research
Sixteen Wells Found the Best Recorded Rare-Earth Result
Decision-focused active learning reached a recycled-magnet enrichment maximum with 16 to 24 experiments instead of 48.
Summary
Decision-focused active learning reached a recycled-magnet enrichment maximum with 16 to 24 experiments instead of 48.
Using records from Pacific Northwest National Laboratory’s CICERO selective-precipitation workflow, the authors retrospectively tested how active learning could choose experiments for critical-material recovery. Adaptive policies found the best recorded neodymium-iron-boron enrichment after 16 to 24 wells, while nonadaptive space filling required 48; two reconstructed policies tied at 16. Results for samarium-cobalt magnets and produced water exposed purity, yield and measurement-assumption trade-offs. The work is conditional and retrospective, and the authors call for a preregistered prospective test before claiming scale-up gains.
Why it matters
Decision-focused active learning reached a recycled-magnet enrichment maximum with 16 to 24 experiments instead of 48.
Limits and context
- Using records from Pacific Northwest National Laboratory’s CICERO selective-precipitation workflow, the authors retrospectively tested how active learning could choose experiments for critical-material recovery.
- The work is conditional and retrospective, and the authors call for a preregistered prospective test before claiming scale-up gains.
Key claims
Decision-focused active learning reached a recycled-magnet enrichment maximum with 16 to 24 experiments instead of 48.
Qualification: Using records from Pacific Northwest National Laboratory’s CICERO selective-precipitation workflow, the authors retrospectively tested how active learning could choose experiments for critical-material recovery.
Evidence: source-2026-09-10-005
Sources
- arXiv preprint 2609.09413arXiv · primary research
Corrections
No corrections have been recorded for this story.