Red Sandstone Dynamic Strength Under Acidic Wetting-Drying Cycles

597 experimental test results on red sandstone dynamic compressive strength under coupled acidic wetting-drying cycles. The dataset was used to develop and validate five ensemble learning models, including Random Forest and XGBoost. Authored by Bin Du and last updated on May 14, 2026.

Use Cases

• Predict rock dynamic compressive strength based on strain rate and wetting-drying cycles.
• Interpret feature significance for rock strength prediction using SHAP analysis.
• Benchmark ensemble learning model performance (RF, AdaBoost, XGBoost, LightGBM, GBDT) on geotechnical data.
• Support geotechnical stability evaluation and risk reduction in acidic environments.

Strengths

• Contains 597 test results, providing a substantial experimental basis.
• Includes five input variables (strain rate, wetting-drying cycles, pH, UCS, P-wave velocity) for model development.
• Model performance was evaluated using four metrics (R², RMSE, MAE, MAPE) and interpreted with SHAP.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data is specific to red sandstone under laboratory conditions; generalizability to other rock types or field conditions is unknown.

Provenance

Source

figshare

Collection Method

Laboratory experiments on red sandstone samples.

Freshness

Last updated 2026-05-14 17:26:47; freshness should be verified.