Enhanced surveillance of subsurface operation integrity using neural network analysis of microseismic data

A method for monitoring operation integrity during hydrocarbon production or fluid injection operations, comprising:

• detecting microseismic waves in a subsurface area of operation using a seismic monitoring system;
• receiving, from the seismic monitoring system, microseismic data representative of the microseismic waves;
• processing, with a computer, the microseismic data to obtain a plurality of data panels corresponding to microseismic data measured over a predetermined time interval;
• determining, with a neural network analysis implemented on the computer, whether any of the plurality of data panels includes a noise event or a non-noise event;
• for data panels including a non-noise event, calculating with the computer, for each data panel, trigger values for data traces corresponding to sensor receivers of the microseismic monitoring system;
• selecting with the computer, as a triggered data panel representative of an event, at least one data panel that satisfies predetermined triggering criteria;
• calculating, with the computer, a value for each of at least two event attributes of a plurality of event attributes of the event;
• and
• using, with the computer, a classification algorithm to classify the event into at least one event category of a plurality of event categories based on the values.

A method for monitoring operation integrity during hydrocarbon production or fluid injection operations, comprising:

• detecting microseismic waves in a subsurface area of operation using a seismic monitoring system;
• receiving, from the seismic monitoring system, microseismic data representative of the microseismic waves;
• processing, with a computer, the microseismic data to obtain a plurality of data panels corresponding to microseismic data measured over a predetermined time interval;
• determining, with a neural network analysis implemented on the computer, whether any of the plurality of data panels includes a noise event or a non-noise event;
• for data panels including a non-noise event, calculating with the computer, for each data panel, trigger values for data traces corresponding to sensor receivers of the microseismic monitoring system;
• selecting with the computer, as a triggered data panel, at least one data panel that satisfies predetermined triggering criteria;
• selecting with the computer, as a non-trivial data panel containing microseismic data representative of an event, at least one triggered data panel that satisfies spectral density criteria;
• determining, with the computer, an event location;
• and
• using, with the computer, the event location to classify the event into at least one event category of a plurality of event categories.

A non-transitory computer usable medium having a computer readable program code embodied therein, said computer readable program code adapted to be executed by a computer to implement a method for monitoring operation integrity during hydrocarbon production or fluid injection operations using microseismic data, said method comprising:

• receiving microseismic data representative of microseismic waves in a subsurface area of operation;
• processing the microseismic data to obtain a plurality of data panels corresponding to microseismic data measured over a predetermined time interval;
• determining, with a neural network analysis, whether any of the plurality of data panels includes a noise event or a non-noise event;
• for data panels including a non-noise event, calculating, for each data panel, trigger values for data traces corresponding to sensor receivers of the microseismic monitoring system;
• selecting, as a triggered data panel, at least one data panel that satisfies predetermined triggering criteria;
• selecting, as a non-trivial data panel containing microseismic data representative of an event, at least one triggered data panel that satisfies spectral density criteria;
• calculating a value for each of at least two event attributes of a plurality of event attributes of the event;
• determining an even score based on the values of the plurality of event attributes;
• and
• classifying the event into at least one event category of a plurality of event categories based on the event score.

A method of identifying an event during hydrocarbon production or fluid injection operations using microseismic data, comprising:

• detecting microseismic waves in a subsurface area of operation using a seismic monitoring system;
• receiving, from the seismic monitoring system, microseismic data representative of the microseismic waves;
• determining, with a neural network analysis implemented on a computer, whether any portion of the microseismic data includes a noise event or a non-noise event;
• and
• for portions of the microseismic data including a non-noise event, classifying, with the computer, the event into at least one event category of a plurality of event categories;
• wherein determining whether any portion of the microseismic data includes a noise event or a non-noise event comprises:
• determining a number of data levels to be used in the neural network analysis;
• and
• for each dataset, adjusting a number of data levels associated with each dataset to match the determined number of data levels;
• each dataset being associated with a respective array of seismic receivers;
• using the computer, determining whether a moveout attribute exists for each trace, wherein the moveout attribute comprises the maximum SLR and the location of the maximum SLR;
• using the computer, identifying noise spikes;
• and
• feeding the moveout attribute and the identified noise spikes into the neural network analysis.