KEYWORDS: Education and training, Data modeling, Performance modeling, Denoising, Signal to noise ratio, Scanning electron microscopy, Manufacturing, Critical dimension metrology
Semiconductor manufacturing relies on Critical Dimension Scanning Electron Microscopy (CD-SEM) for precision in resist pattern measurements. High-resolution CD-SEM images, while desirable, can damage the resist due to increased electron beam exposure with higher frame numbers. To address this, Noise2Noise, a deep-learning noise reduction method, is introduced. Noise2Noise employs multiple noise images for unsupervised noise reduction. However, it struggles with unknown samples and limited training data. This research enhances the Noise2Noise model by introducing Attention and Residual-Recurrent structures to extract high-precision images from low-resolution inputs (1 frame). The Attention-boosted Noise2Noise model in particular exhibits superior accuracy with improved Peak Signal-to-Noise Ratio (PSNR) and Structural Similarity (SSIM) for unseen patterns. Overall, the modeling error characterized by (ΔCD/CD) has been reduced compared to the conventional Noise2Noise method, promising improved CD-SEM accuracy for advanced CMOS manufacturing.
This work presents a disordered metadiffuser that can achieve a uniform angular scattering distribution with a numerical aperture (NA) of 0.85 at a working wavelength of λ=532 nm, as demonstrated through simulations using the Gerchberg- Saxton algorithm. Additionally, we demonstrate the capability of the metadiffuser to achieve near diffraction-limit high NA focusing (NA>0.8) through the use of a spatial light modulator and the optical phase conjugation method for wavefront shaping. Finally, we propose a deep ultraviolet (DUV) model-based optical proximity correction (OPC) system that uses optical and photoresist simulations via Hopkins’s partially coherent image formation and fully convolutional networks (FCN). This system enables larger-area device fabrication with DUV lithography while maintaining precise critical dimension (CD) of meta atoms. The proposed OPC system achieves a lithography accuracy with an average ΔCD/CD of 0.235%. These results offer promising implications for the practical application of metadiffusers and the DUV lithography technique in the field of optical devices.
Dielectric metalenses realized by economic photolithography technology are vital to their mass deployment in optoelectronic applications. However, pattern fidelity has become a serious issue that degrades the device performance due to optical proximity effects. Here, we demonstrate an intelligent reticle modification system which modifies the sizes and shapes of designed patterns based on a neural-network U-net lithographic model to produce nanostructures with desired dimensions. We demonstrate 2 mm-diameter visible metalenses with diffraction-limited focusing using DUV KrF 248 nm photolithography. This work bridges between the semiconductor process and lens-making industries to realize high-volume manufacturing of versatile metalens and metasurface products.
In this study, we propose a deep-learning approach to establish the lithographic model for i-line photolithography and develop an optical proximity correction (OPC) algorithm to increase the resolution limit. The applications of RETs are not only on CMOS semiconductor, but also on some metasurface which used to patterning by electron beam lithography. With the OPC algorithm, we are able to manufacture a near-infrared metalens patterning by i-line photolithography in a more efficient and less expensive way.
In this work, we evaluate the performance of photovoltaic (PV) power generation forecast using various hybrid deep-learning algorithms, including long and short term memory (LSTM), LSTM with an Autoencoder ( LSTM-Autoencoder ) and LSTM with an attention mechanism (LSTM-Attention). We show that the LSTM-Attention model is significantly more accurate in predicting the hourly power generation of a PV plant with 162kW capacity than the other two reference counterparts. After 100 epochs training, the model achieves a superior Root Mean Square Error (RMSE) below 0.01, Mean Absolute Error (MAE) below 0.005, the Absolute Deviation (AD) below 0.02, and the Mean Absolute Percantage Error (MAPE) is around 35%. Moreover, since the correlation coefficient is up to 92%, this hybrid model not only can be used in solar power generation prediction in PV plants, but potentially can also be extended to other renewable energy sources such as predicting wind power or tide power generation.
Access to the requested content is limited to institutions that have purchased or subscribe to SPIE eBooks.
You are receiving this notice because your organization may not have SPIE eBooks access.*
*Shibboleth/Open Athens users─please
sign in
to access your institution's subscriptions.
To obtain this item, you may purchase the complete book in print or electronic format on
SPIE.org.
INSTITUTIONAL Select your institution to access the SPIE Digital Library.
PERSONAL Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.