Automated and Autonomous Experiment in Electron and Scanning Probe Microscopy
arXiv:2103.12165
Abstract
Machine learning and artificial intelligence (ML/AI) are rapidly becoming an indispensable part of physics research, with domain applications ranging from theory and materials prediction to high-throughput data analysis. In parallel, the recent successes in applying ML/AI methods for autonomous systems from robotics through self-driving cars to organic and inorganic synthesis are generating enthusiasm for the potential of these techniques to enable automated and autonomous experiment (AE) in imaging. Here, we aim to analyze the major pathways towards AE in imaging methods with sequential image formation mechanisms, focusing on scanning probe microscopy (SPM) and (scanning) transmission electron microscopy ((S)TEM). We argue that automated experiments should necessarily be discussed in a broader context of the general domain knowledge that both informs the experiment and is increased as the result of the experiment. As such, this analysis should explore the human and ML/AI roles prior to and during the experiment, and consider the latencies, biases, and knowledge priors of the decision-making process. Similarly, such discussion should include the limitations of the existing imaging systems, including intrinsic latencies, non-idealities and drifts comprising both correctable and stochastic components. We further pose that the role of the AE in microscopy is not the exclusion of human operators (as is the case for autonomous driving), but rather automation of routine operations such as microscope tuning, etc., prior to the experiment, and conversion of low latency decision making processes on the time scale spanning from image acquisition to human-level high-order experiment planning.
References in corpus (18)
- Deep Reinforcement Learning for Multi-Agent Systems: A Review of Challenges, Solutions and Applications
- Dota 2 with Large Scale Deep Reinforcement Learning
- Hyperspectral and Multispectral Image Fusion based on a Sparse Representation
- Advanced scanning probe lithography
- Tensor field networks: Rotation- and translation-equivariant neural networks for 3D point clouds
- Bayesian Active Learning for Classification and Preference Learning
- The Band Excitation Method in Scanning Probe Microscopy for Rapid Mapping of Energy Dissipation on the Nanoscale
- Atomically precise placement of single dopants in Si
- Towards a Definition of Disentangled Representations
- Nanoelectromechanics of Piezoresponse Force Microscopy
- "Water-cycle" mechanism for writing and erasing nanostructures at the LaAlO3/SrTiO3 interface
- Assembling Di- and Multiatomic Si Clusters in Graphene via Electron Beam Manipulation
- Achieving atomic resolution magnetic dichroism by controlling the phase symmetry of an electron probe
- Explicitly disentangling image content from translation and rotation with spatial-VAE
- Learning Invariances in Neural Networks
- A unified strategy for implementing curiosity and empowerment driven reinforcement learning
- Guided search for desired functional responses via Bayesian optimization of generative model: Hysteresis loop shape engineering in ferroelectrics
- Ensemble learning and iterative training (ELIT) machine learning: applications towards uncertainty quantification and automated experiment in atom-resolved microscopy