System and method of predicting gas saturation of a formation using neural networks
AssigneeHalliburton Energy Services, Inc.
InventorsDingding Chen, Weijun Guo, Larry A. Jacobson
Life of this patent
Estimating the term…
Abstract
Predicting gas saturation of a formation using neural networks. At least some of the illustrative embodiments include obtaining a gamma count rate decay curve one each for a plurality of gamma detectors of a nuclear logging tool (the gamma count rate decay curves recorded at a particular borehole depth), applying at least a portion of each gamma count rate decay curve to input nodes of a neural network, predicting a value indicative of gas saturation of a formation (the predicting by the neural network in the absence of a formation porosity value supplied to the neural network), and producing a plot of the value indicative of gas saturation of the formation as a function of borehole depth.
Claims20
A method comprising:
- obtaining a gamma count rate decay curve one each for a plurality of gamma detectors of a nuclear logging tool, the gamma count rate decay curves recorded at a particular borehole depth;
- applying at least a portion of each gamma count rate decay curve to input nodes of a neural network;
- predicting by the neural network a value indicative of gas saturation of a formation surrounding the borehole at the particular borehole depth, the predicting by the neural network in the absence of a formation porosity value supplied to the neural network;
- repeating the obtaining, applying and predicting for a plurality of borehole depths;
- producing a plot of the value indicative of gas saturation of the formation as a function of borehole depth.
A system comprising:
- a downhole tool comprising a source of neutrons and a plurality of gamma detectors, each gamma detector counts gamma arrivals to create a gamma count rate decay curve for the respective gamma detector, each gamma count rate decay curve comprising a plurality of time bins with respective count values;
- a computer system comprising a processor and a memory, the computer system communicatively coupled to recorded gamma count rate decay curves;
- the memory stores a program that, when executed by the processor, causes the processor to:
- apply at least a portion of each gamma count rate decay curve to input nodes of a neural network of the program;
- and
- predict by the neural network a value indicative of gas saturation of a formation surrounding the borehole for each of a plurality of depths within the borehole, the prediction by the neural network in the absence of a formation porosity value supplied to the neural network.
A non-transitory computer-readable storage media storing a program that, when executed by a processor, causes the processor to:
- obtain a gamma count rate decay curve for each of a plurality of gamma detectors, each gamma count rate decay curve comprising a plurality of count values for a respective plurality of time bins;
- apply at least a portion of each gamma count rate decay curve to input nodes of a neural network implemented by the program;
- and
- generate by the neural network implemented by the program a predicted value indicative of gas saturation of a formation surrounding the borehole, the prediction by the neural network in the absence of a formation porosity value supplied to the neural network.
Dependencies are inferred from the claim text.