OpenEM: Large-scale multi-structural 3D datasets for electromagnetic methods

2025-10-23

AI Summary

Existing deep learning research in electromagnetic (EM) geophysics is constrained by manually constructed simplified 3D models and the absence of standardized, publicly available 3D geoelectrical datasets. Method: We introduce OpenEM—the first large-scale, multi-structural, geologically realistic open-source 3D geoelectrical dataset, comprising nine representative subsurface configurations. It innovatively integrates high-fidelity 3D EM forward modeling with a deep learning–driven rapid modeling network to significantly enhance data generation efficiency and generalizability. OpenEM supports forward simulations for diverse EM acquisition systems. Contribution/Results: We publicly release the complete dataset, modular forward simulation code, and pre-trained models. This work bridges the critical gap in high-quality 3D EM training data, enabling reproducible, scalable deep learning applications in geophysical exploration.

Technology Category

• Machine Learning: Deep Neural Architectures and Foundation Models
• Data Mining & Knowledge Management: Linked Open Data, Knowledge Graphs & KB Completion
• Knowledge Representation and Reasoning: Geometric, Spatial, and Temporal Reasoning

Application Category

• Graph Algorithms and Modeling for the Web: Graph neural networks and deep learning approaches for Web-related graphs
• Web Mining and Content Analysis: Web data generation and simulation
• Economics, Online Markets and Human Computation: Data quality aspects of human-annotated datasets

Abstract

With the remarkable success of deep learning, applying such techniques to EM methods has emerged as a promising research direction to overcome the limitations of conventional approaches. The effectiveness of deep learning methods depends heavily on the quality of datasets, which directly influences model performance and generalization ability. Existing application studies often construct datasets from random one-dimensional or structurally simple three-dimensional models, which fail to represent the complexity of real geological environments. Furthermore, the absence of standardized, publicly available three-dimensional geoelectric datasets continues to hinder progress in deep learning based EM exploration. To address these limitations, we present OpenEM, a large scale, multi structural three dimensional geoelectric dataset that encompasses a broad range of geologically plausible subsurface structures. OpenEM consists of nine categories of geoelectric models, spanning from simple configurations with anomalous bodies in half space to more complex structures such as flat layers, folded layers, flat faults, curved faults, and their corresponding variants with anomalous bodies. Since three-dimensional forward modeling in electromagnetics is extremely time-consuming, we further developed a deep learning based fast forward modeling approach for OpenEM, enabling efficient and reliable forward modeling across the entire dataset. This capability allows OpenEM to be rapidly deployed for a wide range of tasks. OpenEM provides a unified, comprehensive, and large-scale dataset for common EM exploration systems to accelerate the application of deep learning in electromagnetic methods. The complete dataset, along with the forward modeling codes and trained models, is publicly available at https://doi.org/10.5281/zenodo.17141981.

Problem

• Addressing lack of standardized 3D geoelectric datasets for EM exploration
• Overcoming limitations of oversimplified models in representing geological complexity
• Providing efficient 3D forward modeling capabilities for electromagnetic methods

Innovation

• Large-scale multi-structural 3D geoelectric dataset
• Deep learning based fast forward modeling approach
• Public dataset with nine geological model categories