Panoptes VM predicts the process outcomes of all wafers leveraging fab data in real time.
It enables various use cases, leading to yield improvement, cost savings, and cycle time reduction.
anoptes IM is an end-to-end image metrology solution that covers from image processing, metrology to analytics. You can extract more information based on highly precise and repeatable measurements with less hassles.
Panoptes VM predicts the process outcomes of all wafers leveraging fab data in real time. It enables various use cases, leading to yield improvement, cost savings, and cycle time reduction.
Panoptes VM predicts the process outcomes of all wafers leveraging fab data in real time. It enables various use cases, leading to yield improvement, cost savings, and cycle time reduction.
In advanced manufacturing, monitoring inline processes through metrology data is essential to ensure product quality and consistency. However, traditional metrology tools are often constrained by cost, space, and time. As a result, manufacturers obtain only a handful of sampled data with lags, which limits the process visibility.
Cost
High capex & opex for equipment & sensors
Space
Limited fab space
Time
Longer time to market
Low Sampling
Challenging to obtain full visibility about process or fab
In advanced manufacturing, monitoring inline processes through metrology data is essential to ensure product quality and consistency. However, traditional metrology tools are often constrained by cost, space, and time. As a result, manufacturers obtain only a handful of sampled data with lags, which limits the process visibility.
Cost
High capex & opex for equipment & sensors
Space
Limited fab space
Time
Longer time to market
Low Sampling
Challenging to obtain full visibility about process or fab
Cost
High capex & opex for HW equipment & sensors
Space
Limited fab space
Time
Longer time to market
Low Sampling
Challenging to obtain full visibility about process or fab
Panoptes VM leverages the existing fab data to predict various process outcomes with the state-of-the-art AI technology, such as film thickness after a deposition process.
Panoptes VM leverages the existing fab data to predict various process outcomes with the state-of-the-art AI technology, such as film thickness after a deposition process.
Purpose-Specific
Is specifically developed for virtual metrology in manufacturing with our proprietary algorithms
Automatic
Enables easy model creation and management with automatic functions
Learning Machine
Operates hundreds of thousands of models in real time in high volume manufacturing environments
Purpose-Specific
Is specifically developed for virtual metrology in manufacturing with our proprietary algorithms
Automatic
Enables easy model creation and management with automatic functions
Learning Machine
Operates hundreds of thousands of models in real time in HVM environments
Highly accurate
whenever, wherever
Innovative model
architecture
.webp)
Operable at the
fab scale
Validated in real
high volume manufacturing fabs
Built for engineers
by engineers
For process engineers
with no coding or ML knowledge
Highly accurate
whenever, wherever
Innovative model
architecture
Operable
at the
fab scale
Validated in real high- volume manufacturing fabs
Built for engineers
by engineers
For process engineers
with no coding of ML knowledge
Process Control
Panoptes VM enhances the process control system by helping it adjust the process recipes at a single-wafer level in real time.
Process Monitoring
Panoptes VM allows engineers to detect anomalies and identify root causes faster, leading to excursion prevention.
Metrology Optimization
Panoptes VM enables metrology process to be optimized by analyzing process stability, reducing or expanding the sampling.
Equipment Maintenance
Panoptes VM supports engineers to detect and predict equipment anomalies and mismatching.
Yield
Improvement
Cost
Savings
Cycle Time
Reduction
Process Control
Panoptes VM enhances the process control system by helping it adjust the process recipes at a single-wafer level in real time.
Process Monitoring
Panoptes VM allows engineers to detect anomalies and identify root causes faster, leading to excursion prevention.
Metrology Optimization
Panoptes VM enables metrology process to be optimized by analyzing process stability, reducing or expanding the sampling.
Equipment Maintenance
Panoptes VM supports engineers to detect and predict equipment anomalies and mismatching.
Yield
Improvement
Cost
Savings
Cycle Time
Reduction
.png){kind=icon}
[White Paper]Panoptes VM: Real-Time Insights into Your Manufacturing Process (2025)Download
[Publication]Sawadwuthikul G., et al. “High-performing virtual metrology with group-wise feature transformation and advanced data aggregation techniques." SPIE Advanced Lithography & Patterning (2025)Learn More
[Publication]Lee J., et al. “The Value of In-Line Metrology for Advanced Process Control." 35th Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC) (2024)Learn More
[Publication]Shin M., et al. “Model aggregation for virtual metrology in high-volume manufacturing." SPIE Advanced Lithography & Patterning (2024)Learn More
[Publication]Zabrocki, S., et al. “Adaptive Online Time-Series Prediction for Virtual Metrology in Semiconductor Manufacturing." 34th Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC) (2023)Learn More
[Publication]Park W., et al. “A grid mapping-based U-net algorithm for photolithography overlay virtual metrology." SPIE Advanced Lithography & Patterning (2025)Learn More
[White Paper]Panoptes VM: Real-Time Insights into Your Manufacturing Process (2025)Download
[Publication]Sawadwuthikul G., et al. “High-performing virtual metrology with group-wise feature transformation and advanced data aggregation techniques." SPIE Advanced Lithography & Patterning (2025)Learn More
[Publication]Lee J., et al. “The Value of In-Line Metrology for Advanced Process Control." 35th Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC) (2024)Learn More
[Publication]Shin M., et al. “Model aggregation for virtual metrology in high-volume manufacturing." SPIE Advanced Lithography & Patterning (2024)Learn More
[Publication]Zabrocki, S., et al. “Adaptive Online Time-Series Prediction for Virtual Metrology in Semiconductor Manufacturing." 34th Annual SEMI Advanced Semiconductor Manufacturing Conference (ASMC) (2023)Learn More
[Publication]Park W., et al. “A grid mapping-based U-net algorithm for photolithography overlay virtual metrology." SPIE Advanced Lithography & Patterning (2025)Learn More
.png){kind=icon}
.png){kind=icon}
