Using machine learning in the physical modeling of lithographic processes

Adam, Kostas; Ganjugunte, Shashidhara K.; Moyroud, C.; Shchehlik, Kanstantsin; Lam, Michael; Burbine, Andrew; Fenger, Germain; Granik, Yuri

doi:10.1117/12.2519848

Cited by 9 publications

(6 citation statements)

References 1 publication

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Aerial Image Resist Image Recently, machine learning (ML) has provided an alternative approach to costly physical simulation for DFM. Some DFM applications include direct/indirect prediction of nominal edge placement error to guide mask optimization [6,7] and direct lithography modeling with deep neural networks [8,9,10,11,12,13]. Matsunawa et al [6] build a Bayesian model to predict the OPC edge movements.…”

Section: Mask Imagementioning

confidence: 99%

Generic Lithography Modeling with Dual-band Optics-Inspired Neural Networks

Heng¹,

Li²,

Sastry³

et al. 2022

Preprint

View full text Add to dashboard Cite

Lithography simulation is a critical step in VLSI design and optimization for manufacturability. Existing solutions for highly accurate lithography simulation with rigorous models are computationally expensive and slow, even when equipped with various approximation techniques. Recently, machine learning has provided alternative solutions for lithography simulation tasks such as coarse-grained edge placement error regression and complete contour prediction. However, the impact of these learningbased methods has been limited due to restrictive usage scenarios or low simulation accuracy. To tackle these concerns, we introduce an dual-band optics-inspired neural network design that considers the optical physics underlying lithography. To the best of our knowledge, our approach yields the first published via/metal layer contour simulation at 1nm 2 /pixel resolution with any tile size. Compared to previous machine learning based solutions, we demonstrate that our framework can be trained much faster and offers a significant improvement on efficiency and image quality with 20× smaller model size. We also achieve 85× simulation speedup over traditional lithography simulator with ∼ 1% accuracy loss.

show abstract

Section: Mask Imagementioning

confidence: 99%

Generic Lithography Modeling with Dual-band Optics-Inspired Neural Networks

Heng¹,

Li²,

Sastry³

et al. 2022

Preprint

View full text Add to dashboard Cite

show abstract

“…A number of options can be considered [19] in applying machine learning techniques in lithography model. A polynomial (6) for variable threshold may be replaced by machine learning model.…”

Section: For Resist Modelmentioning

confidence: 99%

“…A polynomial for resist model may be replaced by machine learning model [19]. Each convolution term in Eq.…”

Section: For Resist Modelmentioning

confidence: 99%

“…11 may be put into a single machine learning model. A CNN has been used to predict CD from input aerial image [19], in which the accuracy is good but the parameters involved are too many and difficult to optimize. Another option is to use fully convolutional networks to predict resist contours from input aerial image [19]; in this application, reference resist contours (often extracted from SEM image) have to be very high quality [22].…”

Section: For Resist Modelmentioning

confidence: 99%

See 1 more Smart Citation

Computational Lithography Using Machine Learning Models

Shin

2021

IPSJ Transactions on System LSI Design Methodology

View full text Add to dashboard Cite

Machine learning models have been applied to a wide range of computational lithography applications since around 2010. They provide higher modeling capability, so their application allows modeling of higher accuracy. Many applications which are computationally expensive can take advantage of machine learning models, since a well trained model provides a quick estimation of outcome. This tutorial reviews a number of such computational lithography applications that have been using machine learning models. They include mask optimization with OPC (optical proximity correction) and EPC (etch proximity correction), assist features insertion and their printability check, lithography modeling with optical model and resist model, test patterns, and hotspot detection and correction.

show abstract

“…al. combined neural networks with physics-based models to improve the accuracy of lithographic process modeling [25]. From an industrial perspective, Maleh et.…”

Section: Introductionmentioning

confidence: 99%

Functional Data-Driven Framework for Fast Forecasting of Electrode Slurry Rheology Simulated by Molecular Dynamics

Duquesnoy¹,

Lombardo²,

Caro³

et al. 2022

Preprint

View full text Add to dashboard Cite

Computational modeling of the manufacturing process of Lithium-Ion Battery (LIB) composite electrodes based on mechanistic approaches, allows predicting the influence of manufacturing parameters on electrode properties. However, ensuring that the calculated properties match well with experimental data, is typically time and resources consuming In this work, we tackled this issue by proposing a functional data-driven framework combining Functional Principal Component Analysis and K-Nearest Neighbors algorithms. This aims first to recover the early numerical values of a mechanistic electrode manufacturing simulation to predict if the observable being calculated is prone to match or not, i.e screening step. In a second step it recovers additional numerical values of the ongoing mechanistic simulation iterations to predict the mechanistic simulation result, i.e forecasting step. We demonstrated this approach in context of LIB manufacturing through nonequilibrium molecular dynamics (NEMD) simulations, aiming to capture the rheological behavior of electrode slurries. We discuss in full details our novel methodology and we report that the expected mechanistic simulation results can be obtained 11 times faster with respect to running the complete mechanistic simulation, while being accurate enough from an experimental point of view, with a F 1 score equals to 0.90, and a R 2 score equals to 0.96 for the learnings validation. This paves the way towards a powerful tool to drastically reduce the utilization of computational resources while running mechanistic simulations of battery manufacturing electrodes.

show abstract

Using machine learning in the physical modeling of lithographic processes

Cited by 9 publications

References 1 publication

Generic Lithography Modeling with Dual-band Optics-Inspired Neural Networks

Generic Lithography Modeling with Dual-band Optics-Inspired Neural Networks

Computational Lithography Using Machine Learning Models

Functional Data-Driven Framework for Fast Forecasting of Electrode Slurry Rheology Simulated by Molecular Dynamics

Contact Info

Product

Resources

About