66 D2. Energy Geology

Tuesday, 27 October 2020
1:30 PM - 5:30 PM
Meeting Rooms

AN ANALYSIS OF THE CLINTON OIL AND GAS FIELDS IN NE OHIO USING MACHINE LEARNING TO HIGHLIGHT GEOLOGIC CLUSTERS AND PREDICT PRODUCTION

Paper number: 66-3
Program: Technical Sessions
Time: 1:50 PM – 2:05 PM

Authors

Abstract

In the oil and gas industry, having an understanding of subsurface rock properties and the production they may yield is of great importance to finding new, sustaining prospects. Staying on the forefront of innovation and technological advances to maintain an edge on such geologic knowledge is just as important. Machine learning, specifically Esri’s clustering analyses and Forest-based Regression and Classification, is one technology that gives an edge. These analyses were performed on a subset of wells in the Ohio Clinton fields, a highly drilled and data rich area, to uncover patterns and additional information about the area that had been missed previously.

Each well had an attribute profile of six geologic log values (Neutron and density Porosity, bulk density, gamma ray, resistivity and sonic). ESRI’s Multivariate Clustering and Spatially Constrained Multivariate Clustering were run to determine if clustering is highlighted among the wells. Anticipated results are that some clusters will occur along structures, and in some areas where similarities may not have initially been anticipated. These clusters were then compared to average production to determine an optimal range of values for each attribute for the random-forest analysis. Finally, individual surfaces were interpolated for each attribute value in the dataset. These surfaces were the input for the random-forest analysis to predict production in planned well locations within new exploration areas and wells that lack production information so that further insight into drilled areas could be gained. The final and complete workflow will be employed in other areas of exploration to help generate new prospects.

Geological Society of America Abstracts with Programs. Vol. 52, No. 6

doi: 10.1130/abs/2020AM-354082

© Copyright 2020 The Geological Society of America (GSA), all rights reserved. Permission is hereby granted to the author(s) of this abstract to reproduce and distribute it freely, for noncommercial purposes. Permission is hereby granted to any individual scientist to download a single copy of this electronic file and reproduce up to 20 paper copies for noncommercial purposes advancing science and education, including classroom use, providing all reproductions include the complete content shown here, including the author information. All other forms of reproduction and/or transmittal are prohibited without written permission from GSA Copyright Permissions.