3D Microseismic Monitoring Using Machine Learning. Issue 3 (6th March 2022)

• Record Type: Journal Article
• Authors: Chen, Yangkang; Saad, Omar M.; Savvaidis, Alexandros; Chen, Yunfeng; Fomel, Sergey
• Is Part Of: Journal of geophysical research. Volume 127:Issue 3(2022)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2022-03-06
• Subjects: Geomagnetism -- Periodicals; Geochemistry -- Periodicals; Geophysics -- Periodicals; Earth sciences -- Periodicals; 551.1
• DOI: 10.1029/2021JB023842
• Languages: English
• ISSNs: 2169-9313

Abstract

Abstract: Microseismic source localization is important for inferring the dynamic status of the subsurface stress field during hydraulic fracturing. Traditional deterministic methods for 3D microseismic source localization require either ray tracing or full waveform modeling, thus are computationally expensive. We propose a very efficient (e.g., within 1 s) microseismic source localization method based on machine learning. First, three‐dimensional (3D) ray tracing is performed with hypothetical event locations and realistic acquisition geometry to calculate the theoretical travel‐times. The theoretical travel‐time differences and the spatial locations of the stations are treated as the input features of the training data set, and the corresponding source locations are used as the labels. The manually or automatically picked arrival time differences between different stations and a reference station after a microseismic event and the actual station locations are fed into the well‐trained model for a fast and accurate location prediction. The proposed method is efficient enough to be widely applied for the real‐time monitoring of hydraulic fracturing. The machine learning model is analogous to 3D grid search but performs 3D ray tracings before the actual localization, and needs to be retrained when applied to a new study area. We use several synthetic tests and a real data example from the Weiyuan hydraulic fracturing experiment in Sichuan, China, to demonstrate the effectiveness of the proposed method. The application of the proposed method to earthquake localization is also demonstrated to be straightforward. Plain Language Summary: Microseismic source localization helps to monitor the dynamic status of the target subsurface area during hydraulic fracturing. In traditional methods, the source location is estimated by either travel‐time‐based or waveform‐based methods in an inversion framework. Most state‐of‐the‐art localization methods are based on a 1D velocity model to be computationally efficient, which sacrifices the location accuracy. When it comes to 3D localization that is more accurate, it requires the 3D ray tracing for travel‐time‐based methods or solving the full wave equation for waveform‐based methods, which are both computationally expensive. Here, we present a very fast and accurate 3D source localization method based on machine learning. The proposed method is conceptually simple and easy to implement, and can hopefully substitute the state‐of‐the‐art methods for real‐time seismic monitoring purposes. Key Points: We develop an automatic method for directly predicting the passive‐source location from arrival times based on machine learning The proposed method can estimate the 3D microseismic source location within 1 s and thus is suitable for real‐time applications The proposed method is validated in 3D synthetic models and real case studies and demonstrated to be faster than traditional methods