Weakly Cemented Sandstone Abrasivity Predictions from Improved RBF Model

Yafeng Yao's dataset contains prediction results for the Cerchar Abrasivity Index (CAI) and Cerchar Abrasivity Ratio (CAR) of weakly cemented sandstones. It is a small dataset (5.5 KB) derived from an improved fuzzy stochastic RBF neural network model. The data was last updated in April 2026.

Use Cases

• Validate the improved RBF model's prediction of CAI using inputs like hardness, wave velocity, porosity, and equivalent quartz content.
• Analyze the relationship between CAI and the physical state of sandstone (dry, mud-saturated, water-saturated) as described in the source study.
• Compare predicted CAR values against actual measured values to assess model accuracy, which reportedly has an error of less than 5%.
• Benchmark the performance of the improved RBF model against MLR and SVR models using metrics like MSE and MAE reductions cited in the description.

Strengths

• Model predictions show a high coefficient of determination (R²) of 0.967 against measured values.
• The underlying study reports specific performance improvements, such as a 65.7% reduction in MSE for the improved RBF model.

Limitations

• The dataset is very small at 5.5 KB, indicating limited scope and likely a small number of records or predictions.
• Data is specific to weakly cemented sandstones from western China, limiting geographic and geological generalizability.

Provenance

Source

Yafeng Yao via figshare.

Collection Method

Predictions generated by an improved fuzzy stochastic RBF neural network model using experimental test data.

Time Range

null

Freshness

Last updated in April 2026.

Geography

Weakly cemented sandstones from western China.