Data-driven feature engineering and machine learning for analysis of distributed sensing data

A system, comprising:

• a distributed sensing system having sensors distributed along different depths of a wellbore formed in a subsurface formation;
• a processor;
• and
• a non-transitory computer readable medium having instructions stored thereon that are executable by the processor to cause the processor,
• receive measurements of data from the distributed sensing system;
• perform dynamic mode decomposition of the data to output a number of modes, wherein each mode includes a subset of the data that quantifies behavior of at least one of a fluid in the subsurface formation and a rock in the subsurface formation on a different combination of locations in the wellbore and timing of the measurements, wherein the dynamic mode decomposition is performed simultaneously to consider both spatial and temporal variation of the data during hydraulic fracturing or a production process;
• and
• select a first mode of the number of modes;
• quantify, based at least in part on the first mode, the behavior in the wellbore;
• and
• provide said quantification to a wellbore operator for updating operational parameters to a wellbore operation during hydraulic fracturing or production operations.

A non-transitory, computer-readable medium having instructions stored thereon that are executable by a processor to perform operations comprising:

• receiving data of measurements from a distributed sensing system having sensors distributed along different depths of a wellbore formed in a subsurface formation;
• performing dynamic mode decomposition of the data to output a number of modes, wherein each mode includes a subset of the data that quantifies behavior of at least one of a fluid in the subsurface formation and a rock in the subsurface formation on a different combination of locations in the wellbore and timing of the measurements, wherein the dynamic mode decomposition is performed simultaneously to consider both spatial and temporal variation of the data during hydraulic fracturing or a production process;
• and
• selecting a first mode of the number of modes;
• quantifying, based at least in part on the first mode, the behavior in the wellbore;
• and
• providing said quantification to a wellbore operator for updating operational parameters to a wellbore operation during hydraulic fracturing or production operations.