Full text loading...
-
Subsurface Temperature Measurement Using Electromagnetic Waves and Machine Learning for Enhanced Oil Recovery
- Publisher: European Association of Geoscientists & Engineers
- Source: Conference Proceedings, 82nd EAGE Annual Conference & Exhibition, Oct 2021, Volume 2021, p.1 - 5
Abstract
Technological advances and depletion of easily extracted oil reserves have led to the development of enhanced oil recovery (EOR) methods that allow significantly more oil to be extracted from a reservoir. An increasingly commonly used technique uses thermal injection, which requires a good knowledge of the subsurface thermal conditions. Temperature observation wells (TOW) are used to measure subsurface temperature profiles, an expensive and invasive process.
We present a noninvasive method for the remote monitoring of subsurface temperature using low frequency radar pulses. Radar surveys were performed at 21 locations near TOWs in an oilfield and returns were correlated, after signal processing to extract the modulation, with measured down hole temperatures by training a feedforward neural network. The results were evaluated by excluding one of the 21 data sets from training and use the remaining 20 data sets to predict the excluded site, resulting in 21 blind tests. We believe results are encouraging, though not yet fully reliable and we discuss avenues for improvements.