Machine learning techniques applied for the detection of nanoparticles on surfaces using coherent Fourier scatterometry.

  title={Machine learning techniques applied for the detection of nanoparticles on surfaces using coherent Fourier scatterometry.},
  author={D. Kolenov and Silvania F. Pereira},
  journal={Optics express},
  volume={28 13},
  • D. Kolenov, S. Pereira
  • Published 5 June 2020
  • Computer Science, Physics, Engineering, Medicine
  • Optics express
We present an efficient machine learning framework for detection and classification of nanoparticles on surfaces that are detected in the far-field with coherent Fourier scatterometry (CFS). We study silicon wafers contaminated with spherical polystyrene (PSL) nanoparticles (with diameters down to λ/8). Starting from the raw data, the proposed framework does the pre-processing and particle search. Further, the unsupervised clustering algorithms, such as K-means and DBSCAN, are customized to be… 
A new metrology technique for defect inspection via coherent Fourier scatterometry using orbital angular momentum beams
Coherent Fourier scatterometry (CFS) via laser beams with a Gaussian spatial profile is routinely used as an in-line inspection tool to detect defects on, for example, lithographic substrates, masks,
Coherent Fourier scatterometry using orbital angular momentum beams for defect detection.
A set of novel defect inspection techniques based on bright-field CFS using coherent beams that carry orbital angular momentum (OAM) are introduced that will enable increased sensitivity and robustness for in-line nanoscale defect inspection and the concept could also benefit x-ray scattering and scatterometry in general.
Frequency encoding scheme for reticle front and back side inspection
EUV and DUV reticles are inspected before exposure to guarantee the quality of the lithographic process. The pellicle and the reticle back side are typically inspected for the presence of
Identification of particle mixtures using machine-learning-assisted laser diffraction analysis
Arturo Villegas, Mario A. Quiroz-Juárez, 3 Alfred B. U’Ren, Juan P. Torres, 4 and Roberto de J. León-Montiel ICFO—Institut de Ciencies Fotoniques, the Barcelona Institute of Science and Technology,
Convolutional neural network applied for nanoparticle classification using coherent scatterometry data.
This work trained a convolutional neural network, including its architecture optimization, and achieved 95% accurate results, compared to an existing method based on line-by-line search and thresholding, demonstrating up to a twofold enhanced performance in particle classification.
Super-Resolution without Imaging: Library-Based Approaches Using Near-to-Far-Field Transduction by a Nanophotonic Structure
This paper investigates how partial knowledge of scattering nanostructures enables extraction of nanoscale spatial information from far-field radiation patterns and uses principal component analysis to find patterns in calibration data and use these patterns to retrieve the position of a point source of light.


Numerical Analysis
This book covers not only the standard topics but also some more advanced numerical methods being used by computational scientists and engineerstopics such as compression, forward and backward error analysis, and iterative methods of solving equationsall while maintaining a level of discussion appropriate for undergraduates.
A highly sensitive laser focus positioning method with sub-micrometre accuracy using coherent Fourier scatterometry
We report a novel method of focus determination with high sensitivity and submicrometre accuracy. The technique relies on the asymmetry in the scattered far field from a nanosphere located at the
Data-driven approaches to optical patterned defect detection.
Simulating images of an intentional defect array, a CNN approach is applied to extend detectability and enhance classification to these defects, even those that are more than 20 times smaller than the inspection wavelength.
Heterodyne detection system for nanoparticle detection using coherent Fourier scatterometry
Coherent Fourier Scatterometry (CFS) is a scanning optical technique that is particularly suitable for nanoparticle detection. Inspection of wafer surfaces is one of the critical bottle-necks for
K-means advantages and disadvantages
  • 2019
Optical inspection of nanoscale structures using a novel machine learning based synthetic image generation algorithm.
A novel interpretable machine learning technique that uses unique physical insights about noisy optical images and a few training samples to classify nanoscale defects in noisy Optical images of a semiconductor wafer is presented.
Regularized pseudo-phase imaging for inspecting and sensing nanoscale features.
This article introduces the regularized pseudo-phase, an observation quantity for polychromatic visible light microscopy that seems to be more sensitive than conventional intensity images for characterizing nanoscale features and achieves a significant improvement in signal to noise ratio without making any changes to the imaging hardware.
Sensing sub-10-nm wide perturbations in background nanopatterns using optical pseudo-electrodynamics microscopy (OPEM).
A nondestructive noninterference far-field imaging method, built upon electrodynamic principles (mechanical work and force) of the light-matter interaction, rather than the intrinsic properties of light, which creates a new paradigm for exploring light- Matter interactions at the nanoscale using microscopy that can be extended to many other problems, e.g., bioimaging, material analysis, and nanometrology.
1X HP EUV reticle inspection with a 193nm inspection system
Extensions to the 193nm wavelength inspection system for the typical 2019/20 HVM EUV reticle defect requirements are developed, showing significant defect detection improvements versus the prior generation inspection system.
Matching between simulations and measurements as a key driver for reliable overlay target design
It is demonstrated how simulation-to-measurement matching enabled us to verify the model, identify discrepancies between the model and the product stack and build an improved model that correctly describes the target.