Ranking and Scoring of Input Parameters for Sandstone Strength Prediction

20 sandstone samples from four Iranian formations were tested between an unspecified start date and 2026-05-15. The dataset, authored by Davood Fereidooni and shared on figshare, contains laboratory measurements of physical and mechanical properties used to develop AI models for predicting uniaxial compressive strength and elasticity modulus.

Use Cases

• Predict uniaxial compressive strength (UCS) based on physical properties like dry unit weight and porosity.
• Predict elasticity modulus (E) using Schmidt hammer rebound and point load index measurements.
• Perform sensitivity analysis to rank the influence of input parameters on mechanical property predictions.
• Compare the performance of AI models like Artificial Neural Networks, Random Forest, and K-Nearest Neighbors for geotechnical prediction.

Strengths

• Dataset includes specific, measured value ranges for key properties: dry unit weight (23.34–26.10 kN/m³), porosity (2.07–10.16%), UCS (55.46–104.16 MPa), and E (39.86–57.03 GPa).
• Strong statistical correlations are reported, such as a Pearson correlation of 0.947 between dry unit weight and UCS.
• The associated study achieved high model accuracy, with an ANN model reaching R² values up to 0.992 for UCS prediction.

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 very small at 5.5 KB, indicating a limited scope of 20 samples.

Provenance

Source

Davood Fereidooni

Collection Method

Comprehensive laboratory tests performed on sandstone samples.

Freshness

Last updated 2026-05-15 17:33:56; freshness should be verified.

Geography

Samples from four Iranian formations.