US 11,698,471 B2
Method for predicting subsurface features from seismic using deep learning dimensionality reduction for regression
Donald Paul Griffith, Houston, TX (US); Sam Ahmad Zamanian, Houston, TX (US); and Russell David Potter, Houston, TX (US)
Assigned to SHELL USA, INC., Houston, TX (US)
Appl. No. 17/275,309
Filed by SHELL OIL COMPANY, Houston, TX (US)
PCT Filed Sep. 10, 2019, PCT No. PCT/EP2019/074086
§ 371(c)(1), (2) Date Mar. 11, 2021,
PCT Pub. No. WO2020/053199, PCT Pub. Date Mar. 19, 2020.
Claims priority of provisional application 62/730,773, filed on Sep. 13, 2018.
Prior Publication US 2022/0113441 A1, Apr. 14, 2022
Int. Cl. G01V 1/30 (2006.01); G06N 3/084 (2023.01)
CPC G01V 1/307 (2013.01) [G06N 3/084 (2013.01); G01V 2210/63 (2013.01)] 19 Claims
OG exemplary drawing
 
1. A method for training a backpropagation-enabled regression process for predicting values of an attribute of subsurface data, the method comprising the steps of:
(a) inputting a multi-dimensional seismic data set with an input dimension, n, of at least two into a backpropagation-enabled process;
(b) convolving the multi-dimensional seismic data set using convolutional filters learned from the backpropagation-enabled process to produce a set of input feature maps having a convolutional dimension equal to the input dimension;
(c) downscaling the set of input feature maps to produce a downscaled array of modified feature maps using the convolutional filters learned from the backpropagation-enabled process, so that at least one, but no more than n−1, dimension of the downscaled array is one;
(d) upscaling the downscaled array to produce an upscaled array of further modified feature maps using the convolutional filters learned from the backpropagation-enabled process, wherein the upscaled array has the same dimension of the downscaled array, and
(e) computing a predicted value of the attribute from the upscaled array, wherein the predicted value has a prediction dimension of at least 1 and is at least 1 dimension less than the input dimension.