Open models
Reference modelOpen · reference

Lithium Recovery Predictor

Predicts overall lithium recovery from brine or hard-rock feed through the process circuit.

LithiumLithium Processing IntelligenceRecovery predictionv0.2.1Apache-2.0
5.6k 160 26

This model is a reference implementation. Industrial use requires validation on plant-specific data. Customer-specific fine-tuning remains private unless explicitly approved for publication.

Input schema

FieldTypeDescription
feed_gradefloat · mg/LLithium feed grade
process_conditionsfloat[]Reagent + temperature profile

Output schema

FieldTypeDescription
recoveryfloat · %Predicted recovery

Training data & evaluation

Training data type

Synthetic lithium circuit dataset

Evaluation metrics

MAE 2.1 % 0.88

Limitations

  • Brine and hard-rock routes behave differently; select the matching config.

Discussion

  • s.

    s.iyer

    ML researcher · 3d

    Validation note

    Reproduced the reported metric on the public split with a fixed seed. Numbers line up within noise, so it's a good baseline to build on.

    18
  • l.

    l.zhang

    Process engineer · 1w

    Improvement

    Adding an uncertainty head would make this far more useful for prioritization. Happy to open a PR against the reference repo.

    11
Reference, not production-proven

Validate on your data, keep the result private

Reference models are a starting point. We can fine-tune privately on plant-specific data, with customer-owned IP and no public disclosure.