Soil Thermal Conductivity Data for Uncertainty Quantification via Deep Learning

Data associated with a manuscript submitted to Soil & Tillage Research. The dataset contains three sheets: a training set, a test set, and experimental data. It was created by Minqi Dong and last updated on 2026-05-25.

Use Cases

• Training deep learning models for soil thermal conductivity prediction based on the provided training set.
• Evaluating model performance and uncertainty quantification methods using the separate test set.
• Validating probabilistic prediction intervals against experimental thermal conductivity test results.
• Studying aleatoric and epistemic uncertainty in soil property predictions.

Strengths

• Dataset includes a dedicated experimental validation sheet containing results from extensive thermal conductivity tests.
• Data is structured into distinct training and test sets, which is a standard practice for machine learning development.
• The dataset is associated with a peer-reviewed manuscript submitted to Soil & Tillage Research, suggesting a research context.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count and file size are unknown, which may limit suitability assessment.
• The description metadata is limited; actual data quality requires manual inspection after download.

Provenance

Source

Minqi Dong via figshare

Collection Method

Likely generated from laboratory experiments on silty clay from seasonally frozen regions.

Freshness

Last updated 2026-05-25 09:04:10; freshness should be verified.

Geography

Samples are from seasonally frozen regions; specific location is unknown.