Deep Learning Accelerates the Discovery of Two‐Dimensional Catalysts for Hydrogen Evolution Reaction

Wu, Sicheng; Wang, Zhilong; Zhang, Haikuo; Cai, Junfei; Li, Jinjin

doi:10.1002/eem2.12259

Cited by 25 publications

(23 citation statements)

References 51 publications

(70 reference statements)

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Performing the DFT calculation for such large combinations is practically impossible even with the fastest ab initio tools and is the primary cause for using ML in this work. Previously, the adsorption energy has been observed as a prominent descriptor for the catalyst’s activity. − As the HER has a single electrochemical step and only one intermediate, the catalytic activity of a catalyst for HER is very much dependent on the adsorption energy of the catalyst. Moreover, adsorption energy descriptors are based on linear scaling relationships and linearly correlated with the activation energy through the Brønsted-Evans–Polanyi (BEP) relationships. − Hence, it is a powerful tool for predicting trends in catalytic activity and screening new potential catalyst materials.…”

Section: Methodsmentioning

confidence: 99%

“…Recent studies have demonstrated the use of ML or deep learning (DL) methods to discover new HER catalysts like two-dimensional materials, 33 single-atom catalysts (SACs), 34 and nanoclusters. 35 In this work, we sought to intimately predict electrocatalyst surface material with the inclusion of coverage effect on the catalytic surface by exploiting density functional theory (DFT) along with ML methodologies to anticipate nonhazardous and economic heterogeneous catalyst alloys for HER.…”

mentioning

confidence: 99%

See 1 more Smart Citation

Rational Designing of Bimetallic/Trimetallic Hydrogen Evolution Reaction Catalysts Using Supervised Machine Learning

Pandit

Roy

Mandal

et al. 2022

J. Phys. Chem. Lett.

View full text Add to dashboard Cite

Cost-efficient electrocatalysts to replace precious platinum group metals- (PGMs-) based catalysts for the hydrogen evolution reaction (HER) carry significant potential for sustainable energy solutions. Machine learning (ML) methods have provided new avenues for intelligent screening and predicting efficient heterogeneous catalysts in recent years. We coalesce density functional theory (DFT) and supervised ML methods to discover earth-abundant active heterogeneous NiCoCu-based HER catalysts. An intuitive generalized microstructure model was designed to study the adsorbate’s surface coverage and generate input features for the ML process. The study utilizes optimized eXtreme Gradient Boost Regression (XGBR) models to screen NiCoCu alloy-based catalysts for HER. We show that the most active HER catalysts can be screened from an extensive set of catalysts with this approach. Therefore, our approach can provide an efficient way to discover novel heterogeneous catalysts for various electrochemical reactions.

show abstract

Section: Methodsmentioning

confidence: 99%

mentioning

confidence: 99%

Rational Designing of Bimetallic/Trimetallic Hydrogen Evolution Reaction Catalysts Using Supervised Machine Learning

Pandit

Roy

Mandal

et al. 2022

J. Phys. Chem. Lett.

View full text Add to dashboard Cite

show abstract

“…It is thus desirable to search for 2D materials with intrinsically active basal planes, which could naturally provide a much higher density of active sites. Our 2DMatPedia database includes around 3000 top-down 2D materials, providing a wealth of 2D materials for discovering high-performance HER candidates by high-throughput screening or machine-learning algorithms.…”

Section: Intelligent Data Mining Of Two-dimensional Functional Mateialsmentioning

confidence: 99%

“…From Materials Cloud, Karmodak et al screened out only 15 promising HER catalysts from 258 2D materials with E exf < 35 meV/Å 2 . For deeper data mining, Wu et al used a deep-learning method (at near-DFT accuracy) to screen out 38 high-performance HER catalysts from 6531 2D materials …”

Section: Other Publications Related To the 2dmatpedia Platformmentioning

confidence: 99%

“…52 The accuracy of the predicted band gaps with ML models is tested and validated by 2DMatPedia data sets. 52 39 The electronic structures are the main part of 2D materials databases. By combining 2DMatPedia with C2DB, Liang et al developed a rational machine-learning model for the band gap and exciton binding energy of 2D materials, which can reveal the physical pictures behind the predicted quantity by machine learning.…”

Section: Other Publications Related To the 2dmatpedia Platformmentioning

confidence: 99%

See 1 more Smart Citation

High-Throughput Computational Discovery and Intelligent Design of Two-Dimensional Functional Materials for Various Applications

