Unveiling Hidden Catalysts for the Oxidative Coupling of Methane based on Combining Machine Learning with Literature Data

Takahashi, Keisuke; Miyazato, Itsuki; Nishimura, Shun; Ohyama, Junya

doi:10.1002/cctc.201800310

Cited by 69 publications

(73 citation statements)

References 29 publications

(40 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…To evaluate performance predictions using the proposed approach, a quantitative investigation was done based on the OCM dataset, which had previously published analysis results . In a recent study by Takahashi and coworkers, the catalysts were classified into four groups with C 2 yields of 0–10 %, 10–20 %, 20–30 %, and greater than 30 %, and the performance by classification version of RFR was evaluated. This was done because the OCM dataset from the literature is noisy and inconsistent due to the variety of data sources from different instruments, procedures, platforms, and researchers.…”

Section: Resultsmentioning

confidence: 99%

“…A previous study by Takahashi et al . regarded catalysts as being at roughly the same level if the performance was within the same 10 % intervals; therefore, this 4.15 % test error in RMSE was informative. In addition, Figure provides a visual representation of the details of the ML predictions by plotting actual C 2 yield (x axis) against predicted yield by ML (y axis).…”

Section: Resultsmentioning

confidence: 99%

See 1 more Smart Citation

Statistical Analysis and Discovery of Heterogeneous Catalysts Based on Machine Learning from Diverse Published Data

et al. 2019

View full text Add to dashboard Cite

The literature provides insights for catalyst design and discovery. Effective analysis of reported data using machine learning (ML) methods offers the ability to gain valuable information. However, utilizing the literature in this way has obstacles such as lack of compositional overlaps, bias from prior published data, and low sample counts for many elements. The present study describes an ML approach that considers elemental features as input representations instead of inputting catalyst compositions directly. This ML method has the potential for catalyst discovery, including catalytic reactions with limited catalyst composition overlap in the available data. Oxidative coupling of methane (OCM), water gas shift (WGS), and CO oxidation reactions were chosen to confirm the effectiveness of the proposed method by analysis using several state‐of‐the‐art ML methods. Among the ML methods tested, gradient boosting regression with XGBoost (XGB) provided the best results, and prediction accuracy was improved by the proposed approach for all three reaction types. In addition, a quantitative value of “feature importance score” was calculated to evaluate the most influential input variables on catalyst performance. Finally, catalyst optimization was explored using ML as a “surrogate” model, and the top 20 promising candidate catalysts were identified for the OCM reaction based on the optimization. The advantages of ML in catalysis analysis as well as the difficulties and limitations originating from the complexity of heterogeneous catalysis were explored.

show abstract

Section: Resultsmentioning

confidence: 99%

Section: Resultsmentioning

confidence: 99%

Statistical Analysis and Discovery of Heterogeneous Catalysts Based on Machine Learning from Diverse Published Data

et al. 2019

View full text Add to dashboard Cite

show abstract

“…In earlier years, neural network was implemented to treat heterogeneous catalysis where such data science techniques are proposed to be effective tools for simulating catalyst properties and the performance of solid materials . Since then, rapid development of machine learning algorithms occurred due to the introduction of random forest and support vector machine, which greatly improve and expand the ways of understanding the data . Thus, one can consider that such machine learning techniques could potentially solve the mystery of how reaction conditions determine the catalytic activities in heterogeneous catalysis.…”

Section: Introductionmentioning

confidence: 99%

Data Driven Determination of Reaction Conditions in Oxidative Coupling of Methane via Machine Learning

2019

Self Cite

View full text Add to dashboard Cite

The challenge in catalytic reactions lies within its complexity coming from high dimensional experimental factors. In order to solve such complexity, machine learning is implemented to treat experimental conditions in high dimensions. Oxidative coupling of methane, methane to C2 compounds (ethylene and ethane), is chosen as the prototype reaction where 156 data consisting of various experimental conditions is prepared. Machine learning reveals that the relationship between experimental conditions and C2 yield is non‐linear matter. In particular, extreme tree regression is found to accurately reproduce the experimental data. In addition, machine learning predictions can be a good indicator for designing experiments. Thus, machine learning can be a powerful approach towards understanding and determining experimental conditions in high dimension.

show abstract

“… Three key concepts in catalysts informatics: catalysts data, data to design, platform. Note Permission of reusing the image at visualization is granted by license number 4467060829054 …”

Section: Three Key Conceptsmentioning

confidence: 99%

“… (a) CH 4 conversion and C 2 selectivity of 1868 OCM data. Color bar indicates the corresponding C 2 yield in% . (b) Frequency count of cation1, 2, and 3 in 1868 OCM data.…”

Section: Three Key Conceptsmentioning

confidence: 99%

The Rise of Catalyst Informatics: Towards Catalyst Genomics

Takahashi

Miyazato

et al. 2019

ChemCatChem

Self Cite

View full text Add to dashboard Cite

Catalysis research is on the verge of experiencing a paradigm shift regarding how catalysts are designed and characterized due to the rise of catalyst informatics. The details of catalyst informatics are reviewed where the following three key concepts are proposed: catalyst data, catalyst data to catalyst design via data science, and catalyst platform. Additionally, progress and opportunities within catalyst informatics are explored and introduced. If the field of catalyst informatics grows in the appropriate manner, the methods and approaches taken for catalyst design would be fundamentally altered, leading towards great advancement within catalysis research.

show abstract

Unveiling Hidden Catalysts for the Oxidative Coupling of Methane based on Combining Machine Learning with Literature Data

Abstract: Figure 4. Projected density of state (PDOS)ofC H 4 (left) and CH 3 (right) over (a) Na-doped V(100), (b) Cu-doped V(100),a nd (c) Ba-doped V(100).

Cited by 69 publications

References 29 publications

Statistical Analysis and Discovery of Heterogeneous Catalysts Based on Machine Learning from Diverse Published Data

Statistical Analysis and Discovery of Heterogeneous Catalysts Based on Machine Learning from Diverse Published Data

Data Driven Determination of Reaction Conditions in Oxidative Coupling of Methane via Machine Learning

The Rise of Catalyst Informatics: Towards Catalyst Genomics

Contact Info

Product

Resources

About