A multiobjective closed-loop approach towards autonomous discovery of electrocatalysts for nitrogen reduction

Kavalsky, Lance; Hegde, Vinay I.; Meredig, Bryce; Viswanathan, Venkatasubramanian

doi:10.1039/d3dd00244f

Digital Discovery

2024

DOI: 10.1039/d3dd00244f

|View full text |Cite

A multiobjective closed-loop approach towards autonomous discovery of electrocatalysts for nitrogen reduction

Lance Kavalsky,

Vinay I. Hegde,

Bryce Meredig

et al.

Abstract: Electrocatalyst discovery is an inherently multiobjective challenge that can benefit from closed-loop approaches towards acceleration. However, previous computational closed-loop efforts for electrocatalysis often focus on a single objective to be...

Help me understand this report

Search citation statements

Order By: Relevance

Paper Sections

Select...

Citation Types

Supporting

Mentioning

Contrasting

Year Published

2024

Publication Types

Select...

Article3

Relationship

Self Cite0

Independent3

Authors

Journals

Cited by 3 publications

References 55 publications

(88 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

A brief overview of deep generative models and how they can be used to discover new electrode materials

Hellman

2024

Current Opinion in Electrochemistry

View full text Add to dashboard Cite

A brief overview of deep generative models and how they can be used to discover new electrode materials

Hellman

2024

Current Opinion in Electrochemistry

View full text Add to dashboard Cite

Electrowinning for Room-Temperature Ironmaking: Mapping the Electrochemical Aqueous Iron Interface

Kavalsky,

Viswanathan

2024

J. Phys. Chem. C

View full text Add to dashboard Cite

A promising route toward room-temperature ironmaking is electrowinning, where iron ore dissolution is coupled with cation electrodeposition to grow pure iron. However, poor faradaic efficiencies against the hydrogen evolution reaction (HER) is a major bottleneck. To develop a mechanistic picture of this technology, we conduct a first-principles thermodynamic analysis of the Fe110 aqueous electrochemical interface. Constructing a surface Pourbaix diagram, we predict that the iron surface will always drive toward adsorbate coverage. We calculate theoretical overpotentials for terrace and step sites and predict that growth at the step sites are likely to dominate. Investigating the hydrogen surface phases, we model several hydrogen absorption mechanisms, all of which are predicted to be endothermic. Additionally, for HER we identify step sites as being more reactive than on the terrace and with competitive limiting potentials to iron plating. The results presented here further motivate electrolyte design toward HER suppression.

show abstract

Machine learning materials properties with accurate predictions, uncertainty estimates, domain guidance, and persistent online accessibility

Jacobs,

Schultz,

Scourtas

et al. 2024

Mach. Learn.: Sci. Technol.

View full text Add to dashboard Cite

One compelling vision of the future of materials discovery and design involves the use of machine learning (ML) models to predict materials properties and then rapidly find materials tailored for specific applications. However, realizing this vision requires both providing detailed uncertainty quantification (model prediction errors and domain of applicability) and making models readily usable. At present, it is common practice in the community to assess ML model performance only in terms of prediction accuracy (e.g. mean absolute error), while neglecting detailed uncertainty quantification and robust model accessibility and usability. Here, we demonstrate a practical method for realizing both uncertainty and accessibility features with a large set of models. We develop random forest ML models for 33 materials properties spanning an array of data sources (computational and experimental) and property types (electrical, mechanical, thermodynamic, etc). All models have calibrated ensemble error bars to quantify prediction uncertainty and domain of applicability guidance enabled by kernel-density-estimate-based feature distance measures. All data and models are publicly hosted on the Garden-AI infrastructure, which provides an easy-to-use, persistent interface for model dissemination that permits models to be invoked with only a few lines of Python code. We demonstrate the power of this approach by using our models to conduct a fully ML-based materials discovery exercise to search for new stable, highly active perovskite oxide catalyst materials.

show abstract

scite is a Brooklyn-based organization that helps researchers better discover and understand research articles through Smart Citations–citations that display the context of the citation and describe whether the article provides supporting or contrasting evidence. scite is used by students and researchers from around the world and is funded in part by the National Science Foundation and the National Institute on Drug Abuse of the National Institutes of Health.

Contact Info

customersupport@researchsolutions.com

10624 S. Eastern Ave., Ste. A-614

Henderson, NV 89052, USA

This site is protected by reCAPTCHA and the Google Privacy Policy and Terms of Service apply.

Blog Terms and Conditions API Terms Privacy Policy Contact Cookie Preferences Do Not Sell or Share My Personal Information

Made with 💙 for researchers

Part of the Research Solutions Family.

A multiobjective closed-loop approach towards autonomous discovery of electrocatalysts for nitrogen reduction

Abstract: Electrocatalyst discovery is an inherently multiobjective challenge that can benefit from closed-loop approaches towards acceleration. However, previous computational closed-loop efforts for electrocatalysis often focus on a single objective to be...

Cited by 3 publications

References 55 publications

A brief overview of deep generative models and how they can be used to discover new electrode materials

A brief overview of deep generative models and how they can be used to discover new electrode materials

Electrowinning for Room-Temperature Ironmaking: Mapping the Electrochemical Aqueous Iron Interface

Machine learning materials properties with accurate predictions, uncertainty estimates, domain guidance, and persistent online accessibility

Contact Info

Product

Resources

About