Quantifying Fracture Networks Inferred From Microseismic Point Clouds by a Gaussian Mixture Model With Physical Constraints.

Microseismicity is generated by slip on fractures and faults and can be used to infer natural or anthropogenic deformation processes in the subsurface. Yet identifying patterns and fractures from microseismic point clouds is a major challenge that typically relies on the skill and judgment of practitioners. Clustering has previously been applied to tackle this problem, but with limited success. Here, we introduce a probabilistic clustering method to identify fracture networks, based on a Gaussian mixture model algorithm with physical constraints. This method is applied to a rich microseismic data set recorded during the hydraulic fracturing of eight horizontal wells in western Canada. We show that the method is effective for distinguishing hydraulic‐fracture‐created events from induced seismicity. These fractures follow a log‐normal distribution and reflect the physical mechanisms of the hydraulic fracturing process. We conclude that this method has wide applicability for interpreting natural and anthropogenic processes in the subsurface. Plain Language Summary: This paper presents a method for inferring fractures from numerous small‐magnitude earthquakes (microseismicity) recorded during a hydraulic fracturing program in an oil and gas reservoir. This method probabilistically clusters microseismic events into a network of fractures after reclassifying them into stages and applying physical constraints. It is superior to previously published clustering algorithms for this purpose. It also allows us to distinguish fractures created by hydraulic fracturing from those triggered on preexisting faults (induced seismicity). This information is essential for assessing both natural and triggered earthquakes and helps us understand deformation processes in the Earth. Key Points: A clustering method with a Gaussian mixture model and physical constraints can identify fracture networks based on microseismic point cloudsUsing physical constraints, this method can distinguish hydraulic‐fracturing‐created microseismicity from induced seismicity (slip on faults)The quantified fracture network follows a log‐normal distribution and reveals the physical mechanisms of hydraulic fracturing [ABSTRACT FROM AUTHOR]