Classification and Localization of Low-Frequency DAS Strain Rate Patterns with Convolutional Neural Networks

Abstract

Distributed acoustic sensing (DAS) has been used in the oil and gas industry as an advanced technology for surveillance and diagnostics. Operators use DAS to monitor hydraulic fracturing activities, to examine well stimulation efficacy, and to estimate complex fracture system geometries. Particularly, low-frequency DAS can detect geomechanical events such as fracture-hits as hydraulic fractures propagate and create strain rate variations. Analysis of DAS data today is mostly done post-job and subject to interpretation methods. However, the continuous and dense data stream generated live by DAS offers the opportunity for more efficient and accurate real-time data-driven analysis. The objective of this study is to develop a machine learning-based workflow that can identify and locate fracture-hit events in simulated strain rate response that is correlated with low-frequency DAS data. In this paper, "fracture-hit" refers to a hydraulic fracture originated from a stimulated well intersecting an offset well. We start with building a single fracture propagation model to produce strain rate patterns observed at a hypothetical monitoring well. This model is then used to generate two sets of strain rate responses with one set containing fracture-hit events. The labeled synthetic data are then used to train a custom convolutional neural network (CNN) model for identifying the presence of fracture-hit events. The same model is trained again for locating the event with the output layer of the model replaced with linear units. We achieved near-perfect predictions for both event classification and localization. These promising results prove the feasibility of using CNN for real-time event detection from fiber optic sensing data. Additionally, we used image analysis techniques, including edge detection, for recognizing fracture-hit event patterns in strain rate images. The accuracy is also plausible, but edge detection is more dependent on image quality, hence less robust compared to CNN models. This comparison further supports the need for CNN applications in image-based real-time fiber optic sensing event detection.