Deep learning for electron and scanning probe microscopy: From materials design to atomic fabrication

Kalinin, Sergei V.; Ziatdinov, Maxim; Spurgeon, Steven R.; Ophus, Colin; Stach, Eric A.; Susi, Toma; Agar, Josh C.; Randall, John N.

doi:10.1557/s43577-022-00413-3

Cited by 26 publications

(7 citation statements)

References 63 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Numerous factors, including material design and synthesis, enhanced ex situ and in situ characterization, simulation, and actual performance testing as feedback for greater understanding, influence the development of silicon-based battery materials (Figure a,b). Additionally, the combination of big data analysis with machine learning is a potent one that has shown to be useful in the field of materials science (Figure c). − …”

Section: Discussionmentioning

confidence: 99%

Imaging the Surface/Interface Morphologies Evolution of Silicon Anodes Using in Situ/Operando Electron Microscopy

Yang

Zhang

et al. 2023

ACS Appl. Mater. Interfaces

View full text Add to dashboard Cite

Si-based rechargeable lithium-ion batteries (LIBs) have generated interest as silicon has remarkably high theoretical specific capacity. It is projected that LIBs will meet the increasing need for extensive energy storage systems, electric vehicles, and portable electronics with high energy densities. However, the Si-based LIB has a substantial problem due to the volume cycle variations brought on by Si, which result in severe capacity loss. Making Si-based anodesenabled high-performance LIBs that are easy to utilize requires an understanding of the fading mechanism. Due to its distinct advantage in morphological changes from microscale to nanoscale, even approaching atomic resolution, electron microscopy is one of the most popular methods. Based on operando electron microscopy characterization, the general comprehension of the fading mechanism and the morphology evolution of Si-based LIBs are debated in this review. The current advancements in compositional and structural interpretation for Si-based LIBs using advanced electron microscopy characterization methods are outlined. The future development trends in pertinent silicon materials characterization methods are also highlighted, along with numerous potential research avenues for Si-based LIBs design and characterization.

show abstract

Section: Discussionmentioning

confidence: 99%

Imaging the Surface/Interface Morphologies Evolution of Silicon Anodes Using in Situ/Operando Electron Microscopy

Yang

Zhang

et al. 2023

ACS Appl. Mater. Interfaces

View full text Add to dashboard Cite

show abstract

“…RNNs are useful for modeling sequential data, such as text, and can learn the context and dependencies between words in a document. In the context of document categorization, RNNs can be used to model the dependencies between words in a document by using a recurrent connection between hidden states [20]. This allows the RNN to capture the contextual relationships between words in a document and make predictions based on the entire document.…”

Section: Related Workmentioning

confidence: 99%

Automatic Classification of Scanned Electronic University Documents using Deep Neural Networks with Conv2D Layers

Baimakhanova,

Zhumadillayeva,

Avdarsol

et al. 2023

IJACSA

View full text Add to dashboard Cite

This paper proposes a novel approach for scanned document categorization using a deep neural network architecture. The proposed approach leverages the strengths of both convolutional neural networks (CNNs) and recurrent neural networks (RNNs) to extract features from the scanned documents and model the dependencies between words in the documents. The pre-processed documents are first fed into a CNN, which learns and extracts features from the images. The extracted features are then passed through an RNN, which models the sequential nature of the text. The RNN produces a probability distribution over the predefined categories, and the document is classified into the category with the highest probability. The proposed approach is evaluated on a dataset of scanned documents, where each document is categorized into one of four predefined categories. The experimental results demonstrate that the proposed approach achieves high accuracy and outperforms existing methods. The proposed approach achieves an overall accuracy of 97.3%, which is significantly higher than the existing methods' accuracy. Additionally, the proposed approach's performance was robust to variations in the quality of the scanned documents and the OCR accuracy. The contributions of this paper are twofold. Firstly, it proposes a novel approach for scanned document categorization using deep neural networks that leverages the strengths of CNNs and RNNs. Secondly; it demonstrates the effectiveness of the proposed approach on a dataset of scanned documents, highlighting its potential applications in various domains, such as information retrieval, data mining, and document management. The proposed approach can help organizations manage and analyze large volumes of data efficiently.

show abstract

“…The third type of tip-deconvolution approach is machine learning or deep learning. In the past decade, DL has been used in almost all types of imaging methods, − with the goal of resolution enhancement − and/or pattern recognition. − Surprisingly, the application of DL in quantitative height profiling is rare, leaving a large gap in this important field. , …”

mentioning

confidence: 99%

Precise Surface Profiling at the Nanoscale Enabled by Deep Learning

Bonagiri,

Wang,

Zhou

et al. 2024

Nano Lett.

View full text Add to dashboard Cite

Surface topography, or height profile, is a critical property for various micro-and nanostructured materials and devices, as well as biological systems. At the nanoscale, atomic force microscopy (AFM) is the tool of choice for surface profiling due to its capability to noninvasively map the topography of almost all types of samples. However, this method suffers from one drawback: the convolution of the nanoprobe's shape in the height profile of the samples, which is especially severe for sharp protrusion features. Here, we report a deep learning (DL) approach to overcome this limit. Adopting an image-to-image translation methodology, we use data sets of tip-convoluted and deconvoluted image pairs to train an encoder−decoder based deep convolutional neural network. The trained network successfully removes the tip convolution from AFM topographic images of various nanocorrugated surfaces and recovers the true, precise 3D height profiles of these samples.

show abstract

Deep learning for electron and scanning probe microscopy: From materials design to atomic fabrication

Cited by 26 publications

References 63 publications

Imaging the Surface/Interface Morphologies Evolution of Silicon Anodes Using in Situ/Operando Electron Microscopy

Imaging the Surface/Interface Morphologies Evolution of Silicon Anodes Using in Situ/Operando Electron Microscopy

Automatic Classification of Scanned Electronic University Documents using Deep Neural Networks with Conv2D Layers

Precise Surface Profiling at the Nanoscale Enabled by Deep Learning

Contact Info

Product

Resources

About