DL-RMD: Geophysical Resistivity Models for Deep Learning in Electromagnetics

Aarhus University presents a large-scale electrical resistivity model database for deep learning applications in geophysics. It contains a wide variety of geologically plausible and geophysically resolvable subsurface structures for ground-based and airborne electromagnetic systems. The database aims to standardize data for benchmarking and evolving deep learning algorithms in this domain.

Use Cases

• Building surrogate models for electromagnetic inversion processes based on geologically plausible structures.
• Benchmarking deep learning algorithms for electromagnetic data interpretation based on standardized model data.
• Training models for labor-intensive subsurface mapping tasks based on simulated resistivity variations.
• Improving generalization of deep learning models for geophysics based on geophysically constrained data.

Strengths

• Database is described as large-scale, containing a wide variety of subsurface structures.
• Models are geophysically constrained, aiming for consistency and credibility in resulting ML models.
• Covers commonly deployed ground-based and airborne electromagnetic systems.

Limitations

• Row count, file formats, and sample data are unknown, limiting suitability assessment.
• Column-level documentation is absent; field semantics must be inferred after download.
• Last update date is unknown; freshness unverified.

Provenance

Source

Aarhus University, authored by Muhammad Rizwan Asif.

Collection Method

Likely contains simulated or synthetically generated resistivity models of subsurface structures.