Method for multi-dimensional geophysical data visualization
A method for visualization of multi-dimensional geophysical data involves combining several attributes from multi-dimensional geophysical data or seismic data using color modeling techniques and provides for the interpretation of data more efficiently by a user. A color space is defined and multi-dimensional geophysical data attributes are created along with blending filters, such as asymmetric blending filters. Blended multi-dimensional geophysical data attribute cubes are created from the blending filters and the geophysical data attributes by making a prediction using a deep convolutional neural network trained via a backpropagation-enabled regression process.
1. A method for color mapping attributes from geophysical data, comprising the steps of:
defining a multi-dimensional color space;
defining two or more multi-dimensional geophysical attributes;
defining three or more blending filters, wherein the number of blending filters defined equals the number of axes in the multi-dimensional color space, and wherein the three or more blending filters are defined based, at least in part, on two or more proportions associated with the two or more multi-dimensional geophysical attributes;
defining two or more blending filter weights, wherein the number of blending filter weights corresponds to the number of multi-dimensional geophysical attributes, and wherein each of the two or more blending filter weights uniquely corresponds to one single associated multi-dimensional geophysical attribute of the number of multi-dimensional geophysical attributes;
creating blended geophysical data attributes, wherein the number of blended geophysical data attributes created equals the number of axes in the multi-dimensional color space, and wherein the blended geophysical data attributes are created by combining the two or more multi-dimensional geophysical attributes using the associated two or more blending filter weights, wherein the blended geophysical attributes are created by making a prediction using a deep convolutional neural network trained via a backpropagation-enabled regression process.
2. The method of claim 1 , wherein the two or more multi-dimensional geophysical attributes include at least one of one or more spectral coefficients from three or more spectral sub-bands, one or more adjacent horizon slices from above and below a mapped horizon, and one or more projections along lines with varying slope in a two-dimensional crossplot of multi-component geophysical data.
3. The method of claim 2 , wherein the one or more projections include at least one of compressional and shear components and near and far angle substacks.
4. The method of claim 1 , wherein the three or more blending filters comprise a filter length equal to the number of the two or more multi-dimensional geophysical attributes.
5. The method of claim 1 , wherein the three or more blending filters comprise one or more of a front-loaded filter, a middle-loaded filter, and a back-loaded filter.
6. The method of claim 1 , wherein at least one of the three or more blending filters is an asymmetric blending filter.
7. The method of claim 6 , wherein each of the two or more blending filter weights is defined based, at least in part, on a unique one of the three or more blending filters.
8. The method of claim 1 , wherein the multi-dimensional color space comprises one of an RGB, CIEXYZ, CIELAB, CMYK, HSL, or HSV color space.
9. The method of claim 1 , wherein the backpropagation-enabled regression process is a deep learning process.
10. The method of claim 1 , wherein the backpropagation-enabled regression process is a supervised regression process, wherein the prediction is compared to a result of a conventionally computed technique.
11. The method of claim 1 , wherein the backpropagation-enabled regression process is selected from the group consisting of supervised processes, semi-supervised processes, and combinations thereof.
12. The method of claim 1 , wherein the two or more multi-dimensional geophysical attributes are comprised of geophysical attributes selected from the group consisting of field-acquired data, synthetic data, and combinations thereof.
13. The method of claim 1 , further comprising the step of displaying the blended geophysical data attributes using the multi-dimensional color space, wherein each of the blended geophysical data attributes uniquely corresponds to one of the axes in the multi-dimensional color space.