Creation of a mixed-mode fracture network at meso-scale through hydraulic fracturing and shear stimulation

“…We applied a band-pass filter with corner frequencies of 3 and 20 kHz. Main seismic energy is contained in this wide passband (Schoenball et al, 2020). The frequency filtered seismograms were fed into the neural network for training, which is different from W. Zhu and Beroza (2018).…”

Section: Transfer Learningmentioning

confidence: 99%

“…Our data consist of seismograms from triggered microseismic events between May 2018 and December 2018 at the Experiment 1 site of the EGS Collab project, manually picked P-wave and S-wave arrival times, and the original seismic catalog from Schoenball et al (2020). We used 35 seismic sensors (one hydrophone was defective) with a 100-kHz sampling rate that were deployed in six 60-m-long monitoring wells (supporting information Figure S1).…”

Section: Datamentioning

confidence: 99%

“…We picked all S-wave arrival times manually. Additional details about the monitoring system and data preprocessing procedures of the original seismic catalog can be found in Schoenball et al (2020).…”

Section: Datamentioning

confidence: 99%

“…Seismic event locations and origin times were improved with human reviewed and refined phase picks. The original seismic catalog was processed by Schoenball et al (2020). Several hydraulic stimulations were performed since May 2018.…”

Section: Introductionmentioning

confidence: 99%

See 2 more Smart Citations

Using a Deep Neural Network and Transfer Learning to Bridge Scales for Seismic Phase Picking

Chai

Maceira

Santos-Villalobos

et al. 2020

Geophysical Research Letters

Self Cite

View full text Add to dashboard Cite

The important task of tracking seismic activity requires both sensitive detection and accurate earthquake location. Approximate earthquake locations can be estimated promptly and automatically; however, accurate locations depend on precise seismic phase picking, which is a laborious and time‐consuming task. We adapted a deep neural network (DNN) phase picker trained on local seismic data to mesoscale hydraulic fracturing experiments. We designed a novel workflow, transfer learning‐aided double‐difference tomography, to overcome the 3 orders of magnitude difference in both spatial and temporal scales between our data and data used to train the original DNN. Only 3,500 seismograms (0.45% of the original DNN data) were needed to retrain the original DNN model successfully. The phase picks obtained with transfer‐learned model are at least as accurate as the analyst's and lead to improved event locations. Moreover, the effort required for picking once the DNN is trained is a small fraction of the analyst's.

show abstract

In Situ Continuous Monitoring of Borehole Displacements Induced by Stimulated Hydrofracture Growth

Guglielmi

Cook

Soom

et al. 2021

Geophysical Research Letters

Self Cite

View full text Add to dashboard Cite

We provide direct observations of the three‐dimensional displacements of a fluid‐driven fracture during water injections in a borehole at ∼1.5 km depth in the crystalline rock at the Sanford Underground Research Facility (USA). Micro‐shearing of the borehole initiates on a foliation plane at 61% of the minimum principal stress σ3. As the fluid pressure increases further up to 112% of σ3, borehole axial and radial displacements increase with injection time highlighting the opening and sliding of a new hydrofracture growing ∼10 m away from the borehole, in accordance with the ambient normal stress regime and in alignment with the microseismicity. Our study reveals how important it is to consider monitoring zonal deformation in conjunction with pressure and flow to better manage the complex hydromechanical evolution of the growing fracture.

show abstract

Creation of a mixed-mode fracture network at meso-scale through hydraulic fracturing and shear stimulation

Cited by 6 publications

References 23 publications

In-situ observation of pre-, co- and post-seismic shear slip at 1.5 km depth

In-situ observation of pre-, co- and post-seismic shear slip at 1.5 km depth

Using a Deep Neural Network and Transfer Learning to Bridge Scales for Seismic Phase Picking

In Situ Continuous Monitoring of Borehole Displacements Induced by Stimulated Hydrofracture Growth

Contact Info

Product

Resources

About