Neural network assisted multi-parameter global sensitivity analysis for nanostructure scatterometry

Meng, Kai; Jiang, Bo

doi:10.1016/j.apsusc.2021.151219

Cited by 9 publications

(6 citation statements)

References 48 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…This simulated data is used to train an inverse model, which is then used to solve for the critical dimensions by fitting the model to the measured signal. The process includes a sensitivity analysis to determine the system's measurement sensitivity and ensure the accuracy of the results 10 . Figure 1.…”

Section: Principle Of Optical Scatterometrymentioning

confidence: 99%

Artificial-neural-network-assisted DUV scatterometry for OCD on HAR sub-micron structures

Chein

Yang

et al. 2023

Metrology, Inspection, and Process Control XXXVII

View full text Add to dashboard Cite

A neural network-assisted spectral scatterometry method is presented to measure multi-dimensional critical dimensions (CDs) on high aspect ratio (HAR) structures with micron or submicron scales. With the rise of 3D integrated circuit packaging, there is a need for accurate characterization of HAR sub-micron structures. This method uses DUV scatterometry and a broadband light source from DUV to visible light to gather multi-channel reflection data. The inverse modeling method and artificial neural network model enable accurate measurement of multiple CDs of test structures. The results showed accurate measurement of deep trench critical dimensions with a nominal line width of 0.6 μm and aspect ratio up to 5:1, with accuracy within a few nanometers comparable to SEM results using the same sample.

show abstract

Section: Principle Of Optical Scatterometrymentioning

confidence: 99%

Artificial-neural-network-assisted DUV scatterometry for OCD on HAR sub-micron structures

Chein

Yang

et al. 2023

Metrology, Inspection, and Process Control XXXVII

View full text Add to dashboard Cite

show abstract

“…Please note that the computational performance of the NNbased surrogate model is contingent upon the configuration of its hidden layers. In practice, increasing the number of layers proves to be more advantageous than merely augmenting the number of neurons within a layer [12]. Hence, a series of preliminary numerical simulations are conducted to identify an optimal architecture for the hidden layers and the number of neurons.…”

Section: Nn-based Surrogate Modelmentioning

confidence: 99%

“…Dong et al conducted a global sensitivity analysis to identify the optimal measurement configuration by assessing the individual influence of input parameters on the output signatures based on the analysis of noise level and the main effect defined in global sensitivity analysis [11]. Meng et al proposed a neuralnetwork (NN)-based and density-based sensitivity analysis to identify the optimal measurement configuration that exhibits a significant change in optical responses with small variations in dimensions [12]. Foldyna et al proposed choosing optimal incidence and azimuth angles based on the standard evaluation of the parameter variances and parameter correlations in Mueller matrix scatterometry (MMS) [13].…”

Section: Introductionmentioning

confidence: 99%

Condition-number-based measurement configuration optimization for nanostructure reconstruction by optical scatterometry

Yang

Chen

Liu

et al. 2023

Meas. Sci. Technol.

View full text Add to dashboard Cite

The quality of the measured signature is influenced not only by the instrument’s precision but also by the selected measurement configuration. In optical scatterometry, the purpose of measurement configuration optimization (MCO) is to select an optimal or suboptimal combination of measurement conditions, such as the angles of incidence, azimuth, polarization and wavelength, to achieve higher measurement accuracy. This analysis not only requires an effective optimization strategy but is also time-consuming. In this work, we propose a general MCO method that incorporates error propagation theory and condition-number-based error estimation technique, by which the MCO problem can be formulated as an optimization problem for the condition number of the coefficient matrix in the linear estimation of parameter deviations. The method is demonstrated on a multi-wavelength Mueller matrix scatterometry measuring a Si grating. With the help of the neural-network-based surrogate model, the feasibility of the method is verified by making a comparison with Latin Hypercube sampling. Fitting results of the measured and calculated Mueller matrix spectra obtained at the selected optimal measurement configuration show a good agreement. The proposed method is promising to provide an alternate solution to globally evaluate the MCO problem in optical scatterometry and other measurement scenarios.

show abstract

“…In this study, one of the density-based GSA methods, PAWN method, is used due to its efficiency and effectiveness in generating approximations from data samples [31]. This method has been successfully applied to assess the influences of multiple parameters in one-dimensional grating structures on their spectroscopic ellipsometry responses [34].…”

Section: Introductionmentioning

confidence: 99%

Neural network driven sensitivity analysis of diffraction-based overlay metrology performance to target defect features

Wang,

Meng,

Zhang

et al. 2024

Meas. Sci. Technol.

View full text Add to dashboard Cite

Overlay (OVL) is one significant performance indicator for the lithography process control in semiconductor manufacturing. The accuracy of the OVL metrology is extremely critical for guarantee the lithography quality. Currently, diffraction-based overlay (DBO) is one of the mainstream OVL metrology techniques. Unfortunately, the accuracy of the DBO metrology is largely affected by the defect features of the overlay target. Therefore, there is a strong need to investigate the impacts of these target defects on the DBO metrology performance. However, efficiently investigating the statistical and interactive impacts of various DBO target defects remains challenging. This study aims to address this issue through proposing an intelligent sensitivity analysis approach. A cumulative distribution based Global Sensitivity Analysis (GSA) method is utilized to assess the nonlinear influences of multiple defects in the OVL target on the DBO inaccuracy. The scenarios with both known and unknow distributions of the OVL target defects are considered. For the former, a neural network driven forward model is constructed for fast calculating the optical diffraction responses to accelerate the GSA process. For the latter, another neural network based inverse model are built for efficiently estimating the distribution of the target defects. Finally, a series of simulation experiments are conduct for typical DBO targets with multiple common defect features. The results demonstrate the effectiveness and robustness of the proposed approach as well as give valuable insights into the DBO defect analysis. Our study provides a strong tool to assist the practitioners in achieving intelligent and efficient DBO analysis and thus in enhancing OVL metrology performance.

show abstract

Neural network assisted multi-parameter global sensitivity analysis for nanostructure scatterometry

Cited by 9 publications

References 48 publications

Artificial-neural-network-assisted DUV scatterometry for OCD on HAR sub-micron structures

Artificial-neural-network-assisted DUV scatterometry for OCD on HAR sub-micron structures

Condition-number-based measurement configuration optimization for nanostructure reconstruction by optical scatterometry

Neural network driven sensitivity analysis of diffraction-based overlay metrology performance to target defect features

Contact Info

Product

Resources

About