This technical webinar shows battery cell developers how to use machine learning to identify optimal electrode materials with fewer tests, transforming historical test data into precise recommendations for your next campaign.

The Optimal Cathode Recipe is Hidden Among Millions of Parameter Combinations 

Modern cathode development requires balancing multiple competing objectives that traditional approaches struggle to optimise efficiently:

• Finding ideal ratios between active material, binders, and conductive additives
• Maximising energy density while maintaining mechanical stability
• Reducing development cycles without compromising performance

We'll examine how machine learning approaches can enhance DoE methodologies by identifying promising formulation regions more efficiently, helping development teams focus their testing resources on the most promising cathode compositions for specific performance targets.

Continue Testing Randomly or Rely on Intuition? Both Lead to Suboptimal Results

Most labs fall into one of two traps: relying heavily on intuition and experience, or employing systematic but inefficient Design of Experiments approaches.

Meanwhile, testing equipment runs suboptimal tests while development timelines stretch and budgets strain. The data you've already collected contains valuable insights that remain untapped. 

A Smarter Approach: Data-Driven Test Recommendations for Cathode Optimisation

In this webinar, we'll demonstrate how Monolith's Next Test Recommender transforms your existing test data into a strategic advantage. You'll learn: 

• Smart Test Planning: How to ensure each test delivers maximum information gain toward your performance targets 
• Data-Driven Material Selection: Techniques for identifying specific cathode compositions to prioritise 
• Technical Demonstration: A walkthrough showing the workflow from raw data to actionable recommendations