Algae Yield Predictor

Predict biomass / lipid / protein / carbohydrate with a selectable model (STACK / XGB / LGBM / CAT / MLP), local uncertainty bands, and species×medium literature-range clamping.

Inputs

Target

Choose outcome to predict

Model

Choose which trained model to use

Species

Only curated species

Medium

Restricted by species

Culture Conditions

Light (μmol·m⁻²·s⁻¹)

10 400

Days

Total culture duration

1 45

Day Exposure (h)

0 24

Night Exposure (h)

0 24

Temperature (°C)

Plot variable

Sweep one input to see response curve with uncertainty band

Suggested Conditions

💡 Suggested conditions for a. platensis → biomass

Light: 60–300 | Days: 15–25

Model Tips

Recommendations

STACK (Ensemble) — best overall accuracy (offline metrics ~R² 0.89 / MAE ~0.66).
XGB / LGBM — fast, strong single models (R² ~0.69).
CAT — robust to categorical quirks (R² ~0.62).
MLP — requires scaler; slower cold start (R² ~0.55 here).

Pick: Use STACK by default. Choose XGB/LGBM for speed or to sanity-check disagreement across models.

Click Predict + Plot to run.

Response Plot

Plot

Literature (DOI) Matches

Click Find Closest DOI Matches to see references.

Citation

If you use this predictor or dataset, please cite:

Tiwari, A., Dubey, S., Sumathi, Y., Patel, A. K, & Kuo, T.-R. (2025).
Augmented and Real Microalgae Datasets for Biomass and Biochemical Composition Prediction [Data set]. Zenodo.
https://doi.org/10.5281/zenodo.17177597