Recent advances in autonomous synthesis of materials

Li, Yucen; Xia, Lingling; Fan, Yi‐Ming; Wang, Qinyue; Hu, Ming

doi:10.1016/j.chphma.2021.10.002

Cited by 20 publications

(22 citation statements)

References 75 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…In combination with automated growth [16][17][18] and characterization apparatuses, the entire growth process has been automated. These approaches are collectively referred to as autonomous materials synthesis [19][20][21][22][23][24] .…”

Section: Introductionmentioning

confidence: 99%

Bayesian optimization with experimental failure for high-throughput materials growth

et al. 2022

View full text Add to dashboard Cite

A crucial problem in achieving innovative high-throughput materials growth with machine learning, such as Bayesian optimization (BO), and automation techniques has been a lack of an appropriate way to handle missing data due to experimental failures. Here, we propose a BO algorithm that complements the missing data in optimizing materials growth parameters. The proposed method provides a flexible optimization algorithm that searches a wide multi-dimensional parameter space. We demonstrate the effectiveness of the method with simulated data as well as in its implementation for actual materials growth, namely machine-learning-assisted molecular beam epitaxy (ML-MBE) of SrRuO3, which is widely used as a metallic electrode in oxide electronics. Through the exploitation and exploration in a wide three-dimensional parameter space, while complementing the missing data, we attained tensile-strained SrRuO3 film with a high residual resistivity ratio of 80.1, the highest among tensile-strained SrRuO3 films ever reported, in only 35 MBE growth runs.

show abstract

Section: Introductionmentioning

confidence: 99%

Bayesian optimization with experimental failure for high-throughput materials growth

et al. 2022

View full text Add to dashboard Cite

show abstract

“…, second harmonic generation, lifetime measurements, ultrafast pump–probe reflectivity, and vis–UV absorption, etc. ) can be envisioned as additional in situ or ex situ metrics to optimize specific desired functionalities, providing feedback-control over the PLD plasma diagnostics via machine learning or the development of growth models, ultimately heading toward autonomous synthesis. , The great sensitivity of 2D materials to such in situ optical assessments, coupled with the great versatility, digital flux, and tunable kinetic energies that can be controlled in situ in the sub-50 eV/atom regime as shown here, provide the general means to optimize the structure and quality of quantum materials, addressing priority research directions for precision synthesis with real-time adaptive control.…”

Section: Discussionmentioning

confidence: 99%

Real-Time Diagnostics of 2D Crystal Transformations by Pulsed Laser Deposition: Controlled Synthesis of Janus WSSe Monolayers and Alloys

et al. 2023

View full text Add to dashboard Cite

Energetic processing methods such as hyperthermal implantation hold special promise to achieve the precision synthesis of metastable two-dimensional (2D) materials such as Janus monolayers; however, they require precise control. Here, we report a feedback approach to reveal and control the transformation pathways in materials synthesis by pulsed laser deposition (PLD) and apply it to investigate the transformation kinetics of monolayer WS 2 crystals into Janus WSSe and WSe 2 by implantation of Se clusters with different maximum kinetic energies (<42 eV/Se-atom) generated by laser ablation of a Se target. Real-time Raman spectroscopy and photoluminescence are used to assess the structure, composition, and optoelectronic quality of the monolayer crystal as it is implanted with well-controlled fluxes of selenium for different kinetic energies that are regulated with in situ ICCD imaging, ion probe, and spectroscopy diagnostics. First-principles calculations, XPS, and atomic-resolution HAADF STEM imaging are used to understand the intermediate alloy compositions and their vibrational modes to identify transformation pathways. The real-time kinetics measurements reveal highly selective top-layer conversion as WS 2 transforms through WS 2(1−x) Se 2x alloys to WSe 2 and provide the means to adjust processing conditions to achieve fractional and complete Janus WSSe monolayers as metastable transition states. The general approach demonstrates a real-time feedback method to achieve Janus layers or other metastable alloys of the desired composition, and a general means to adjust the structure and quality of materials grown by PLD, addressing priority research directions for precision synthesis with real-time adaptive control.

show abstract

“…In this aspect, we have seen the advent of robotic platforms for nanomaterial synthesis and characterization to reduce hands-on operation and minimize human-related errors. [124][125][126] We postulate a growing interest in the development of similar automated platforms specializing in different nanosensor modications to produce highly consistent nanosensors, such as surface functionalization with target receptor moieties and controlled MOF encapsulation.…”

Section: Discussionmentioning

confidence: 99%

Emerging nanosensor platforms and machine learning strategies toward rapid, point-of-need small-molecule metabolite detection and monitoring

Leong

Koh

et al. 2022

Chem. Sci.

View full text Add to dashboard Cite

show abstract

Recent advances in autonomous synthesis of materials

Cited by 20 publications

References 75 publications

Bayesian optimization with experimental failure for high-throughput materials growth

Bayesian optimization with experimental failure for high-throughput materials growth

Real-Time Diagnostics of 2D Crystal Transformations by Pulsed Laser Deposition: Controlled Synthesis of Janus WSSe Monolayers and Alloys

Emerging nanosensor platforms and machine learning strategies toward rapid, point-of-need small-molecule metabolite detection and monitoring

Contact Info

Product

Resources

About