scholarly journals Autonomous reinforcement learning agent for chemical vapor deposition synthesis of quantum materials

2021 ◽  
Vol 7 (1) ◽  
Author(s):  
Pankaj Rajak ◽  
Aravind Krishnamoorthy ◽  
Ankit Mishra ◽  
Rajiv Kalia ◽  
Aiichiro Nakano ◽  
...  

AbstractPredictive materials synthesis is the primary bottleneck in realizing functional and quantum materials. Strategies for synthesis of promising materials are currently identified by time-consuming trial and error and there are no known predictive schemes to design synthesis parameters for materials. We use offline reinforcement learning (RL) to predict optimal synthesis schedules, i.e., a time-sequence of reaction conditions like temperatures and concentrations, for the synthesis of semiconducting monolayer MoS2 using chemical vapor deposition. The RL agent, trained on 10,000 computational synthesis simulations, learned threshold temperatures and chemical potentials for onset of chemical reactions and predicted previously unknown synthesis schedules that produce well-sulfidized crystalline, phase-pure MoS2. The model can be extended to multi-task objectives such as predicting profiles for synthesis of complex structures including multi-phase heterostructures and can predict long-time behavior of reacting systems, far beyond the domain of molecular dynamics simulations, making these predictions directly relevant to experimental synthesis.

Author(s):  
J. Drucker ◽  
R. Sharma ◽  
J. Kouvetakis ◽  
K.H.J. Weiss

Patterning of metals is a key element in the fabrication of integrated microelectronics. For circuit repair and engineering changes constructive lithography, writing techniques, based on electron, ion or photon beam-induced decomposition of precursor molecule and its deposition on top of a structure have gained wide acceptance Recently, scanning probe techniques have been used for line drawing and wire growth of W on a silicon substrate for quantum effect devices. The kinetics of electron beam induced W deposition from WF6 gas has been studied by adsorbing the gas on SiO2 surface and measuring the growth in a TEM for various exposure times. Our environmental cell allows us to control not only electron exposure time but also the gas pressure flow and the temperature. We have studied the growth kinetics of Au Chemical vapor deposition (CVD), in situ, at different temperatures with/without the electron beam on highly clean Si surfaces in an environmental cell fitted inside a TEM column.


Author(s):  
M. E. Twigg ◽  
E. D. Richmond ◽  
J. G. Pellegrino

For heteroepitaxial systems, such as silicon on sapphire (SOS), microtwins occur in significant numbers and are thought to contribute to strain relief in the silicon thin film. The size of this contribution can be assessed from TEM measurements, of the differential volume fraction of microtwins, dV/dν (the derivative of the microtwin volume V with respect to the film volume ν), for SOS grown by both chemical vapor deposition (CVD) and molecular beam epitaxy (MBE).In a (001) silicon thin film subjected to compressive stress along the [100] axis , this stress can be relieved by four twinning systems: a/6[211]/( lll), a/6(21l]/(l1l), a/6[21l] /( l1l), and a/6(2ll)/(1ll).3 For the a/6[211]/(1ll) system, the glide of a single a/6[2ll] twinning partial dislocation draws the two halves of the crystal, separated by the microtwin, closer together by a/3.


2001 ◽  
Vol 11 (PR3) ◽  
pp. Pr3-885-Pr3-892 ◽  
Author(s):  
N. Popovska ◽  
S. Schmidt ◽  
E. Edelmann ◽  
V. K. Wunder ◽  
H. Gerhard ◽  
...  

2015 ◽  
Vol 48 (6) ◽  
pp. 104-109
Author(s):  
Youn-Joon Baik ◽  
Do-Hyun Kwon ◽  
Jong-Keuk Park ◽  
Wook-Seong Lee

Sign in / Sign up

Export Citation Format

Share Document