Loess Compressibility Model Predictions for Xinjiang Study Areas

Xinjiang study areas in Huocheng and Xinyuan counties provide data comparing loess compressibility model predictions with measured values. The dataset includes results from Random Forest, MLP, CART, and SVM models, with error metrics for validation. It is a small dataset at 5.5 KB, authored by Zhiqi Liu and last updated in March 2026.

Use Cases

• Compare Random Forest model predictions for loess compressibility parameters against measured data.
• Analyze error metrics priority for model validation across different engineering classification methods.
• Evaluate the correlation between core input indicators and compressibility modulus in typical study areas.

Strengths

• Dataset is openly licensed under CC BY 4.0.
• Includes results from multiple model types (Random Forest, MLP, CART, SVM) for comparison.
• Focuses on specific geographic study areas in Xinjiang, China.

Limitations

• Extremely small dataset size of 5.5 KB suggests limited scope and likely few data points.
• No column or row count is provided, limiting understanding of the data's structure and scale.
• The description is very brief, lacking detail on specific variables, sample data, or methodology.

Provenance

Source

figshare, authored by Zhiqi Liu.

Collection Method

Comparison of model prediction results with measured data; specific collection method unknown.

Freshness

Last updated March 2026.

Geography

Study areas in Huocheng and Xinyuan counties, Xinjiang, China.