Mudassir Ali Sayyed
Current Organizations / Institutes
The organizations/institutes from the scholar's latest article
Research Subjects
Mudassir Ali Sayyed has a total of 20 co-authors. Here are the top co-authors by number of shared publications:
- Harald Kuhn
Fraunhofer Institute for Electronic Nano Systems
4 shared publications - Jan Langer
Fraunhofer Institute for Electronic Nano Systems
4 shared publications - Micha Haase
Chemnitz University of Technology
3 shared publications - Alexey Shaporin
Fraunhofer Institute for Electronic Nano Systems ENAS
1 shared publication Andre Lauff
Infineon Technologies Dresden GmbH & Co. KG, Dresden, Germany
1 shared publication- Anish Datta
TCS Research, Tata Consultancy Services Ltd
1 shared publication
Latest Publications
- Open Access
- 4 August 2026
- Published by Springer Nature in Research Square
Virtual Metrology for Plasma Etching: A Two-Stage Framework for Sensor Data Compression and Prediction
Plasma etching is a critical but difficult-to-monitor process in semiconductor manufacturing because wafer quality is governed by nonlinear plasma chemistry, sheath dynamics, surface reactions, chamber conditions, and tool drift. Physical metrology provides accurate measurements of quantities such as critical dimension, etch depth, etch rate, profile shape, and uniformity, but it is usually sparse, delayed, and costly. Virtual metrology (VM) addresses this limitation by estimating wafer quality from in situ sensor and equipment data, including optical emission spectroscopy (OES), radio-frequency (RF) signals, and equipment engineering system (EES) variables. This review analyzes 105 plasma-etch VM studies published between 2012 and 2025 and organizes the field around a two-stage framework. Stage 1 covers feature selection, feature transformation, spectral and temporal compression, clustering, deep representation learning, and hybrid compression strategies. Stage 2 covers regression, classification, endpoint detection, fault detection and classification, and uncertainty-aware and interpretable prediction, with multi-task extensions in which several etch targets are predicted from a shared representation. The review shows that the main challenge in plasma-etch VM is not only prediction accuracy, but also the construction of compact, robust, and physically meaningful representations from high-dimensional, noisy, and drift-prone process data. Key open issues include sparse labels, model drift, chamber transferability, benchmarking, uncertainty reporting, latency, and integration with advanced process control. The review highlights knowledge-guided compression, adaptive learning, shared representations, and uncertainty-aware deployment as important directions for industrial VM systems.
- 4 August 2026
- Published by Springer Nature in Research Square
Open AccessVirtual Metrology for Plasma Etching: A Two-Stage Framework for Sensor Data Compression and Prediction
Plasma etching is a critical but difficult-to-monitor process in semiconductor manufacturing because wafer quality is governed by nonlinear plasma chemistry, sheath dynamics, surface reactions, chamber conditions, and tool drift. Physical metrology provides accurate measurements of quantities such as critical dimension, etch depth, etch rate, profile shape, and uniformity, but it is usually sparse, delayed, and costly. Virtual metrology (VM) addresses this limitation by estimating wafer quality from in situ sensor and equipment data, including optical emission spectroscopy (OES), radio-frequency (RF) signals, and equipment engineering system (EES) variables. This review analyzes 105 plasma-etch VM studies published between 2012 and 2025 and organizes the field around a two-stage framework. Stage 1 covers feature selection, feature transformation, spectral and temporal compression, clustering, deep representation learning, and hybrid compression strategies. Stage 2 covers regression, classification, endpoint detection, fault detection and classification, and uncertainty-aware and interpretable prediction, with multi-task extensions in which several etch targets are predicted from a shared representation. The review shows that the main challenge in plasma-etch VM is not only prediction accuracy, but also the construction of compact, robust, and physically meaningful representations from high-dimensional, noisy, and drift-prone process data. Key open issues include sparse labels, model drift, chamber transferability, benchmarking, uncertainty reporting, latency, and integration with advanced process control. The review highlights knowledge-guided compression, adaptive learning, shared representations, and uncertainty-aware deployment as important directions for industrial VM systems.
