Prediction and analysis etching model of anti-glare glass roughness based on machine learning method DOI

Tao Yang,

Lin Zhu, Fan Yang

et al.

Process Safety and Environmental Protection, Journal Year: 2024, Volume and Issue: 205, P. 28 - 38

Published: March 21, 2024

Language: Английский

Accelerated Electrosynthesis Development Enabled by High-Throughput Experimentation DOI
Yiming Mo, Huijie Chen

Synthesis, Journal Year: 2023, Volume and Issue: 55(18), P. 2817 - 2832

Published: April 12, 2023

Abstract Electrochemical synthesis has recently emerged as an environmentally benign method for synthesizing value-added fine chemicals. Its unique reactivity attracted significant interests of synthetic chemists to develop new redox chemistries. However, compared conventional chemistry, the increased complexity caused by electrode materials, supporting electrolytes, and setup configurations create obstacles efficient reaction discovery optimization. The recent increasing adoption high-throughput experimentation (HTE) in chemistry significantly expedites development. Considering potential implementing HTE electrosynthesis tackle challenges parameter space, this short review aims at providing advances technology electrosynthesis, including electrocatalysts screening, device miniaturization, electroanalytical methods, artificial intelligence, system integration. discussed contents also cover some topics electrochemistry areas other than hoping spark inspirations readers use interdisciplinary techniques solve electrochemistry. 1 Introduction 2 Parallelized Reaction Screening 3 High-Throughput Electrocatalysts 4 Miniaturization Devices 5 Analytical Methods Electrosynthesis 6 Artificial Intelligence 7 Integrated Systems 8 Conclusion Outlook

Language: Английский

Citations

7

Vacancy-induced phonon localization in boron arsenide using a unified neural network interatomic potential DOI Creative Commons
Junjie Zhang, Hao Zhang, Jing Wu

et al.

Cell Reports Physical Science, Journal Year: 2023, Volume and Issue: 5(1), P. 101760 - 101760

Published: Dec. 29, 2023

Boron arsenide, considered an ideal semiconductor, inevitably introduces arsenic defects during crystal growth. Here, we develop a unified neural network interatomic potential with quantum-mechanical precision that accurately describes phonon transport properties in both perfect and defective boron arsenides. Through molecular dynamics simulations, quantitatively explore the degree of localization arsenide caused by vacancies. We confirm this primarily affects vibration modes within frequency range 2.0–4.0 THz, which is challenge for conventional first-principles approaches. In addition, examine fluctuation heat flux autocorrelation function, reveals extent phase disruption resulting from voids lattice anharmonicity more fundamental perspective. Our study highlights applicability simulations conjunction systems, laying theoretical groundwork engineering real semiconductor crystals.

Language: Английский

Citations

6

Advancements and prospects of deep learning in biomaterials evolution DOI Creative Commons

Shuailin You,

Ying Fan, Yeyun Chen

et al.

Cell Reports Physical Science, Journal Year: 2024, Volume and Issue: 5(9), P. 102116 - 102116

Published: July 25, 2024

In recent decades, significant strides have been made in advancing biomaterials for biomedical applications. Ideal necessitate suitable mechanical properties, excellent biocompatibility, and specific bioactivities. However, the design preparation of materials with these essential characteristics pose formidable challenges, persisting as issues field. The development optimization high-performance biomaterials, along construction composites hybrids diverse biofunctions, present promising strategies enhancing therapeutic diagnostic procedures. reliance on traditional "trial error" methods acquiring a substantial volume experimental data proves to be laborious, time consuming, unreliable. An emerging approach involves successful application artificial intelligence (AI), specifically deep learning (DL), investigate optimize manufacturing techniques various biomaterials. DL, an automated intelligent tool within AI domain, finds widespread devising, analyzing, optimizing different Through "experiment-AI" technique, DL predicts potential feature information performance showcasing remarkable biomaterial research development. This review comprehensively explores DL-based technologies field, emphasizing cutting-edge advantages providing insights recommendations enhance efficacy such approaches

Language: Английский

Citations

2

Inverse Design of Microstructures Using Conditional Continuous Normalizing Flows DOI Creative Commons
Hossein Mirzaee, Serveh Kamrava

Acta Materialia, Journal Year: 2024, Volume and Issue: unknown, P. 120704 - 120704

Published: Dec. 1, 2024

Language: Английский

Citations

2

Prediction and analysis etching model of anti-glare glass roughness based on machine learning method DOI

Tao Yang,

Lin Zhu, Fan Yang

et al.

Process Safety and Environmental Protection, Journal Year: 2024, Volume and Issue: 205, P. 28 - 38

Published: March 21, 2024

Language: Английский

Citations

1