Interpretability of high-resolution transmission electron microscopy images.

High-resolution electron microscopy is a well-suited tool for characterizing the nanoscale structure of materials. However, the interaction of the sample and the high-energy electrons of the beam can often have a detrimental impact on the sample structure. This effect can only be alleviated by decreasing the number of electrons to which the sample is exposed but will come at the cost of a decreased signal-to-noise ratio in the resulting image.

Beam induced heating in electron microscopy modeled with machine learning interatomic potentials.

We develop a combined theoretical and experimental method for estimating the amount of heating that occurs in metallic nanoparticles that are being imaged in an electron microscope. We model the thermal transport between the nanoparticle and the supporting material using molecular dynamics and equivariant neural network potentials. The potentials are trained to Density Functional Theory (DFT) calculations, and we show that an ensemble of potentials can be used as an estimate of the errors the neural network make in predicting energies and forces.

Quantifying noise limitations of neural network segmentations in high-resolution transmission electron microscopy.

Motivated by the need for low electron dose transmission electron microscopy imaging, we report the optimal frame dose (i.e.e/Å) range for object detection and segmentation tasks with neural networks.

Reconstructing the exit wave of 2D materials in high-resolution transmission electron microscopy using machine learning.

Reconstruction of the exit wave function is an important route to interpreting high-resolution transmission electron microscopy (HRTEM) images. Here we demonstrate that convolutional neural networks can be used to reconstruct the exit wave from a short focal series of HRTEM images, with a fidelity comparable to conventional exit wave reconstruction. We use a fully convolutional neural network based on the U-Net architecture, and demonstrate that we can train it on simulated exit waves and simulated HRTEM images of graphene-supported molybdenum disulphide (an industrial desulfurization catalyst).

Multi-scale approach to first-principles electron transport beyond 100 nm.

Multi-scale computational approaches are important for studies of novel, low-dimensional electronic devices since they are able to capture the different length-scales involved in the device operation, and at the same time describe critical parts such as surfaces, defects, interfaces, gates, and applied bias, on a atomistic, quantum-chemical level. Here we present a multi-scale method which enables calculations of electronic currents in two-dimensional devices larger than 100 nm2, where multiple perturbed regions described by density functional theory (DFT) are embedded into an extended unperturbed region described by a DFT-parametrized tight-binding model. We explain the details of the method, provide examples, and point out the main challenges regarding its practical implementation.