• Corpus ID: 235435771

Generating Data Augmentation samples for Semantic Segmentation of Salt Bodies in a Synthetic Seismic Image Dataset

  title={Generating Data Augmentation samples for Semantic Segmentation of Salt Bodies in a Synthetic Seismic Image Dataset},
  author={Luis Felipe M.O. Henriques and S{\'e}rgio Colcher and Ruy Luiz Milidi'u and Andr{\'e} Bulc{\~a}o and Pablo Barros},
Nowadays, subsurface salt body localization and delineation, also called semantic segmentation of salt bodies, are among the most challenging geophysicist tasks. Thus, identifying large salt bodies is notoriously tricky and is crucial for identifying hydrocarbon reservoirs and drill path planning. While several successful attempts to apply Deep Neural Networks (DNNs) have been made in the field, the need for a huge amount of labeled data and the associated costs of manual annotations by experts… 

Figures and Tables from this paper


Semi-Supervised Segmentation of Salt Bodies in Seismic Images using an Ensemble of Convolutional Neural Networks
A semi-supervised method for segmentation (delineation) of salt bodies in seismic images which utilizes unlabeled data for multi-round self-training and outperforms state-of-the-art on the TGS Salt Identification Challenge dataset and is ranked the first among the 3234 competing methods.
Identification of Salt Deposits on Seismic Images Using Deep Learning Method for Semantic Segmentation
The architecture of the proposed network is inspired by the U-Net model in combination with ResNet and DenseNet architectures, and a series of experiments showed that the proposed architecture is comparable and, in most cases, better than these segmentation models.
SaltSeg: Automatic 3D salt segmentation using a deep convolutional neural network
This work has formulated the problem as 3D image segmentation and evaluated an efficient approach based on deep convolutional neural networks with an encoder-decoder architecture that is capable of automatically capturing subtle salt features from the 3D seismic image with less or no need for manual input.
Deep Convolutional Neural Networks for Seismic Salt-Body Delineation*
Salt-bodies are important subsurface structures with significant implications for hydrocarbon accumulation and sealing in offshore petroleum reservoirs, and accurate salt-body imaging and delineation
Automatic Seismic Salt Interpretation with Deep Convolutional Neural Networks
The preliminary result using SEG-SEAM data shows good agreement between the predicted salt body and manually interpreted salt body, especially in areas with weak reflections, indicating the great potential of applying CNN for salt-related interpretations.
Methods to compute salt likelihoods and extract salt boundaries from 3D seismic images
ABSTRACTSalt body interpretation is important for building subsurface models and interpreting seismic horizons and faults that might be truncated by the salt. Salt interpretation often includes two
Convolutional neural networks for automated seismic interpretation
The intuition behind convolutional neural networks, a method revolutionizing the field of image analysis and pushing the state of the art, is looked into and considerations that must be made in order to make the method reliable are discussed.
FaultSeg3D: Using synthetic data sets to train an end-to-end convolutional neural network for 3D seismic fault segmentation
Multiple field examples indicate that the neural network (trained by only synthetic data sets) can predict faults from 3D seismic images much more accurately and efficiently than conventional methods.
Real-time seismic-image interpretation via deconvolutional neural network
Seismic interpretation is now serving as a fundamental tool for depicting subsurface geology and assisting activities in various domains, such as environmental engineering and petroleum exploration.
SalSi: A new seismic attribute for salt dome detection
This work aims to highlight the parts of the seismic volume that receive highest attention from the human interpreter, and based on the salient features of a seismic image, SalSi, to detect salt dome bodies within seismic volumes is proposed.