Journal
GEOPHYSICS
Volume 87, Issue 3, Pages N45-N61Publisher
SOC EXPLORATION GEOPHYSICISTS - SEG
DOI: 10.1190/geo2021-0568.1
Keywords
-
Categories
Funding
- Stanford Center for Earth Resources Forecasting (SCERF)
- School of Earth, Energy, and Environmental Sciences at Stanford University
Ask authors/readers for more resources
Deep learning applications in seismic reservoir characterization often require synthetic data generation. The article discusses a method for generating synthetic training data and highlights practical issues when training models on synthetic seismic data, using a real case study as an example.
Deep learning (DL) applications of seismic reservoir characterization often require the generation of synthetic data to augment available sparse labeled data. An approach for generating synthetic training data consists of specifying probability distributions modeling prior geologic uncertainty on reservoir properties and forward modeling the seismic data. A prior falsification approach is critical to establish the consistency of the synthetic training data distribution with real seismic data. With the help of a real case study of facies classification with convolutional neural networks (CNNs) from an offshore deltaic reservoir, we have highlighted several practical nuances associated with training DL models on synthetic seismic data. We highlight the issue of overfitting of CNNs to the synthetic training data distribution and prothe efficacy of our proposed strategies by training the CNN on synthetic data and making robust predictions with real 3D partial stack seismic data.
Authors
I am an author on this paper
Click your name to claim this paper and add it to your profile.
Reviews
Recommended
No Data Available