Back to results
US 2026/0259957 A1Published application
Clusterization of nmr 2d maps using water level separation method & automated fluid interpretation using fluid interpretation mask
AssigneeSchlumberger Technology Corporation
InventorsGeorge Alexis Bordakov, Evgeny Karpekin
Life of this patent
Estimating the term…
Abstract
Aspects describe methods and apparatus to evaluate nuclear magnetic resonance data maps to identify structures and fluids within a geological stratum or series of geological stratum in an automatic fashion.
Claims20
A method for analyzing a two dimensional nuclear resonance map comprising:
- i) choosing a dataset as a reference;
- ii) performing blind source separation with non-negative matrix factorization, followed by water level separation on the reference dataset;
- iii) calculating residual misfits for each number factor;
- iv) analyzing the calculated residual misfits;
- v) determining a recommended number of factors;
- vi) calculating confidence intervals for the calculated residual misfits;
- vii) comparing the calculated residual misfits with the calculated confident intervals;
- and
- viii) determining non-negative weights for the determined blind source separation factors and feasibly water level separation clusters.
6 more elements
A method comprising:
- performing a blind source separation technique for a different number of factors;
- calculating residual misfits for the different number of factors, wherein several types of misfit characteristics in addition to residual variance are calculated;
- estimating a number of factors for each type of misfit characteristics via exhausting the entire useful signal;
- computing a misfit linear regression for the number of factors corresponding to noise with regression confidence intervals;
- based on the regression confidence intervals, separating factors corresponding to fluids from the factors corresponding to a noise;
- estimating a proper number of factors for each type of misfit characteristic;
- analyzing failures from the estimated proper number of factors;
- and
- combining all non-failed proper number of factors for all misfit types with one of refined and non-refined factors.
6 more elements
A method, comprising:
- loading a map as a two-dimensional array of shape;
- raveling the array into a one-dimensional array of shape;
- sorting the array by values from highest to lowest;
- sorting an array of original coordinates by a same sorting order as the sorting of the array by values from highest to lowest;
- iterating, in a loop, through all remaining pair-values in the original coordinate array;
- taking next point-candidates from the original coordinate array;
- calculating a Euclidean distance between a new 2-value coordinate point candidate to all coordinate points in a summit array;
- determining if the Euclidean distances calculated are greater than a square root of 2 and when such determination is true, then noting that a candidate is not adjacent to any previously identified island-summits and when the Euclidean distances calculated are not true, proceeding to a next point in the array of original coordinates;
- inferring a number of identified clusters;
- allocating an empty array for each identified cluster;
- populating every identified cluster with a single point-coordinate of a cluster summit from a summit array;
- and
- iterating through all points in the original coordinate array to produce results.
10 more elements
Dependencies are inferred from the claim text.