[2009.06739] Predictive Synthesis of Quantum Materials by Probabilistic Reinforcement Learningopen searchopen navigation menucontact arXivsubscribe to arXiv mailings

Predictive materials synthesis is the primary bottleneck in realizing new functional and quantum materials. Strategies for synthesis of promising materials are currently identified by time-consuming trial and error approaches and there are no known predictive schemes to design synthesis parameters for new materials. We use reinforcement learning to predict optimal synthesis schedules, i.e. a time-sequence of reaction conditions like temperatures and reactant concentrations, for the synthesis of a prototypical quantum material, semiconducting monolayer MoS$_{2}$, using chemical vapor deposition. The predictive reinforcement leaning agent is coupled to a deep generative model to capture the crystallinity and phase-composition of synthesized MoS$_{2}$ during CVD synthesis as a function of time-dependent synthesis conditions. This model, trained on 10000 computational synthesis simulations, successfully learned threshold temperatures and chemical potentials for the onset of chemical reacti

3 mentions: @tjmlab
Date: 2020/09/16 03:51

Related Entries

Read more [2002.00068] DMFTwDFT: An open-source code combining Dynamical Mean Field Theory with various Densit...
0 users, 2 mentions 2020/02/04 03:51
Read more [2002.10173] Observation of long-range quantum interferences of d-wave Andreev pairs in graphenecont...
0 users, 2 mentions 2020/02/25 05:21
Read more [2003.03088] Electron-Doping Effect on Tc in the Undoped (Ce-Free) Superconductor T'-La1.8Eu0.2CuO4 ...
0 users, 2 mentions 2020/03/09 02:20
Read more [2003.04711] Physics for Neuromorphic Computingcontact arXivarXiv Twitter
0 users, 2 mentions 2020/03/11 06:51
Read more [2003.12259] 0.71-Å resolution electron tomography enabled by deep learning aided information recove...
0 users, 2 mentions 2020/03/30 03:51