United StatesChemicals and materials2025 – ongoingQnity Electronics
AI-assisted development of semiconductor formulations
Qnity reported reaching a semiconductor formulation solution 35% faster with AI-assisted machine learning
Problem
Developing formulations for advanced chips required experimental work to identify materials that improved yield. Qnity sought to shorten that development cycle.
Approach
Qnity used proprietary experimental data to build predictive models and iterative learning loops. It combined this work with molecular modeling for targeted formulations. An internal case reported reaching a solution faster than its traditional approach.
Results
Takeaway
The reported speed improvement concerned an internal formulation case. Qnity did not provide a comparison across its full development portfolio.
Categories
- Size
- Large enterprise
- Industry
- Chemicals and materials
- Business function
- IT and R&D
- Innovation type
- Process innovation
- AI technology
- Predictive analytics and ML
- Adoption
- Built in-house
- Evidence
- Company's own claim
Sources
Source summaries
Qnity described its use of experimental data and AI-assisted machine learning in formulation development. It reported reaching a solution 35% faster than the traditional model in an internal formulation case.
Full details are in the original sources.