Critical dimension prediction of metal oxide nanoparticle photoresists for electron beam lithography using a recurrent neural network

Zhao, Rongbo; Wang, Xiaolin; Hu, Ziyu; Xu, Hong; He, Xiangming

doi:10.1039/d3nr01356a

Cited by 3 publications

(1 citation statement)

References 56 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Machine learning (ML) is one of the most intelligent and cutting-edge modeling methods in artificial intelligence (AI), which studies how to use computers to simulate or implement human learning activities . Recently, researchers have begun to pay attention to an ML method, that is, long short-term memory (LSTM) networks, and use them to build predictive models for fuel cells, financial market, stock market, soft sensor, wind power, photovoltaic power, and solar irradiance. − It is worth noting that many scholars have demonstrated that the LSTM network − with long-term memory function has better prediction ability than multilayer perceptron neural network (MPNN), ,,− which is one of the most commonly used ML modeling methods. Therefore, in this article, we use an LSTM network to establish a lithographic imaging prediction model.…”

Section: Introductionmentioning

confidence: 99%

Machine Learning Applied to Electron Beam Lithography to Accelerate Process Optimization of a Contact Hole Layer

Zhao,

Wang,

Wei

et al. 2024

ACS Appl. Mater. Interfaces

Self Cite

View full text Add to dashboard Cite

Determining the lithographic process conditions with high-resolution patterning plays a crucial role in accelerating chip manufacturing. However, lithography imaging is an extremely complex nonlinear system, and obtaining suitable process conditions requires extensive experimental attempts. This severely creates a bottleneck in optimizing and controlling the lithographic process conditions. Herein, we report a process optimization solution for a contact layer of metal oxide nanoparticle photoresists by combining electron beam lithography (EBL) experiments with machine learning. In this solution, a long short-term memory (LSTM) network and a support vector machine (SVM) model are used to establish the contact hole imaging and process condition classification models, respectively. By combining SVM with the LSTM network, the process conditions that simultaneously satisfy the requirements of the contact hole width and local critical dimension uniformity tolerance can be screened. The verification results demonstrate that the horizontal and vertical contact widths predicted by the LSTM network are highly consistent with the EBL experimental results, and the classification model shows good accuracy, providing a reference for process optimization of a contact layer.

show abstract

Section: Introductionmentioning

confidence: 99%

Machine Learning Applied to Electron Beam Lithography to Accelerate Process Optimization of a Contact Hole Layer

Zhao,

Wang,

Wei

et al. 2024

ACS Appl. Mater. Interfaces

Self Cite

View full text Add to dashboard Cite

show abstract

Convolutional Neural Network-Assisted Photoresist Formulation Discriminator Design of a Contact Layer for Electron Beam Lithography

Zhao,

Wei,

Wang

et al. 2024

J. Phys. Chem. Lett.

View full text Add to dashboard Cite

Grating-based metasurfaces for ultra-narrow near-infrared bandpass filtering with wide out-of-band suppression

Hu,

Yang,

Yang

et al. 2024

Opt. Express

View full text Add to dashboard Cite

Here, we present a straightforward strategy for designing silicon grating-based metasurfaces tailored for narrow near-infrared bandpass filtering. By selecting appropriate structural parameters for the grating and including periodic groove perturbations within each grating slit, transverse guided mode resonances (GMRs) propagating perpendicular and parallel to the grating slit are created to provide wide out-of-band suppression and high-Q filter responses, respectively. The destructive and constructive interference between radiations from groove perturbations are then introduced to eliminate all GMRs except one, producing a single-band bandpass filter. Simply adjusting the period of the groove perturbations allows precise tuning of the passband’s central wavelength across the operational spectral range from 1350 nm to 1750nm, throughout which the passband exhibits a Q-factor exceeding 9,000 and the attenuation level outside the passband remains below 1%. Furthermore, our proposed narrow bandpass filters are found to be robust against the potential fabrication imperfections, such as variations in groove size and position.

show abstract

Critical dimension prediction of metal oxide nanoparticle photoresists for electron beam lithography using a recurrent neural network

Abstract: A photoresist critical dimension (CD) recurrent neural network model is established and applied to electron beam lithography experiments. The CD prediction accuracy exceeds 93% and appropriate process conditions can be accurately screened.

Cited by 3 publications

References 56 publications

Machine Learning Applied to Electron Beam Lithography to Accelerate Process Optimization of a Contact Hole Layer

Machine Learning Applied to Electron Beam Lithography to Accelerate Process Optimization of a Contact Hole Layer

Convolutional Neural Network-Assisted Photoresist Formulation Discriminator Design of a Contact Layer for Electron Beam Lithography

Grating-based metasurfaces for ultra-narrow near-infrared bandpass filtering with wide out-of-band suppression

Contact Info

Product

Resources

About