Machine Learning Driven Synthesis of Few-Layered WTe₂ with Geometrical Control

Abstract

Reducing the lateral scale of two-dimensional (2D) materials to one-dimensional (1D) has attracted substantial research interest not only to achieve competitive electronic device applications but also for the exploration of fundamental physical properties. Controllable synthesis of high-quality 1D nanoribbons (NRs) is thus highly desirable and essential for the further study. Traditional exploration of the optimal synthesis conditions of novel materials is based on the trial-and-error approach, which is time consuming, costly and laborious. Recently, machine learning (ML) has demonstrated promising capability in guiding material synthesis through effectively learning from the past data and then making recommendations. Here, we report the implementation of supervised ML for the chemical vapor deposition (CVD) synthesis of high-quality 1D few-layered WTe2 nanoribbons (NRs). The synthesis parameters of the WTe2 NRs are optimized by the trained ML model. On top of that, the growth mechanism of as-synthesized 1T' fewlayered WTe2 NRs is further proposed, which may inspire the growth strategies for other 1D nanostructures. Our findings suggest that ML is a powerful and efficient approach to aid the synthesis of 1D nanostructures, opening up new opportunities for intelligent material development.

Chemical vapor deposition of 2D materials: A review of modeling, simulation, and machine learning studies

“…In another study, Xu et al. used a supervised ML algorithm for understanding the CVD growth of high quality WTe 2 nanoribbons ( Xu et al., 2021 ). The growth parameters were optimized using the trained ML model.…”

“…The authors concluded from the feature importance study that the flow rate of hydrogen gas and temperature of the reaction were the most critical parameters. Hence, it was observed that augmenting experimental results with ML models can accelerate development of nanoribbons ( Xu et al., 2021 ). In other work, Tang et al.…”

Abnormal linear dichroism transition in two-dimensional PdPS

“…In order to further study the light and matter interaction in 2D PdPS, Raman spectroscopy was performed to offer rich information on interlayer interaction. [17][18][19][20][21][22][23] The PdPS flakes were obtained via the mechanical exfoliation method and the layerdependent Raman spectra from 1.7 nm to bulk were investigated, as shown in Fig. 4a.…”

Controllable Synthesis of Novel Two-Dimensional Nonlayered β-Bi2Te4O11 Flakes for Promising Optoelectronic Applications

“…In fact, ML has shown great potential in materials research such as catalyzer design, preparation of functional materials, and chemical synthesis. − The powerful generalization capability of ML models can efficiently optimize synthesis parameters and avoid an inefficient trial-and-error process. For example, Xu et al achieved the controllable preparation of WS 2 nanoribbons by using an ML-guided CVD method . Benefitting from the feature importance analysis of ML, the growth conditions of WS 2 nanoribbons were optimized, and the corresponding growth mechanism was demonstrated.…”

“…For example, Xu et al achieved the controllable preparation of WS 2 nanoribbons by using an ML-guided CVD method. 37 Benefitting from the feature importance analysis of ML, the growth conditions of WS 2 nanoribbons were optimized, and the corresponding growth mechanism was demonstrated. Beckham et al reported the ML-guided synthesis of flash graphene.…”