Neural Potential Field Data for Celestial Body Gravity Modeling

Giving access to replication data for a neural potential field method used in high-fidelity gravity modeling and density inversion of irregular small celestial bodies. The data supports the research published in Engineering Applications of Artificial Intelligence in 2026, authored by Gao, Wutong.

Use Cases

• Train a neural network model for gravity field prediction using the neural potential field method described in the source paper.
• Perform density inversion for irregular small celestial bodies based on the provided gravity modeling data.
• Validate high-fidelity gravity simulation results against the replication data for celestial bodies.

Strengths

• Data is associated with a peer-reviewed publication in Engineering Applications of Artificial Intelligence (2026).
• The dataset is hosted and curated by the Harvard Dataverse repository.

Limitations

• The specific data structure, including column names, row count, and file formats, is unknown.
• The dataset's scope is limited to the specific methodology (neural potential field) and application (irregular small celestial bodies) of the source paper.

Provenance

Source

Harvard Dataverse

Collection Method

Replication data for a published research paper on neural potential fields.

Freshness

Last updated on February 5, 2026.