Is CO2 injection at Aquistore aseismic? A combined seismological and geomechanical study of early injection operations

Stork, A.; Nixon, C.; Hawkes, Christopher D.; Birnie, Claire; White, Don; Schmitt, Douglas R.; Roberts, Bruce R.

doi:10.1016/j.ijggc.2018.05.016

Cited by 22 publications

(18 citation statements)

References 66 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…It should be noted here that not all deep learning applications on seismic data require subsampling. For example, should the same segmentation procedure developed in this paper be adapted for a different, smaller permanent array, such as the 50 receiver array at Aquistore (Stork et al, 2018), the input dimensions would be smaller than those used in the original UNet implementation rendering any discussion on subsampling unnecessary.…”

Section: Discussionmentioning

confidence: 99%

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

Section: Discussionmentioning

confidence: 99%

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

show abstract

“…Finally, a real concern surrounding the development of any new event detection procedure is that they can be applied real time. [27] cited this as the reason why new detection approaches are commonly not implemented. Figure 14 illustrates the detection time for a two second window for the three approaches for increasing number of traces † .…”

Section: Discussionmentioning

confidence: 99%

Bidirectional recurrent neural networks for seismic event detection

Birnie¹,

Hansteen²

2020

Preprint

View full text Add to dashboard Cite

Real time, accurate passive seismic event detection is a critical safety measure across a range of monitoring applications from reservoir stability to carbon storage to volcanic tremor detection. The most common detection procedure remains the Short-Term-Average to Long-Term-Average (STA/LTA) trigger despite its common pitfalls of requiring a signal-to-noise ratio greater than one and being highly sensitive to the trigger parameters. Whilst numerous alternatives have been proposed, they often are tailored to a specific monitoring setting and therefore cannot be globally applied, or they are too computationally expensive therefore cannot be run real time. This work introduces a deep learning approach to event detection that is an alternative to the STA/LTA trigger. A bi-directional, long-short-term memory, neural network is trained solely on synthetic traces. Evaluated on synthetic and field data, the neural network approach significantly outperforms the STA/LTA trigger both on the number of correctly detected arrivals as well as on reducing the number of falsely detected events. Its real time applicability is proven with 600 traces processed in real time on a single processing unit.Recently, Machine Learning (ML) methodologies, in particular Deep Learning (DL), has seen a resurgence across all fields of seismology, and wider geoscience applications. The majority of applications have focused on the adaptation of computer vision approaches for aiding seismic interpretation. For example, salt body detection [8], fault detection [9], and horizon detection [10]. However, other studies have considered how ML methodologies can be utilised for seismic event detection. [11] proposed the combination of convolutional Neural Networks (NN) with k-means clustering for detection of seismic arrivals, whilst [12] presents one of the earliest studies that considered using NNs for event detection on broadband seismometers. Novelly, they combined three different back-propagation NNs that

show abstract

“…The magnitude of the deviation of the critical fluid pressure c f P (x,y) on the fault plane from the expected ambient P P (x,y): orientation. Schwab et al (2017), Stork et al (2018), andWeides et al (2014) provide examples of studies that estimate the stability on actual faults or lineaments imaged in 3D reflection seismic volumes, but other studies have used seismicity to outline fault trends (e.g., Eyre et al, 2019;Jia, 2019). To overcome this limitation, we carry out the calculations, with S h , S V , P P , and ϕ values calculated in RD_stress.m and S H using Equation 9, over the study area by first assuming that at each mapped point, the planes of weakness have the same orientation as the most stable Plane 1 (Figure 10) for Event A and then, for the sake of comparison, the hypothetical, optimally oriented plane along which slip would be most likely.…”

Section: Assess Regional Susceptibilitymentioning

confidence: 99%

“…(2017), Stork et al. (2018), and Weides et al. (2014) provide examples of studies that estimate the stability on actual faults or lineaments imaged in 3D reflection seismic volumes, but other studies have used seismicity to outline fault trends (e.g., Eyre et al., 2019; Jia, 2019).…”

Section: Stress Measurements and Fault Stabilitymentioning

confidence: 99%

“…Nevertheless, these reports, attempting to correlate earthquakes temporally and spatially with industrial activities, are primarily statistical in nature. There are very few exceptions based on deterministic geomechanical observations (e.g., Ameen, 2016; Deng et al., 2016; McClure & Horne, 2011; Shen, Schmitt, & Schultz, 2019; Stork et al., 2018).…”

Section: Introductionmentioning

confidence: 99%

See 1 more Smart Citation

States of In Situ Stress in the Duvernay East Shale Basin and Willesden Green of Alberta, Canada: Variable In Situ Stress States Effect Fault Stability

et al. 2021

View full text Add to dashboard Cite

show abstract

Is CO2 injection at Aquistore aseismic? A combined seismological and geomechanical study of early injection operations

Cited by 22 publications

References 66 publications

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

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

Bidirectional recurrent neural networks for seismic event detection

States of In Situ Stress in the Duvernay East Shale Basin and Willesden Green of Alberta, Canada: Variable In Situ Stress States Effect Fault Stability

Contact Info

Product

Resources

About