English (United Kingdom)

https://curated-unify.zendy.io/wp-json/zendy-region/v1/featured_content/oa?rat=en

https://curated-unify.zendy.io/wp-json/zendy-region/v1/highlighted_journal/

Global: Zendy Plus annual

Presents the access of premium content as premium feature

Premium Content

Presents the keyphrase highlighting as premium feature

Keyphrase Highlighting

Presents the summarisation as premium feature

Summarisation

Insights

Presents the pdf analysis as premium feature

PDF Analysis

Presents the zaia usage as premium feature

ZAIA

Global: Zendy Plus monthly

Global: Zendy Tools annual

Global: Zendy Tools monthly

Global: Zendy Free Plan

Predictive materials synthesis is the primary bottleneck in realizing newfunctional and quantum materials. Strategies for synthesis of promisingmaterials are currently identified by time-consuming trial and error approachesand there are no known predictive schemes to design synthesis parameters fornew materials. We use reinforcement learning to predict optimal synthesisschedules, i.e. a time-sequence of reaction conditions like temperatures andreactant concentrations, for the synthesis of a prototypical quantum material,semiconducting monolayer MoS$_{2}$, using chemical vapor deposition. Thepredictive reinforcement leaning agent is coupled to a deep generative model tocapture the crystallinity and phase-composition of synthesized MoS$_{2}$ duringCVD synthesis as a function of time-dependent synthesis conditions. This model,trained on 10000 computational synthesis simulations, successfully learnedthreshold temperatures and chemical potentials for the onset of chemicalreactions and predicted new synthesis schedules for producing well-sulfidizedcrystalline and phase-pure MoS$_{2}$, which were validated by computationalsynthesis simulations. The model can be extended to predict profiles forsynthesis of complex structures including multi-phase heterostructures and canalso predict long-time behavior of reacting systems, far beyond the domain ofthe MD simulations used to train the model, making these predictions directlyrelevant to experimental synthesis.

Predictive Synthesis of Quantum Materials by Probabilistic Reinforcement Learning