Soil Organic Carbon Survey Across 456 Chinese Legume Fields

A soil survey conducted across 456 field sites in major food legume-producing regions of China. The dataset was created by Qi Liu and last updated in May 2026. It was used to apply a random forest model with SHAP analysis to identify key factors correlated with Soil Organic Carbon (SOC) content.

Use Cases

• Modeling soil organic carbon (SOC) content based on soil survey data.
• Identifying key environmental factors influencing SOC in legume production systems.
• Applying SHAP analysis to interpret machine learning model predictions for soil properties.

Strengths

• Data is derived from a large-scale survey of 456 field sites.
• Focuses on major food legume-producing regions in China, providing geographic specificity.

Limitations

• Column-level documentation is absent; field semantics must be inferred after download.
• Row count is unknown, which may limit suitability assessment.
• Data may reflect geographic bias inherent to the surveyed regions in China.

Provenance

Source

Qi Liu via figshare

Collection Method

Large-scale soil survey across field sites.

Freshness

Last updated 2026-05-15 09:36:22; freshness should be verified.

Geography

Major food legume-producing regions in China.