Biochar Production and CO2 Adsorption Data for Machine Learning Modeling

A dataset supporting a machine learning model for engineering porous biochar for CO2 adsorption. The gradient boosting regression model uses biomass composition, pyrolysis, activation, and adsorption conditions as inputs, achieving an R² of 0.99 and RMSE of 0.15. The dataset, created by Chengkai Cao and last updated in May 2026, is provided in an XLSX file.

Use Cases

• Training predictive models for biochar CO2 adsorption capacity based on feedstock composition and process parameters.
• Screening biomass feedstocks to identify optimal candidates for high-performance biochar production.
• Optimizing pyrolysis and activation conditions to engineer biochar porosity for CO2 capture.
• Validating machine learning frameworks for sustainable material design without requiring physical characterization.

Strengths

• Model performance metrics are provided, with an R² of 0.99 and RMSE of 0.15.
• The approach requires only simple feedstock information, potentially reducing experimental overhead.
• The model was validated on an extra unseen dataset, suggesting robustness.

Limitations

• Row count is unknown, which may limit suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• The dataset is small at 129.9 KB, indicating limited scope.

Provenance

Source

figshare, author Chengkai Cao.

Collection Method

Likely compiled from literature sources and model inputs/outputs.

Time Range

null

Freshness

Last updated 2026-05-03 13:06:47; freshness should be verified.

Geography

null