Computing system assessment of geological similarity of wells employing well-log data
Computing system assessment of geological similarity of wells employing well-log data includes receiving logs with chronostratigraphic markers, and extracting signatures from the logs using the chronostratigraphic markers. A distance matrix is generated from the signatures using dynamic time warping. Using the distance matrix, a set of clusters are generated. The set of clusters are presented with an image.
1. A method comprising:
receiving a plurality of logs with chronostratigraphic markers;
extracting a plurality of signatures from the plurality of logs using the chronostratigraphic markers;
correlating a set of signatures, from the plurality of signatures, using dynamic time warping to generate a distance matrix from the plurality of signatures,
wherein the set of signatures use a same chronostratigraphic marker from the chronostratigraphic markers, and
wherein the set of signatures are for varying depths;
generating a set of clusters using the distance matrix; and
presenting the set of clusters with an image.
2. The method of claim 1 , further comprising:
identifying two chronostratigraphic markers in a log of the plurality of logs, wherein the two chronostratigraphic markers comprise a start marker and an end marker and correspond to at least two signatures, from the set of signatures, at different depths.
3. The method of claim 2 , further comprising:
extracting a signature of the plurality of signatures from a portion of the log that is between the two chronostratigraphic markers.
4. The method of claim 1 , further comprising:
generating the distance matrix by:
calculating a dynamic time warping distance between each pair of signatures of the plurality of signatures to form a plurality of dynamic time warping distances; and
updating elements of the distance matrix to include the plurality of dynamic time warping distances.
5. The method of claim 1 , further comprising:
identifying the set of clusters by:
generating a cluster for each signature of the plurality of signatures to form the set of clusters; and
determining a pair of clusters with a least distance from the set of clusters.
6. The method of claim 5 ,
wherein identifying the set of clusters further comprises:
generating a combined cluster for the pair of clusters and updating the set of clusters with the combined cluster.
7. The method of claim 6 ,
wherein identifying the set of clusters further comprises:
repeating the determining a pair of clusters and generating a combined cluster until a cluster of the set of clusters includes each of the signatures.
8. The method of claim 1 , further comprising:
presenting the set of clusters by:
filtering the set of clusters with a distance threshold to select clusters with maximum distances that are less than the distance threshold and form a set of filtered clusters.
9. The method of claim 8 ,
wherein presenting the set of clusters further comprises:
assigning a coding scheme to each filtered cluster of the set of filtered clusters.
10. The method of claim 9 ,
wherein presenting the set of clusters further comprises:
presenting the signatures using the coding schemes of the set of filtered clusters.
11. A system comprising:
a memory coupled to a processor;
an analyzer service that executes on the processor, uses the memory, and is configured for:
receiving a plurality of logs with chronostratigraphic markers;
extracting a plurality of signatures from the plurality of logs using the chronostratigraphic markers;
correlating a set of signatures, from the plurality of signatures, using dynamic time warping to generate a distance matrix from the plurality of signatures,
wherein the set of signatures use a same chronostratigraphic marker from the chronostratigraphic markers, and
wherein the set of signatures are for varying depths;
generating a set of clusters using the distance matrix; and
presenting the set of clusters with an image.
12. The system of claim 11 , wherein the analyzer service is further configured for:
identifying two chronostratigraphic markers in a log of the plurality of logs, wherein the two chronostratigraphic markers comprise a start marker and an end marker and correspond to at least two signatures, from the set of signatures, at different depths.
13. The system of claim 12 , wherein the analyzer service is further configured for:
extracting a signature of the plurality of signatures from a portion of the log that is between the two chronostratigraphic markers.
14. The system of claim 11 , wherein the analyzer service is further configured for:
generating the distance matrix by:
calculating a dynamic time warping distance between each pair of signatures of the plurality of signatures to form a plurality of dynamic time warping distances; and
updating elements of the distance matrix to include the plurality of dynamic time warping distances.
15. The system of claim 11 , wherein the analyzer service is further configured for:
identifying the set of clusters by:
generating a cluster for each signature of the plurality of signatures to form the set of clusters; and
determining a pair of clusters with a least distance from the set of clusters.
16. The system of claim 15 ,
wherein identifying the set of clusters further comprises:
generating a combined cluster for the pair of clusters and updating the set of clusters with the combined cluster.
17. The system of claim 16 ,
wherein identifying the set of clusters further comprises:
repeating the determining a pair of clusters and generating a combined cluster until a cluster of the set of clusters includes each of the signatures.
18. The system of claim 11 , wherein the analyzer service is further configured for:
presenting the set of clusters by:
filtering the set of clusters with a distance threshold to select clusters with maximum distances that are less than the distance threshold and form a set of filtered clusters.
19. The system of claim 18 ,
wherein presenting the set of clusters further comprises:
assigning a coding scheme to each filtered cluster of the set of filtered clusters.
20. A non-transitory computer readable medium comprising computer readable program code for:
receiving a plurality of logs with chronostratigraphic markers;
extracting a plurality of signatures from the plurality of logs using the chronostratigraphic markers;
correlating a set of signatures, from the plurality of signatures, using dynamic time warping to generate a distance matrix from the plurality of signatures using dynamic time warping,
wherein the set of signatures use a same chronostratigraphic marker from the chronostratigraphic markers, and
wherein the set of signatures are for varying depths;
generating a set of clusters using the distance matrix; and
presenting the set of clusters with an image.