Exploration seismic data are heavily manipulated before human interpreters are able to extract meaningful information regarding subsurface structures. This manipulation adds modeling and human biases and is limited by methodological shortcomings. Alternatively, using seismic data directly is becoming possible thanks to deep learning (DL) techniques. A DL-based workflow is introduced that uses analog velocity models and realistic raw seismic waveforms as input and produces subsurface velocity models as output. When insufficient data are used for training, DL algorithms tend to overfit or fail. Gathering large amounts of labeled and standardized seismic data sets is not straightforward. This shortage of quality data is addressed by building a generative adversarial network (GAN) to augment the original training data set, which is then used by DL-driven seismic tomography as input. The DL tomographic operator predicts velocity models with high statistical and structural accuracy after being trained with GAN-generated velocity models. Beyond the field of exploration geophysics, the use of machine learning in earth science is challenged by the lack of labeled data or properly interpreted ground truth, since we seldom know what truly exists beneath the earth's surface. The unsupervised approach (using GANs to generate labeled data)illustrates a way to mitigate this problem and opens geology, geophysics, and planetary sciences to more DL applications.

No abstract

Perforation shots can be recorded by downhole distributed acoustic sensing (DAS) arrays. In this study, we demonstrate that guided waves induced by perforation shots propagate in a low-velocity shale reservoir layer. Such guided waves have a high frequency content of up to 700 Hz and are dispersive, with lower frequencies propagating faster than higher frequencies. They can propagate as P- and S-waves, and their group velocity is higher than their phase velocity. The high temporal and spatial resolution of the DAS array enables unaliased recording despite short wavelengths. The guided waves disappear from the records when the well exits the shale formation. Synthetic modeling predicts their existence for acoustic and elastic cases in simple velocity models. We show that perforation shots from an offset well at a distance of about 270 m can be recorded by the DAS array. Induced guided S-waves undergo significant disturbances while propagating through previously stimulated zones. These disturbances manifest as kinematic and dynamic changes of the recorded wavefield and as scattered events. The nature of the stimulation-induced changes is interpreted as a combination of unknown spatial and temporal effects linked to fluid-filled fractures. Guided waves hold tremendous potential for high-resolution reservoir imaging and should be used in conjunction with conventional DAS arrays and state-of-the-art DAS interrogators.

No abstract