In order to join virtual sessions, you must be registered and logged-in(Were you registered for the in-person meeting in Denver? if yes, just log in.) 
Note: All session times are in Mountain Daylight Time.

Using Machine Learning to Understand Shale Well Related Seismicity.

Authors: David Kramar*, Minnesota State University Moorhead, Jacob Larson, Houston Engineering, Karl Leonard, Minnesota State University Moorhead
Topics: Human-Environment Geography, Geographic Information Science and Systems, Land Use
Keywords: Shale Well, Seismicity,
Session Type: Paper
Presentation File: No File Uploaded


Seismicity related to the injection of waste water from hydraulic fracturing operations is of ongoing interest in the United States. In 2016, 4,672 small-magnitude earthquakes occurred in Oklahoma alone, and Oklahoma now ranks number one for earthquake frequency in the United States. It is thought that this rise in seismicity is a function of waste water disposal (WWD) into Oklahoma’s subsurface near previously inactive fault lines, effectively operating as a lubricant that allows movement of these otherwise inactive faults. Here we model these earthquake frequencies using Geographic Information Systems (GIS) and machine learning statistical processes. Data representing WWD sites considered Area of Interest (AOI) by the Oklahoma Geological Survey (OGS) and Oklahoma Corporation Commission (OCC) were used, as well as 2016 Oklahoma earthquake and fault data. Euclidean distance values from each earthquake to its nearest WWD site, nearest fault, and average fluid injection rate at each nearest AOI WWD site were used to build two non-parametric regression models using Random Forests (RF) and Neural Networks (NN). Results from the analysis indicate (NN R2 = 0.749, RMSE = 0.26; RF R2 = 0.71, RMSE = 0.27) that spatial proximity to AOI WWD sites, fluid injection rates, and relative adjacency to subsurface faults are satisfactory independent variables to model seismicity in the north-central portion of Oklahoma. These results provide further information that may aid in developing more stringent guidelines for dealing with WWD.

Abstract Information

This abstract is already part of a session. View the session here.

To access contact information login