Data-driven workflow for the preemptive detection of excess water producing wells drilled in unconventional shales

Abstract

Listen

Translate article

The continuous rise in global energy demand requires the production of oil and gas from unconventional shale resources. One major concern for oil and gas producers has been the large volumes of produced water associated with the production of hydrocarbon from the shale resources. Yet, to the level of our knowledge, the source/s of the excess water produced in unconventional shale reservoirs has not been presented in a scientific publication. In this work, we developed a data-driven workflow for identifying potentially high water-producing wells drilled in unconventional shale formation and we identified geophysical signatures that explain the source of excess water production from the wells drilled in unconventional shale reservoirs. To that end, we applied unsupervised learning followed by supervised learning to process five conventional well logs, namely shallow and deep resistivity logs, density porosity logs, neutron porosity logs, and gamma ray logs, from wells drilled in two unconventional shale formations – Gulf Coast and Fort Worth. A novelty of our study is the use of clustering methods to generate pseudo-lithology prior to applying classification techniques for determining excess water producing wells. The data-driven workflow built using 23 wells in Gulf coast basin and 29 wells in Fort Worth basin. Fort Worth (FW) and Gulf Coast (GC) basins in the U.S. are highly productive shale basins that produce 380 million cubic feet of gas and 1.74 million barrels of crude oil every day. Additionally, based on permutation feature ranking and Kendall Tau's associated test, we identified the sources of excess water – highly water-wet and low thermally matured shale present at deep depths in Fort Worth basin, and absence of bituminous, pyrite-bearing shales at deep depths in Gulf Coast basin.