Data for TgNN: Subsurface Flow Simulation Data for Theory-Guided Neural Networks

Supporting materials for the paper 'Deep Learning of Subsurface Flow via Theory-guided Neural Network' authored by Nanzhe Wang. The data likely contains simulation results or measurements for modeling fluid flow in porous media. Its specific size, format, and row count are not detailed in the provided metadata.

Use Cases

• Training theory-guided neural networks based on subsurface flow physics mentioned in the description.
• Benchmarking physics-informed deep learning methods for porous media flow simulation.
• Studying the integration of domain knowledge and neural networks for scientific problems.

Strengths

• Data is directly associated with a published academic paper, providing research context.
• The paper's focus on theory-guided neural networks suggests the data is designed for a specific, advanced modeling paradigm.

Limitations

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

Provenance

Source

Nanzhe Wang

Collection Method

Likely generated via scientific simulation or collected from experiments, as implied by the paper's focus on subsurface flow.