Scanning probe microscopy (SPM) has revolutionized the fields of materials, nano-science, chemistry, and biology, by enabling mapping of surface properties and surface manipulation with atomic precision. However, these achievements require constant human supervision; fully automated SPM has not been accomplished yet. Here we demonstrate an artificial intelligence framework based on machine learning for autonomous SPM operation (DeepSPM). DeepSPM includes an algorithmic search of good sample regions, a convolutional neural network to assess the quality of acquired images, and a deep reinforcement learning agent to reliably condition the state of the probe. DeepSPM is able to acquire and classify data continuously in multi-day scanning tunneling microscopy experiments, managing the probe quality in response to varying experimental conditions. Our approach paves the way for advanced methods hardly feasible by human operation (e.g., large dataset acquisition and SPM-based nanolithography). DeepSPM can be generalized to most SPM techniques, with the source code publicly available.

No abstract

No abstract

No abstract

A new model is proposed for the effect of doping on dislocation velocity in tetrahedrally coordinated semiconductors. The electronic structure of 30° and 90° partials, which are the components of screw and 60° dislocations, is assumed to consist of a full donor band an empty (higher energy) acceptor band in the neutral state. Kinks are thought to be associated with localised acceptor/donor levels within the gap of the dislocation bands. The doping effect is considered to be due to the reduction of the free energy of the system by the transition of an electron/hole from the conduction/valence band, or from the dislocation bands, to the kink sites. The model accounts reasonably well for the observed variation of dislocation velocity with dopant concentration at a given temperature, and yields values for the energies of the localised kink states in Ge and Si, which are of the same order as the energy levels associated with edge dislocations as determined from electrical measurements