- Open Access
- 5 September 2025
- Published by Fuji Technology Press Ltd. in International Journal of Automation Technology
- Vol. 19 (5) , 879-889
Real-Time Interfacial Pressure Prediction in CMP Using Machine Learning Surrogates of Finite Element Simulations
Achieving uniform material removal in chemical-mechanical polishing requires precise tuning of interfacial pressure. High-fidelity finite-element simulations can accurately model pressure profiles essential for this tuning process. However, these simulations are too computationally intensive for extensive parameter studies. This work introduces a surrogate modelling approach for two-dimensional radial pressure profiles in five-zone polishing heads. Functional principal component analysis identifies a compact, data-driven basis from a dataset of finite-element-generated pressure profiles. Kernel ridge regression then maps applied zone loadings to the extracted coefficients. Validation across diverse loading scenarios shows that the proposed surrogate matches the accuracy of detailed finite-element simulations while delivering millisecond-level predictions and clear interpretability which inputs drive specific pressure‐profile changes. Researchers with existing high-fidelity models can adopt this framework to develop fast, interpretable surrogates for real-time process optimization.
- 5 September 2025
- Published by Fuji Technology Press Ltd. in International Journal of Automation Technology
- Vol. 19 (5) , 879-889
Open AccessReal-Time Interfacial Pressure Prediction in CMP Using Machine Learning Surrogates of Finite Element Simulations
Achieving uniform material removal in chemical-mechanical polishing requires precise tuning of interfacial pressure. High-fidelity finite-element simulations can accurately model pressure profiles essential for this tuning process. However, these simulations are too computationally intensive for extensive parameter studies. This work introduces a surrogate modelling approach for two-dimensional radial pressure profiles in five-zone polishing heads. Functional principal component analysis identifies a compact, data-driven basis from a dataset of finite-element-generated pressure profiles. Kernel ridge regression then maps applied zone loadings to the extracted coefficients. Validation across diverse loading scenarios shows that the proposed surrogate matches the accuracy of detailed finite-element simulations while delivering millisecond-level predictions and clear interpretability which inputs drive specific pressure‐profile changes. Researchers with existing high-fidelity models can adopt this framework to develop fast, interpretable surrogates for real-time process optimization.
- 15 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-2
Hybrid Spectral Data Compression for Efficient and Interpretable Bosch Process Monitoring
Virtual Metrology (VM) is used to estimate waferlevel process outcome using in-situ data, which helps in reducing metrology cost and time. In cyclical plasma etching processes such as Bosch etching, Optical Emission Spectroscopy (OES) provides high-dimensional, temporally resolved data that is rich in process information but computationally burdensome. We propose a hybrid data compression framework for OES data (3648 Channels, 25 Hz) using discrete wavelet transform (DWT) filtering, principal component analysis (PCA), and functional PCA (fPCA). The resulting compressed embedding is interpretable, compact, and predictive, enabling accurate VM while preserving plasma physics insights. Experiments on 100 wafers etched through 100 Bosch cycles demonstrate that the embedding achieves strong data compression ($<0.001 \%$ of the total volume) and supports accurate prediction of etch depth, outperforming baselines.
- 15 June 2025
- Published by Institute of Electrical and Electronics Engineers (IEEE)
- p. 1-2
Hybrid Spectral Data Compression for Efficient and Interpretable Bosch Process Monitoring
Virtual Metrology (VM) is used to estimate waferlevel process outcome using in-situ data, which helps in reducing metrology cost and time. In cyclical plasma etching processes such as Bosch etching, Optical Emission Spectroscopy (OES) provides high-dimensional, temporally resolved data that is rich in process information but computationally burdensome. We propose a hybrid data compression framework for OES data (3648 Channels, 25 Hz) using discrete wavelet transform (DWT) filtering, principal component analysis (PCA), and functional PCA (fPCA). The resulting compressed embedding is interpretable, compact, and predictive, enabling accurate VM while preserving plasma physics insights. Experiments on 100 wafers etched through 100 Bosch cycles demonstrate that the embedding achieves strong data compression ($<0.001 \%$ of the total volume) and supports accurate prediction of etch depth, outperforming baselines.
