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

ACS Catalysis, Journal Year: 2024, Volume and Issue: 14(15), P. 11749 - 11779

Published: July 24, 2024

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

Language: Английский

---

Unlocking the potential: machine learning applications in electrocatalyst design for electrochemical hydrogen energy transformation

Chemical Society Reviews, Journal Year: 2024, Volume and Issue: unknown

Published: Jan. 1, 2024

This review explores machine learning's impact on designing electrocatalysts for hydrogen energy, detailing how it transcends traditional methods by utilizing experimental and computational data to enhance electrocatalyst efficiency discovery.

Language: Английский

---

High-throughput screening and an interpretable machine learning model of single-atom hydrogen evolution catalysts with an asymmetric coordination environment constructed from heteroatom-doped graphdiyne

Journal of Materials Chemistry A, Journal Year: 2025, Volume and Issue: unknown

Published: Jan. 1, 2025

Exploring high-activity and low-cost electrocatalysts for the hydrogen evolution reaction is key to developing new energy sources, but it faces major challenges.

Language: Английский

---

Unveiling the Role of Charge Transfer in Enhanced Electrochemical Nitrogen Fixation at Single-Atom Catalysts on BX Sheets (X = As, P, Sb)

The Journal of Physical Chemistry Letters, Journal Year: 2022, Volume and Issue: 13(20), P. 4530 - 4537

Published: May 16, 2022

To tune single-atom catalysts (SACs) for effective nitrogen reduction reaction (NRR), we investigate various transition metals implanted on boron-arsenide (BAs), boron-phosphide (BP), and boron-antimony (BSb) using density functional theory (DFT). Interestingly, W-BAs shows high catalytic activity excellent selectivity with an insignificant barrier of only 0.05 eV along the distal pathway a surmountable kinetic 0.34 eV. The W-BSb Mo-BSb exhibit performances limiting potentials -0.19 -0.34 V. Bader-charge descriptor reveals that charge transfers from substrate to *NNH in first protonation step *NH3 last step, circumventing big hurdle NRR by achieving negative free energy change *NH2 *NH3. Furthermore, machine learning (ML) descriptors are introduced reduce computational cost. Our rational design meets three critical prerequisites chemisorbing N2 molecules, stabilizing *NNH, destabilizing adsorbates high-efficiency NRR.

Language: Английский

---

Atomic layers of ruthenium oxide coupled with Mo2TiC2Tx MXene for exceptionally high catalytic activity toward water oxidation

Applied Catalysis B Environment and Energy, Journal Year: 2023, Volume and Issue: 339, P. 123139 - 123139

Published: July 29, 2023

Language: Английский

---

MatGPT: A Vane of Materials Informatics from Past, Present, to Future

Advanced Materials, Journal Year: 2023, Volume and Issue: 36(6)

Published: Oct. 10, 2023

Abstract Combining materials science, artificial intelligence (AI), physical chemistry, and other disciplines, informatics is continuously accelerating the vigorous development of new materials. The emergence “GPT (Generative Pre‐trained Transformer) AI” shows that scientific research field has entered era intelligent civilization with “data” as basic factor “algorithm + computing power” core productivity. continuous innovation AI will impact cognitive laws methods, reconstruct knowledge wisdom system. This leads to think more about informatics. Here, a comprehensive discussion models infrastructures provided, advances in discovery design are reviewed. With rise paradigms triggered by “AI for Science”, vane informatics: “MatGPT”, proposed technical path planning from aspects data, descriptors, generative models, pretraining directed collaborative training, experimental robots, well efforts preparations needed develop generation informatics, carried out. Finally, challenges constraints faced discussed, order achieve digital, intelligent, automated construction joint interdisciplinary scientists.

Language: Английский

---

Data-Driven Discovery of Graphene-Based Dual-Atom Catalysts for Hydrogen Evolution Reaction with Graph Neural Network and DFT Calculations

ACS Applied Materials & Interfaces, Journal Year: 2023, Volume and Issue: 15(10), P. 12936 - 12945

Published: Feb. 6, 2023

The flexible tuning ability of dual-atom catalysts (DACs) makes them an ideal system for a wide range electrochemical applications. However, the large design space DACs and complexity in binding motif intermediates hinder efficient determination DAC combinations desirable catalytic properties. A crystal graph convolutional neural network (CGCNN) was adopted to accelerate high-throughput screening hydrogen evolution reaction (HER) catalysts. From pool 435 N-doped graphene (N6Gr), we screened out two high-performance HER (AuCo@N6Gr NiNi@N6Gr) with excellent HER, electronic conductivity, stability using combination CGCNN density functional theory (DFT). Furthermore, comprehensive DFT studies were conducted on these confirm their outstanding kinetics understand cooperative effect between metal pair HER. To obtain AuCo, inert Au weakens strong Co, while NiNi, weakly Ni cooperate. present protocol able select different physical origins can be applied other catalysts, which should hasten catalyst discovery.

Language: Английский

---

Methods, progresses, and opportunities of materials informatics

InfoMat, Journal Year: 2023, Volume and Issue: 5(8)

Published: June 1, 2023

Abstract As an implementation tool of data intensive scientific research methods, machine learning (ML) can effectively shorten the and development (R&D) cycle new materials by half or even more. ML shows great potential in combination with other technologies, especially processing classification large amounts material from theoretical calculation experimental characterization. It is very important to systematically understand ideas informatics accelerate exploration materials. Here, we provide a comprehensive introduction most commonly used modeling methods classic cases. Then, review latest progresses prediction models, which focus on processing–structure–properties–performance (PSPP) relationships some popular systems, such as perovskites, catalysts, alloys, two‐dimensional materials, polymers. In addition, summarize recent pioneering researches innovation technology, inverse design, interatomic potentials, microtopography characterization assistance, directions informatics. Finally, comprehensively significant challenges outlooks related future field This provides critical concise appraisal for applications informatics, systematic coherent guidance scientists choose based required technologies.

Language: Английский

---

High throughput screening of single atomic catalysts with optimized local structures for the electrochemical oxygen reduction by machine learning

Journal of Energy Chemistry, Journal Year: 2023, Volume and Issue: 81, P. 349 - 357

Published: March 14, 2023

Language: Английский

---

Unlocking the performance of ternary metal (hydro)oxide amorphous catalysts via data-driven active-site engineering

Energy & Environmental Science, Journal Year: 2023, Volume and Issue: 16(11), P. 5065 - 5075

Published: Jan. 1, 2023

A machine-learning methodology was applied to unveil the structure–property relationships of fabricated ternary Ni, Fe, and Co amorphous oxygen evolution catalyst, showcasing remarkable performance stability via corrosion engineering.

Language: Английский

---