et al. 2022

View full text Add to dashboard Cite

Metrics & MoreArticle Recommendations CONSPECTUS: Novel technologies and new materials are in high demand for future various applications to overcome the fundamental limitations of current techniques. For example, the nanomaterials are in high demand for the miniaturization of electric devices. Spintronics is one of the most viable solutions for green electric devices. The single-atom catalysts can provide a 100% utilization rate. Heterojunctions hold promise for applications in energy conversion and storage. Two-dimensional (2D) materials show promising applications in various applications because they can be tailored to the specific property on which a technology is based and may be compatible with other technologies. Although the number of experimentally discovered 2D materials is growing, the speed is very slow and only a few dozen 2D materials have been synthesized or exfoliated since the discovery of graphene. Recently, a novel computational technique, dubbed high-throughput computational materials design, has become a burgeoning area of materials science, which is a combination of quantum mechanical theory, materials information, and database construction with intelligent data mining. This new and powerful tool can greatly accelerate the discovery, design, and application of 2D materials by creating a database containing a large number of 2D materials with calculated fundamental properties and then intelligently mining (via high-throughput automation or machine learning) the database in the search for 2D materials with the desired properties for particular applications, such as energy conversion/storage, catalysis, water purification, electronics, and optoelectronics.In this Account, we summarize our recent progress in the emerging area of 2D materials discovery, database construction, 2D functional materials design, and device development by quantum-mechanical modeling, high-throughput calculations, and machine learning inspired by the materials genome concept.We developed an open 2D materials database−2D materials encyclopedia (2DMatPedia; http://www.2dmatpedia.org/), which includes a variety of structural, thermodynamic, mechanical, electronic, and magnetic properties of more than 6000 two-dimensional materials. Using high-throughput computational screening and machinelearning techniques, we identified exotic 2D materials and heterojunctions with desired properties for several applications, such as the electrocatalysis of hydrogen and nitrogen evolution reactions, photocatalysis for water splitting, high Curie temperature ferromagnetic materials, ferromagnetic(ferroelectric) tunnel junctions, piezo(ferro)electricity, and excitonic solar cells. Our open 2D materials database with high-throughput calculations and proper advanced models will greatly reduce the experimental effort in trial and error, narrow the scope for both experimental and theoretical explorations, and thus boost the fast and sustainable development in the area of 2D materials. Despite the significant progress and successful deployment o...

show abstract

Tailor‐Engineered 2D Cocatalysts: Harnessing Electron–Hole Redox Center of 2D g‐C₃N₄ Photocatalysts toward Solar‐to‐Chemical Conversion and Environmental Purification

Ling

Ong

2022

Adv Funct Materials

126

View full text Add to dashboard Cite

Sparked by natural photosynthesis, solar photocatalysis using metal‐free graphitic carbon nitride (g‐C3N4) with appealing electronic structure has turned up as the most captivating technique to the quest for sustainable energy generation and pollution‐free environment. Nonetheless, low‐dimensional g‐C3N4 is thwarted from sluggish kinetics and rapid recombination of photogenerated carriers upon light irradiation. Among multifarious modification strategies, engineering 2D cocatalysts is anticipated to accelerate redox kinetics, augment active sites and ameliorate electron–hole separation of 2D g‐C3N4 for boosted activity thanks to its face‐to‐face contact surface. It is of timely and technological significance to review the 2D/2D interfaces with state‐of‐the‐art 2D cocatalysts, spanning from carbon‐containing to phosphorus‐containing, metal dichalcogenide, and other cocatalysts. Fundamental principles for each photocatalytic application will be introduced. Thereafter, the recent advances of 2D/2D cocatalyst‐mediated g‐C3N4 systems will be critically evaluated based on their interfacial engineering, emerging roles, and impacts toward stability and catalytic efficiency. Importantly, mechanistic insights into the charge dynamics and structure–performance relationship will be deciphered. Last, noteworthy research directions are prospected to deliver insightful ideas for future development of g‐C3N4. Overall, this review is anticipated to serve as a scaffold and cornerstone in designing dimensionality‐dependent 2D cocatalyst‐assisted g‐C3N4 toward renewable energy and ecologically green environment.

show abstract

Deep Learning Accelerates the Discovery of Two‐Dimensional Catalysts for Hydrogen Evolution Reaction

Cited by 25 publications

References 51 publications

Rational Designing of Bimetallic/Trimetallic Hydrogen Evolution Reaction Catalysts Using Supervised Machine Learning

Rational Designing of Bimetallic/Trimetallic Hydrogen Evolution Reaction Catalysts Using Supervised Machine Learning

High-Throughput Computational Discovery and Intelligent Design of Two-Dimensional Functional Materials for Various Applications

Tailor‐Engineered 2D Cocatalysts: Harnessing Electron–Hole Redox Center of 2D g‐C₃N₄ Photocatalysts toward Solar‐to‐Chemical Conversion and Environmental Purification

Contact Info

Product

Resources

About

Deep Learning Accelerates the Discovery of Two‐Dimensional Catalysts for Hydrogen Evolution Reaction

Cited by 25 publications

References 51 publications

Rational Designing of Bimetallic/Trimetallic Hydrogen Evolution Reaction Catalysts Using Supervised Machine Learning

Rational Designing of Bimetallic/Trimetallic Hydrogen Evolution Reaction Catalysts Using Supervised Machine Learning

High-Throughput Computational Discovery and Intelligent Design of Two-Dimensional Functional Materials for Various Applications

Tailor‐Engineered 2D Cocatalysts: Harnessing Electron–Hole Redox Center of 2D g‐C3N4 Photocatalysts toward Solar‐to‐Chemical Conversion and Environmental Purification

Contact Info

Product

Resources

About

Tailor‐Engineered 2D Cocatalysts: Harnessing Electron–Hole Redox Center of 2D g‐C₃N₄ Photocatalysts toward Solar‐to‐Chemical Conversion and Environmental Purification