• Corpus ID: 119347336

Artificial Intelligent Atomic Force Microscope Enabled by Machine Learning

  title={Artificial Intelligent Atomic Force Microscope Enabled by Machine Learning},
  author={Boyuan Huang and Zhenghao Li and Jiangyu Li},
  journal={arXiv: Materials Science},
Artificial intelligence (AI) and machine learning have promised to revolutionize the way we live and work, and one of particularly promising areas for AI is image analysis. Nevertheless, many current AI applications focus on post-processing of data, while in both materials sciences and medicines, it is often critical to respond to the data acquired on the fly. Here we demonstrate an artificial intelligent atomic force microscope (AI-AFM) that is capable of not only pattern recognition and… 
13 Citations

Figures from this paper

Artificial-intelligence-driven scanning probe microscopy

DeepSPM is a machine learning approach allowing to acquire and classify data autonomously in multi-day Scanning Tunnelling Microscopy experiments, and paves the way for advanced methods hardly feasible by human operation.

Machine learning at the (sub)atomic scale: next generation scanning probe microscopy

We discuss the exciting prospects for a step change in our ability to map and modify matter at the atomic/molecular level by embedding machine learning algorithms in scanning probe microscopy (with a

Mask R-CNN to Classify Chemical Compounds in Nanostructured Materials

The architecture Mask R-CNN was trained with TEM images, and performs the classification, location, and segmentation of chemical compounds with a data set of 26 images, reaching scores above 90% of accuracy.

Data acquisition and imaging using wavelet transform: a new path for high speed transient force microscopy

The unique ability of Atomic Force Microscopy (AFM) to image, manipulate and characterize materials at the nanoscale has made it a remarkable tool in nanotechnology. In dynamic AFM, acquisition and

Nanoinformatics, and the big challenges for the science of small things.

The combination of computational chemistry and computational materials science with machine learning and artificial intelligence provides a powerful way of relating structural features of

A dynamical approach to topography estimation in atomic force microscopy based on smooth orthogonal decomposition

A novel approach based on the smooth orthogonal decomposition for the estimation of the surface topography in AFM that not only eliminates the need for a closed-loop controller but also acquires the surface three-dimensional shape (topography) very quickly and accurately.

High-throughput sequential excitation for nanoscale mapping of electrochemical strain in granular ceria.

A high-throughput sequential excitation AFM that captures contact dynamics of probe-sample interactions with high fidelity and efficiency, acquiring the spectrum of data on each pixel over a range of frequencies that are excited in a sequential manner.

Investigation of AFM-based machining of ferroelectric thin films at the nanoscale

Atomic force microscopy (AFM) has been utilized for nanomechanical machining of various materials including polymers, metals, and semiconductors. Despite being important candidate materials for a

A time and resource efficient machine learning assisted design of non-fullerene small molecule acceptors for P3HT-based organic solar cells and green solvent selection

A time and money efficient machine learning assisted design of non-fullerene small molecule acceptors for P3HT based organic solar cells is reported, selected using machine learning predicted Hansen solubility parameters.



Deep Learning of Atomically Resolved Scanning Transmission Electron Microscopy Images: Chemical Identification and Tracking Local Transformations.

This work develops a "weakly supervised" approach that uses information on the coordinates of all atomic species in the image, extracted via a deep neural network, to identify a rich variety of defects that are not part of an initial training set.

Big data and deep data in scanning and electron microscopies: deriving functionality from multidimensional data sets

Here, several recent applications of the big and deep data analysis methods are reviewed to visualize, compress, and translate this multidimensional structural and functional data into physically and chemically relevant information.

Machine learning–enabled identification of material phase transitions based on experimental data: Exploring collective dynamics in ferroelectric relaxors

Results indicate that machine learning approaches can be used to determine phase transitions in ferroelectrics, providing a general, statistically significant, and robust approach toward determining the presence of critical regimes and phase boundaries.

Ferroelectric or non-ferroelectric: Why so many materials exhibit "ferroelectricity" on the nanoscale

Ferroelectric materials have remained one of the major focal points of condensed matter physics and materials science for over 50 years. In the last 20 years, the development of voltage-modulated

Cellular-Level Surgery Using Nano Robots

This article proposes a new concept of an AFM-based nano robot that can be applied for cellular-level surgery on living samples and provides a “videolized” visual feedback for monitoring the dynamic changes on the sample surface.

Accelerated Discovery of Large Electrostrains in BaTiO3‐Based Piezoelectrics Using Active Learning

It is shown how the use of machine learning coupled to optimization methods can accelerate the discovery of new Pb-free BaTiO3 (BTO-) based piezoelectrics with large electrostrains with Landau theory and insights from density functional theory.

Machine learning unifies the modeling of materials and molecules

A machine-learning model, based on a local description of chemical environments and Bayesian statistical learning, provides a unified framework to predict atomic-scale properties and captures the quantum mechanical effects governing the complex surface reconstructions of silicon.

Crystal nucleation in metallic alloys using x-ray radiography and machine learning

It is shown that crystallization occurred in temporal and spatial bursts associated with a solute-suppressed nucleation zone and confirmed the efficiency of extrinsic grain refiners and gave support to the widely assumed free growth model of heterogeneous nucleation.

Solving the quantum many-body problem with artificial neural networks

A variational representation of quantum states based on artificial neural networks with a variable number of hidden neurons and a reinforcement-learning scheme that is capable of both finding the ground state and describing the unitary time evolution of complex interacting quantum systems.