A growing machine learning approach to optimize use of prestack and poststack seismic data

Hami-Eddine, Kamal; Ribet, Bruno de; Durand, Patrick; Gascue, Patxi

doi:10.1190/segam2017-17767532.1

Cited by 5 publications

(2 citation statements)

References 3 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Besides the conventional post-stack data used for interpretation, geophysicists are turning their attention to the prestack data. For example, Hami-Eddine et al [72] investigated a machine learning approach to optimize the use of both prestack and post-stack seismic data. Araya-Polo et al [73] and [74] proposed using a deep neural network to learn a mapping relationship between the raw seismic data and the subsurface geology so that the labor-intensive processing stage could be avoided.…”

Section: B Building Blocksmentioning

confidence: 99%

Subsurface Structure Analysis Using Computational Interpretation and Learning: A Visual Signal Processing Perspective

AlRegib

Deriche

Long

et al. 2018

IEEE Signal Process. Mag.

View full text Add to dashboard Cite

Understanding Earth's subsurface structures has been and continues to be an essential component of various applications such as environmental monitoring, carbon sequestration, and oil and gas exploration. By viewing the seismic volumes that are generated through the processing of recorded seismic traces, researchers were able to learn from applying advanced image processing and computer vision algorithms to effectively analyze and understand Earth's subsurface structures. In this paper, first, we summarize the recent advances in this direction that relied heavily on the fields of image processing and computer vision. Second, we discuss the challenges in seismic interpretation and provide insights and some directions to address such challenges using emerging machine learning algorithms.Keywords subsurface imaging and exploration, seismic interpretation, digital signal processing, machine learning, human visual system, visual analytics

show abstract

Section: B Building Blocksmentioning

confidence: 99%

Subsurface Structure Analysis Using Computational Interpretation and Learning: A Visual Signal Processing Perspective

AlRegib

Deriche

Long

et al. 2018

IEEE Signal Process. Mag.

View full text Add to dashboard Cite

show abstract

“…; Di, Shafiq and AlRegib , ; Hami‐Eddine et al . ; Huang, Dong and Clee ; Lin et al . ; Di, Wang and AlRegib ; Wang et al .…”

Section: Introductionmentioning

confidence: 99%

Semi‐automatic fault/fracture interpretation based on seismic geometry analysis

AlRegib

2019

Geophysical Prospecting

View full text Add to dashboard Cite

A B S T R A C TFault and fracture interpretation is a fundamental but essential tool for subsurface structure mapping and modelling from 3D seismic data. The existing methods for semi-automatic/automatic fault picking are primarily based on seismic discontinuity analysis that evaluates the lateral changes in seismic waveform and/or amplitude, which is limited by its low resolution on subtle faults and fractures without apparent vertical displacements in seismic images. This study presents an innovative workflow for computer-aided fault/fracture interpretation based on seismic geometry analysis. First, the seismic curvature and flexure attributes are estimated for highlighting both the major faults and the subtle fractures in a seismic volume. Then, fault probability is estimated from the curvature and flexure volumes for differentiation between the potential faults and non-faulting features in the geometric attributes. Finally, the seeded fault picking is implemented for interpreting the target faults and fractures guided by the knowledge of interpreters to avoid misinterpretation and artefacts in the presence of faulting complexities as well as coherent seismic noises. Applications to two 3D seismic volumes from the Netherlands North Sea and the offshore New Zealand demonstrate the added values of the proposed method in imaging and picking the subtle faults and fractures that are often overlooked in the conventional seismic discontinuity analysis and the following fault-interpretation procedures.

show abstract

An introduction to distributed training of deep neural networks for segmentation tasks with large seismic data sets

2021

View full text Add to dashboard Cite

Deep learning applications are drastically progressing in seismic processing and interpretation tasks. However, the majority of approaches subsample data volumes and restrict model sizes to minimise computational requirements. Subsampling the data risks losing vital spatio-temporal information which could aid training whilst restricting model sizes can impact model performance, or in some extreme cases, renders more complicated tasks such as segmentation impossible. This paper illustrates how to tackle the two main issues of training of large neural networks: memory limitations and impracticably large training times. Typically, training data is preloaded into memory prior to training, a particular challenge for seismic applications where data is typically four times larger than that used for standard image processing tasks (float32 vs. uint8). Using a microseismic use case, we illustrate how over 750 GB of data can be used to train a model by using a data generator approach which only stores in memory the data required for that training batch. Furthermore, efficient training over large models is illustrated through the training of a 7-layer UNet with input data dimensions of 4096×4096 (approximately 7.8 M parameters). Through a batch-splitting distributed training approach, training times are reduced by a factor of four. The combination of data generators and distributed training removes any necessity of data 1 subsampling or restriction of neural network sizes, offering the opportunity of utilisation of larger networks, higher-resolution input data or moving from 2D to 3D problem spaces.

show abstract

A growing machine learning approach to optimize use of prestack and poststack seismic data

Cited by 5 publications

References 3 publications

Subsurface Structure Analysis Using Computational Interpretation and Learning: A Visual Signal Processing Perspective

Subsurface Structure Analysis Using Computational Interpretation and Learning: A Visual Signal Processing Perspective

Semi‐automatic fault/fracture interpretation based on seismic geometry analysis

An introduction to distributed training of deep neural networks for segmentation tasks with large seismic data sets

Contact Info

Product

Resources

About