Semi-supervised Sequence Modeling for Elastic Impedance Inversion
Not on the map. Why?
Abstract (arXiv)
Recent applications of machine learning algorithms in the seismic domain have shown great potential in different areas such as seismic inversion and interpretation. However, such algorithms rarely enforce geophysical constraints - the lack of which might lead to undesirable results. To overcome this issue, we have developed a semi-supervised sequence modeling framework based on recurrent neural networks for elastic impedance inversion from multi-angle seismic data. Specifically, seismic traces and elastic impedance (EI) traces are modeled as a time series. Then, a neural-network-based inversion model comprising convolutional and recurrent neural layers is used to invert seismic data for EI. The proposed workflow uses well-log data to guide the inversion. In addition, it uses seismic forward modeling to regularize the training and to serve as a geophysical constraint for the inversion. The proposed workflow achieves an average correlation of 98% between the estimated and target EI using 10 well logs for training on a synthetic data set.
Key facts. Cited by 10 papers in the map (data through 14 Oct 2026). First posted on arXiv 19 Aug 2019.
Builds on
No reference list yet.
Built on by
Citing papers per year: 2021: 3; 2022: 2; 2023: 1; 2024: 0; 2025: 2; 2026: 2.
10 papers.
- 2022Volumetric Supervised Contrastive Learning for Seismic Semantic Segmentationcited by 12
- 2023Example Forgetting: A Novel Approach to Explain and Interpret Deep Neural Networks in Seismic Interpretationcited by 4
- 2025A Large-scale Benchmark on Geological Fault Delineation Models: Domain Shift, Training Dynamics, Generalizability, Evaluation and Inferential Behaviorcited by 4
- 2021Self-Supervised Delineation of Geological Structures using Orthogonal Latent Space Projectioncited by 2
- 2021Revisit Geophysical Imaging in A New View of Physics-informed Generative Adversarial Learningcited by 2
- 2021Semi-supervised Impedance Inversion by Bayesian Neural Network Based on 2-d CNN Pre-trainingcited by 1
- 2022Explainable Machine Learning for Hydrocarbon Prospect Riskingcited by 1
- 2025Seismic Acoustic Impedance Inversion Framework Based on Conditional Latent Generative Diffusion Modelcited by 0
- 2026Seismic full-waveform inversion based on a physics-driven generative adversarial networkcited by 0
- 2026Latent Variable-Mediated Cross-Learning for Few-Shot Acoustic Impedance Imagingcited by 0
- 2026Latent Variable-Mediated Cross-Learning for Few-Shot Acoustic Impedance Imaging23 Jul 2026
- 2026Seismic full-waveform inversion based on a physics-driven generative adversarial network16 Mar 2026
- 2025Seismic Acoustic Impedance Inversion Framework Based on Conditional Latent Generative Diffusion Model16 Jun 2025
- 2025A Large-scale Benchmark on Geological Fault Delineation Models: Domain Shift, Training Dynamics, Generalizability, Evaluation and Inferential Behavior13 May 2025
- 2023Example Forgetting: A Novel Approach to Explain and Interpret Deep Neural Networks in Seismic Interpretation24 Feb 2023
- 2022Explainable Machine Learning for Hydrocarbon Prospect Risking15 Dec 2022
- 2022Volumetric Supervised Contrastive Learning for Seismic Semantic Segmentation16 Jun 2022
- 2021Semi-supervised Impedance Inversion by Bayesian Neural Network Based on 2-d CNN Pre-training20 Nov 2021
- 2021Revisit Geophysical Imaging in A New View of Physics-informed Generative Adversarial Learning23 Sep 2021
- 2021Self-Supervised Delineation of Geological Structures using Orthogonal Latent Space Projection22 Aug 2021