- Open Access
About the Data Analysis of Optical Emission Spectra of Reactive Ion Etching Processes—The Method of Spectral Redundancy Reduction
In this study, we present the Method of Spectral Redundancy Reduction (MSRR) for analyzing OES (optical emission spectroscopy) data of dry etching processes based on the principles of spectral clustering. To achieve this, the OES data are transformed into abstract graph matrices whose associated eigenvectors directly indicate anomalies in the data set. We developed an approach that allows for the reduction in temporally resolved optical emission spectra from plasma structuring processes in such a way that individual emission lines can be algorithmically detected, which exhibit a temporal behavior different from the collective behavior of the temporally resolved overall spectrum. The proportion of emission lines that behave consistently throughout the entire process duration is not considered. Our work may find applications in which OES is used as a process-monitoring technique, especially for low-pressure plasma processing. The major benefit of the developed method is that the scale of the original data is kept, making physical interpretations possible despite data reductions.
Open AccessAbout the Data Analysis of Optical Emission Spectra of Reactive Ion Etching Processes—The Method of Spectral Redundancy Reduction
In this study, we present the Method of Spectral Redundancy Reduction (MSRR) for analyzing OES (optical emission spectroscopy) data of dry etching processes based on the principles of spectral clustering. To achieve this, the OES data are transformed into abstract graph matrices whose associated eigenvectors directly indicate anomalies in the data set. We developed an approach that allows for the reduction in temporally resolved optical emission spectra from plasma structuring processes in such a way that individual emission lines can be algorithmically detected, which exhibit a temporal behavior different from the collective behavior of the temporally resolved overall spectrum. The proportion of emission lines that behave consistently throughout the entire process duration is not considered. Our work may find applications in which OES is used as a process-monitoring technique, especially for low-pressure plasma processing. The major benefit of the developed method is that the scale of the original data is kept, making physical interpretations possible despite data reductions.
- Open Access
- 25 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Physics Guided Generative Learning for Domain Adaptable Data Synthesis : Progressive Fault Synthesization for Predictive Machine Maintenance
In this work, we perform Physics guided data synthesis. Proposed method uses seed data from the observed source state / domain for data generation of unobserved target state / domain. Our method adapts the variation of features with respect to the observed source state across unobserved states. This approach uses Physics knowledge and its associated impacts on statistical and signal properties of data. We use generative learning comprising of a variational auto-encoder (VAE) based neural network model. Proposed model has a Physics influenced optimization function to achieve the data generation and adaptation of features across domains. Proposed method aims to overcome the challenges of getting the data for different progressive fault states to achieve improved predictive machine maintenance. We demonstrate the proposed method using real-world gear fault vibration time-series for synthesizing progressive faults from normal to various faulty states.
- 25 October 2023
- Published by Association for Computing Machinery (ACM)
- p. 1-7
Open AccessPhysics Guided Generative Learning for Domain Adaptable Data Synthesis : Progressive Fault Synthesization for Predictive Machine Maintenance
In this work, we perform Physics guided data synthesis. Proposed method uses seed data from the observed source state / domain for data generation of unobserved target state / domain. Our method adapts the variation of features with respect to the observed source state across unobserved states. This approach uses Physics knowledge and its associated impacts on statistical and signal properties of data. We use generative learning comprising of a variational auto-encoder (VAE) based neural network model. Proposed model has a Physics influenced optimization function to achieve the data generation and adaptation of features across domains. Proposed method aims to overcome the challenges of getting the data for different progressive fault states to achieve improved predictive machine maintenance. We demonstrate the proposed method using real-world gear fault vibration time-series for synthesizing progressive faults from normal to various faulty states.