Title | Delineating the controlling factors of hydraulic fracturing-induced seismicity in the Northern Montney Play, northeastern British Columbia, Canada, with machine learning |
| |
Author | Wang, B; Kao, H ;
Dokht, R M H; Visser, R; Yu, H |
Source | Seismological Research Letters 2022 p. 1-12, https://doi.org/10.1785/0220220075 |
Image |  |
Year | 2022 |
Alt Series | Natural Resources Canada, Contribution Series 20220008 |
Publisher | Seismological Society of America |
Document | serial |
Lang. | English |
Media | paper; on-line; digital |
File format | pdf |
Province | British Columbia |
NTS | 94A/03; 94A/04; 94A/05; 94A/06; 94A/13; 94A/14; 94A/11; 94A/12; 94H/03; 94H/04; 94H/05; 94H/06; 94H/13; 94H/14; 94H/11; 94H/12; 94B/01; 94B/02; 94B/07; 94B/08; 94B/09; 94B/10; 94B/15; 94B/16; 94G/01; 94G/02;
94G/07; 94G/08; 94G/09; 94G/10; 94G/15; 94G/16 |
Lat/Long WENS | -123.0000 -121.0000 58.0000 56.0000 |
Subjects | tectonics; earthquakes; seismicity; models; seismic models; Montney Formation; Western Canadian Sedimentary Basin; machine learning |
Illustrations | location maps; figures; plots |
Program | Environmental Geoscience Shale Gas - induced seismicity |
Released | 2022 05 31 |
Abstract | Recent studies confirm that the distribution of injection-induced earthquakes (IIE) can be related to both natural (e.g., tectonic, geological, and hydrological) settings and operational details.
However, the relative importance of operational factors with respect to the natural ones has not been fully understood for the western Canada sedimentary basin. In this study, we train the eXtreme Gradient Boosting (XGBoost) machine-learning
algorithm to comprehensively evaluate six geological and seven industrial operational factors suspected to be correlated with the distribution of IIE in the northern Montney play (NMP), British Columbia. We then derive the Shapley Additive
Explanations values to quantitatively interpret the outputs from XGBoost. Our results reveal that operational and geological factors have comparable contributions to the IIE distribution. The top four features that contribute most to the seismicity
pattern are horizontal distance to the Cordilleran deformation front, cumulative injected volume, shut-in pressure and vertical distance to the Debolt formation (with respect to the hydraulic fracturing [HF] depth). Features with secondary influence
are the thickness of the Montney formation, breakdown pressure, cumulative fault length per unit area, and vertical distance to the basement (with respect to the HF depth). Other remaining features (e.g., the average treating pressure and injection
rate) appear the least related. Our results provide critical information to establishing a comprehensive susceptibility model that includes key geological and operational factors affecting the IIE distribution in the NMP area. |
Summary | (Plain Language Summary, not published) Recent studies confirm that the distribution of injection-induced earthquakes (IIE) can be related to both natural settings (such as regional geology)
and operational details (such as injection pressure and rate). However, the relative importance of operational factors with respect to the natural ones has not been systematically investigated for the Western Canada Sedimentary Basin. In this study,
we use a machine-learning algorithm, namely XGBoost, to comprehensively evaluate six geological and seven industrial operational factors suspected to be correlated with the distribution of IIE in northern Montney play (NMP), British Columbia. Our
results reveal that both operational and geological factors have comparable contributions to the IIE distribution. The top four features that contribute most to the seismicity pattern are horizontal distance to the Cordilleran deformation front,
cumulative injected volume, shut-in pressure and vertical distance to the Debolt formation. Our results provide critical information to establishing a comprehensive susceptibility model that includes key geological and operational factors affecting
the IIE distribution in the NMP area. |
GEOSCAN ID | 329940 |
|
|