Transfer Learning Approach to Multitarget Temperature-Dependent Reaction Rate Prediction

Ibrahim, Emad Al; Farooq, Aamir

doi:10.1021/acs.jpca.2c00713

Cited by 9 publications

(5 citation statements)

References 62 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…The ML models built in this work include only the cluster electronic structures that are closely related to the step of C–H activation, whereas the kinetic data specifically relevant to dehydrogenation and C–C cleavage are neglected. Recent progress in predicting reaction rate constants of organic and combustion reactions ,− by ML algorithms has witnessed the critical role of kinetic features such as activation energy, barrier parameters, and transition state properties. Hence, the kinetic features of the reactions in this study may also be introduced in the future as candidate descriptors to train better ML models.…”

Section: Discussionmentioning

confidence: 99%

Machine Learning for Experimental Reactivity of a Set of Metal Clusters toward C–H Activation

Zhao,

Yang,

et al. 2024

J. Am. Chem. Soc.

View full text Add to dashboard Cite

Understanding the mechanisms of C−H activation of alkanes is a very important research topic. The reactions of metal clusters with alkanes have been extensively studied to reveal the electronic features governing C−H activation, while the experimental cluster reactivity was qualitatively interpreted case by case in the literature. Herein, we prepared and mass-selected over 100 rhodium-based clusters (Rh x V y O z − and Rh x Co y O z − ) to react with light alkanes, enabling the determination of reaction rate constants spanning six orders of magnitude. A satisfactory model being able to quantitatively describe the rate data in terms of multiple cluster electronic features (average electron occupancy of valence s orbitals, the minimum natural charge on the metal atom, cluster polarizability, and energy gap involved in the agostic interaction) has been constructed through a machine learning approach. This study demonstrates that the general mechanisms governing the very important process of C−H activation by diverse metal centers can be discovered by interpreting experimental data with artificial intelligence.

show abstract

Section: Discussionmentioning

confidence: 99%

Machine Learning for Experimental Reactivity of a Set of Metal Clusters toward C–H Activation

Zhao,

Yang,

et al. 2024

J. Am. Chem. Soc.

View full text Add to dashboard Cite

show abstract

“…Materials design, , novel drug discovery, , catalyst optimization, , and clean energy production , are some of the many fields where knowledge has expanded because of ML. Advances in molecular dynamics, in combination with machine learning, have also paved the way for bridging the connection between molecular structure and physical characteristics. , Recent work emphasizes the improved application of FTIR spectroscopy, and more broadly, vibrational spectroscopy, for qualitative and quantitative assignment, especially when combined with ML models. , Takamura and colleagues explored methods to identify donor biological sex from urine samples . They presented several ML applications, including partial least-squares discriminant analysis with and without a genetic algorithm, to explore the chemical information contained in their FTIR spectra.…”

Section: Introductionmentioning

confidence: 99%

“…Advances in molecular dynamics, in combination with machine learning, have also paved the way for bridging the connection between molecular structure and physical characteristics. 43,44 Recent work emphasizes the improved application of FTIR spectroscopy, and more broadly, vibrational spectroscopy, for qualitative and quantitative assignment, especially when combined with ML models. 45,46 Takamura and colleagues explored methods to identify donor biological sex from urine samples.…”

Section: ■ Introductionmentioning

confidence: 99%

Saccharide Concentration Prediction from Proxy Ocean Samples Analyzed Via Infrared Spectroscopy and Quantitative Machine Learning

North,

Enders,

Clark

et al. 2024

ACS Earth Space Chem.

View full text Add to dashboard Cite

Solvated organics in the ocean are present in relatively small concentrations but contribute largely to ocean chemical diversity and complexity. Existing in the ocean as dissolved organic carbon (DOC) and enriched within the sea surface microlayer (SSML), these compounds have large impacts on atmospheric chemistry through their contributions to cloud nucleation, ice formation, and other climatological processes. The ability to quantify the concentrations of organics in ocean samples is critical to understanding these marine processes. The work presented herein details an investigation to develop a machine learning (ML) methodology utilizing infrared spectroscopy data to accurately estimate saccharide concentrations in complex solutions. We evaluated multivariate linear regression (MLR), K-nearest neighbors (KNN), decision trees (DT), gradient-boosted regressors (GBR), multilayer perceptrons (MLP), and support vector regressors (SVR) toward this goal. SVR models are shown to best predict accurate generalized saccharide concentrations. Our work presents an application combining fast spectroscopic techniques with ML to analyze organic composition in proxy ocean samples. As a result, we target a generalized method for analyzing field marine samples more efficiently without sacrificing accuracy or precision.

show abstract

“…Advances in molecular dynamics in combination with machine learning have also paved the way for bridging the connection between molecular structure and physical characteristics. 39,40 Recent work emphasizes the improved application of FTIR spectroscopy, and more broadly vibrational spectroscopy, for qualitative and quantitative assignment, especially when combined with ML models. 41,42 Takamura and colleagues explored methods to identify donor biological sex from urine samples.…”

Section: Introductionmentioning

confidence: 99%

Saccharide concentration prediction from proxy sea surface microlayer samples analyzed via infrared spectroscopy and quantitative machine learning

Enders,

North,

Clark

et al. 2024

Preprint

View full text Add to dashboard Cite

Solvated organics in the ocean are present in relatively small concentrations but contribute largely to ocean chemical diversity and complexity. Existing in the ocean as dissolved organic carbon (DOC) and enriched within the sea surface microlayer (SSML), these compounds have large impacts on atmospheric chemistry through their contributions to cloud nucleation, ice formation and other climatological processes. The ability to quantify the concentrations of organics in ocean samples is critical for understanding these marine processes. The work presented herein details an investigation to develop machine learning (ML) methodology utilizing infrared spectroscopy data to accurately estimate saccharide concentrations in complex solutions. We evaluated multivariate linear regression (MLR), K-Nearest-Neighbors (KNN), Decision Trees (DT), Gradient Boosted Regressors (GBR), Multilayer Perceptrons (MLP), and Support Vector Regressors (SVR) toward this goal. SVR models are shown to predict the accurate generalized saccharide concentrations best. Our work presents an application combining fast spectroscopic techniques with ML to analyze organic composition proxy ocean samples to target a generalized method for analyzing field marine samples more efficiently, without sacrificing accuracy or precision.

show abstract

Transfer Learning Approach to Multitarget Temperature-Dependent Reaction Rate Prediction

Cited by 9 publications

References 62 publications

Machine Learning for Experimental Reactivity of a Set of Metal Clusters toward C–H Activation

Machine Learning for Experimental Reactivity of a Set of Metal Clusters toward C–H Activation

Saccharide Concentration Prediction from Proxy Ocean Samples Analyzed Via Infrared Spectroscopy and Quantitative Machine Learning

Saccharide concentration prediction from proxy sea surface microlayer samples analyzed via infrared spectroscopy and quantitative machine learning

Contact Info

Product

Resources

About