Towards smart scanning probe lithography: a framework accelerating nano-fabrication process with in-situ...

Area of Science:

• Nanotechnology
• Materials Science
• Machine Learning

Background:

• Scanning probe lithography (SPL) offers nanoscale fabrication but faces challenges in quality control and subjective feature measurement.
• Process parameters significantly impact nano-fabrication critical dimensions in SPL.

Purpose of the Study:

• To develop a novel machine learning (ML) framework for optimizing SPL process parameters and segmenting nano-fabricated features.
• To overcome the limitations of traditional manual labeling-based experimental methods in SPL.

Main Methods:

• Utilized a machine learning framework for intelligent extraction of global information for statistical analysis.
• Applied the framework to fine-tune and optimize SPL process parameters for enhanced nano-fabrication.

Main Results:

• Achieved processing of smaller critical dimensions through optimized SPL process parameters.
• Successfully performed large-scale direct-write nano-lithography.
• Demonstrated data-driven feature extraction and analysis for fabrication quality optimization.

Conclusions:

• The proposed ML framework effectively optimizes SPL process parameters, leading to improved nano-fabrication precision and scale.
• This data-driven approach offers potential guidance for other characterization methods and fabrication quality enhancement.