Unsupervised learning approaches can greatly benefit synthesis, characterization, modeling and simulation of nanosystems. In this presentation, I will first describe the application of Restricted Boltzmann Machine (RBM) and Variational Autoencoder (VAE) to synthesis and characterization of two-dimensional (2D) layered materials. The RBM is implemented on a quantum annealer, and can correctly identify different phases and defects in the computational synthesis of a MoS2 monolayer by chemical vapor deposition (CVD). The VAE identifies pathways connecting the semiconducting (2H) and metallic (1T) phases via novel intermediate structures called a and b in a 2D MoWSe2 alloy. These structures are akin to those observed by scanning transmission electron microscopy in a 2D MoS2. The latent-space structures in VAE are combined to form MoWSe2 devices with a and b interfaces. Quantum simulations show that interfaces synthesized from the latent space in VAE are stable and the devices with those interfaces are suitable for novel nanoelectronics applications. Next, I’ll discuss the Weighted Constraint Satisfaction Problem (WCSP) for learning, representation and reasoning across different levels of abstraction in nanosystems. I will demonstrate the success of WCSP methods on imputation of missing data in (a) CVD images of monolayer MoS2, and (b) electron microscopy images. I will also show WCSP results on identifying corrupted parts of electron microscopy images. Lastly, I’ll present a novel, extrapolative neural network called Equation Learner (EQL) for mathematical modeling of experimental and simulation data.

Deep learning for nanosystems

Macromolecular Chemistry: The Second Century

[Author Benefits](https://scimeetings.acs.org/?utm_source=pubs_content_marketing&utm_medium=website&utm_campaign=0320_MCF_NPI_Launch_Spring_Homepage&ref=pubs_content_marketing)

[How to use SciMeetings](https://storage.googleapis.com/dl.morressier.com/acs/SciMeetings-ACSSpring2020-HowToGuide_M3020-Final.pdf)

[Frequently Asked Questions](https://storage.googleapis.com/dl.morressier.com/acs/SciMtng_ACSNMSp2020_FAQ_M3120_Final.pdf)

ACS Spring 2020 National Meeting & Expo

The official archive and repository for all ACS Meetings & Expositions abstracts and select posters or presentations.