About this Abstract |
Meeting |
2025 TMS Annual Meeting & Exhibition
|
Symposium
|
Novel Strategies for Rapid Acquisition and Processing of Large Datasets from Advanced Characterization Techniques
|
Presentation Title |
AI-Driven Microstructural Data Correlation Using In-Situ Raman Spectroscopy in Self-Driving Lab by Using Chocolate as Frugal Twin |
Author(s) |
Kinston Ackölf, Taylor D Sparks |
On-Site Speaker (Planned) |
Kinston Ackölf |
Abstract Scope |
Utilizing chocolate as a frugal twin, this research employs in-situ Raman spectroscopy within an autonomous lab to correlate microstructural data with material properties and processing variables. AI/ML models analyze large datasets, focusing on high-throughput methodologies and real-time data extraction. Optical microscopy complements Raman data to validate our approach. This proof of concept accelerates feature extraction and quantification, facilitating rapid discovery and optimization of novel materials. The study highlights the importance of advanced data handling and AI in modern materials characterization. |
Proceedings Inclusion? |
Planned: |
Keywords |
Characterization, Other, Machine Learning |