This study presents the first demonstration of the transferability of a convolutional neural network (CNN) trained to detect microseismic events in one fiber-optic distributed acoustic sensing (DAS) data set to other data sets. DAS is being increasingly used for microseismic monitoring in industrial settings, and the dense spatial and temporal sampling provided by these systems produces large data volumes (approximately 650 GB/day for a 2 km long cable sampling at 2000 Hz with a spatial sampling of 1 m), requiring new processing techniques for near-real-time microseismic analysis. We have trained the CNN known as YOLOv3, an object detection algorithm, to detect microseismic events using synthetically generated waveforms with real noise superimposed. The performance of the CNN network is compared to the number of events detected using filtering and amplitude threshold (short-term average/long-term average) detection techniques. In the data set from which the real noise is taken, the network is able to detect >80% of the events identified by manual inspection and 14% more than detected by standard frequency-wavenumber filtering techniques. The false detection rate is approximately 2% or one event every 20 s. In other data sets, with monitoring geometries and conditions previously unseen by the network, >50% of events identified by manual inspection are detected by the CNN.

Fiber-optic distributed acoustic sensing (DAS) cables are now used to monitor microseismicity during hydraulic-fracture stimulations of unconventional gas reservoirs. Unlike geophone arrays, DAS systems are sensitive to uniaxial strain or strain rate along the fiber direction and thus provide a 1C recording, which makes identifying the directionality and polarization of incoming waves difficult. Using synthetic examples, we have shown some fundamental characteristics of microseismic recordings on DAS systems for purposes of hydraulic fracture monitoring in a horizontal well in anisotropic (vertical transverse isotropy [VTI]) shales. We determine that SH arrivals dominate the recorded signals because their polarization is aligned along the horizontal cable at the near offset, although SV will typically dominate for events directly above or below the array. The amplitude of coherent shear-wave (S-wave) arrivals along the cable exhibits a characteristic pattern with bimodal peaks, the width of which relates to the distance of the event from the cable. Furthermore, we find that S-wave splitting recorded on DAS systems can be used to infer the inclination of the incoming waves, overcoming a current limitation of event locations that have constrained events to lie in a horizontal plane. Low-amplitude SV arrivals suggest an event depth similar to that of the DAS cable. Conversely, steep arrivals produce higher amplitude SV-waves, with S-wave splitting increasing with offset along the cable. Finally, we determine how polarity reversals observed in the P and SH phases can be used to provide strong constraints on the source mechanisms.

Distributed ber-optic sensing, and speci cally the introduction of intelligent distributed acoustic sensing (DAS), has gained the attention of production engineers with the promise of a versatile and cost-effective decisionsupport tool. These systems can either be permanently installed, or temporarily deployed using diverse types of intervention systems. This article covers the principles of ow allocation using distributed sensing and show how these can be used and combined to identify uid-entry points, quantify production and identify uid phases. We will describe the methods used to improve quantitative interpretation from distributed sensing, especially the use of phase-coherent DAS for quantitative measurement of sound speed and its use in analyzis of ow velocity and uid phase. While early DAS systems were previously limited in their ow-detection thresholds we have recently introduced a new sensing system, bringing a 20dB (100×) improvement in signal-to-noise. This offers a signi cant improvement in measurement and associated interpretation capability.

No abstract

No abstract