Synthetic Rare Earth Separation Dataset
Synthetic solvent-extraction separation runs pairing stage conditions and feed assays with recovery and purity outcomes, generated from a first-principles separation model.
42k
rows
38
features
6.1k
downloads
This dataset is intended for research, education, and benchmarking. Industrial deployment requires validation with plant-specific data.
Schema
| Field | Type | Description |
|---|---|---|
| stage_ph_1..n | float | Stage pH profile |
| org_aq_ratio | float | Phase ratio |
| feed_La..Lu | float · wt% | Feed assay by element |
| recovery | float · % | Element recovery (label) |
| purity | float · % | Product purity (label) |
Sample preview
| run_id | org_aq_ratio | feed_Nd | stage_ph_5 | recovery | purity |
|---|---|---|---|---|---|
| r-00021 | 1.15 | 18.4 | 3.1 | 94.2 | 99.4 |
| r-00022 | 1.32 | 17.9 | 2.8 | 91.7 | 99.1 |
| r-00023 | 1.08 | 19.2 | 3.4 | 95.6 | 99.6 |
| r-00024 | 1.44 | 16.5 | 2.6 | 88.9 | 98.7 |
Data dictionary
- org_aq_ratioOrganic-to-aqueous phase ratio in the mixer-settler
- feed_NdNeodymium fraction in feed assay (wt%)
- recoveryRecovered fraction of target element (label)
Discussion
- r.Question
r.okafor
Digital product lead · 4d
Is the synthetic generator's noise model documented anywhere? Want to make sure augmentation is comparable to what we add on our side.
9 - maComment
matereal
Maintainer · 4d
Generator notes are in the linked research summary. Happy to expand the data dictionary if any fields are unclear.
6
Build on open metal intelligence, keep your plant advantage private
Explore open reference models and datasets, or start a private technical discussion. Open industry knowledge and private customer advantage are kept separate.