliyanda

2023

Preprint

View full text Add to dashboard Cite

The oxidative coupling of methane (OCM) to produce ethane and ethylene (C2 compounds) as platform chemicals involves complex chemistry with reactions both in the gas phase and on the catalyst surface, resulting in a distribution of products at the expense of C2 selectivity. This work uses experimental data from a variety of mixed metal oxides on supports at different reaction conditions (temperature, contact time, and reactant flow rates) to train a random forest regressor that predicts methane conversion and C2 selectivity (key performance indicators (KPIs)), and deploys it to locate optimal conditions that maximize C2 yield for a catalyst. Investigating the regressor interpretability via feature importance reveals that the choice of metals and support are crucial to C2 selectivity predictions, while the predictions of methane conversion are driven by the reaction conditions. The machine learning (ML) regressor is used as a surrogate to develop performance curves for each of the catalysts via a multi-objective optimization routine that seeks to maximize the KPIs in the decision space of reaction conditions, is seen to locate optimal conditions at which the maximum C2 yields for catalysts are predicted to be 15%, higher on average. Analyzing the catalysts in the space of their performance curves with respect to a popular OCM catalyst, Mn-Na2WO4/SiO2, reveals distinct patterns based on intrinsic properties of metals and supports. Further, the decision space with catalyst descriptors and reaction conditions is optimized for high C2 yields using the ML surrogate, in a static multi-objective optimization routine, and an adaptive Bayesian routine, where the latter was found to have a wider field focus in proposing catalyst formulations and conditions. Transition metal oxides on a variety of supports were proposed but not their lanthanide oxide counterparts.

show abstract

Phosphate-Containing Alkali Metal-Doped TbOx/MgO Catalysts for the Oxidative Coupling of Methane

Jones,

Alfonso,

Hagelin Weaver

2024

Applied Catalysis A: General

View full text Add to dashboard Cite

Leveraging machine learning engineering to uncover insights into heterogeneous catalyst design for oxidative coupling of methane

Abstract: Machine learning (ML)-assented catalyst investigations for oxidative coupling of methane (OCM) are assessed using published datasets that includes literature data reported by different research teams, along with systematic high-throughput screening...

Cited by 4 publications

References 55 publications

From Characterization to Discovery: Artificial Intelligence, Machine Learning and High-Throughput Experiments for Heterogeneous Catalyst Design

From Characterization to Discovery: Artificial Intelligence, Machine Learning and High-Throughput Experiments for Heterogeneous Catalyst Design

Model-Based Catalyst Screening and Optimal Experimental Design for the Oxidative Coupling of Methane

Phosphate-Containing Alkali Metal-Doped TbOx/MgO Catalysts for the Oxidative Coupling of Methane

Contact Info

Product

Resources

About