CPC G01V 1/306 (2013.01) [G01V 1/302 (2013.01); G01V 1/308 (2013.01); G06N 3/084 (2013.01); G01V 2210/612 (2013.01); G01V 2210/614 (2013.01); G01V 2210/641 (2013.01); G01V 2210/642 (2013.01)] | 19 Claims |
1. A method for training a backpropagation-enabled segmentation process for identifying an occurrence of a subsurface feature, 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 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 prediction of the occurrence of the subsurface feature from the upscaled array, wherein the prediction has a prediction dimension of at least 1 and is at least 1 dimension less than the input dimension.
|