A method includes generating a seismic shot by a seismic source, the seismic shot directed at a geological subsurface, and receiving, by one or more receivers, a plurality of reflected seismic traces from the seismic shot. The method further includes generating a correlogram of each reflected seismic trace to generate a plurality of correlograms, isolating a coda wave train of each correlogram of the plurality of correlograms, and computing an energy ratio between an energy of the coda wave train of each correlogram and a total energy of a corresponding correlogram of the plurality of correlograms to generate a plurality of energy ratios. The method further includes determining an average of the plurality of energy ratios to generate an average energy ratio of the seismic shot and determining a likelihood of striking a subsurface geohazard when drilling into the geological subsurface based on the average energy ratio.

Strata surfaces can be identified in well logs and correlated across the well logs taking into account manual corrections. For example, a computing device can receive well logs. The computing device can determine multiple stratum-surface correlations based on the well logs. Then, the computing device can receive user input indicating a correction to a particular stratum-surface correlation. Based on the correction to the particular stratum-surface correlation, the computing device can update some or all of the other stratum-surface correlations.

Strata surfaces can be identified in well logs and correlated across the well logs taking into account manual corrections. For example, a computing device can receive well logs. The computing device can determine multiple stratum-surface correlations based on the well logs. Then, the computing device can receive user input indicating a correction to a particular stratum-surface correlation. Based on the correction to the particular stratum-surface correlation, the computing device can update some or all of the other stratum-surface correlations.

A method and apparatus for machine learning for use with automated seismic interpretation include: obtaining input data; extracting patches from a pre-extraction dataset based on the input data; transforming data of a pre-transformation dataset based on the input data and geologic domain knowledge and/or geophysical domain knowledge; and generating augmented data from the extracted patches and the transformed data. A method and apparatus for machine learning for use with automated seismic interpretation include: a data input module configured to obtain input data; a patch extraction module configured to extract patches from a pre-extraction dataset that is based on the input data; a data transformation module configured to transform data from a pre-transformation dataset that is based on the input data and geologic domain knowledge and/or geophysical domain knowledge; and a data augmentation module configured to augment data from the extracted patches and the transformed data.

A method for interpreting seismic data includes receiving seismic data that represents a subterranean volume, and generating inline probability values and crossline probability values using a first machine learning technique. The first machine learning technique is trained to identify one or more vertical fault lines in a seismic volume based on the seismic data. The method includes generating a merged data set by combining the inline probability values and the crossline probability values, training a second machine learning technique based on a subset of labeled horizontal planes from the merged data set, the second machine learning technique trained to identify horizontal fault lines from the seismic volume, and generating a representation of the seismic volume based on the second machine learning technique, the representation including an indication of a three-dimensional fault structure within the seismic volume.

A method for interpreting seismic data includes receiving seismic data that represents a subterranean volume, and generating inline probability values and crossline probability values using a first machine learning technique. The first machine learning technique is trained to identify one or more vertical fault lines in a seismic volume based on the seismic data. The method includes generating a merged data set by combining the inline probability values and the crossline probability values, training a second machine learning technique based on a subset of labeled horizontal planes from the merged data set, the second machine learning technique trained to identify horizontal fault lines from the seismic volume, and generating a representation of the seismic volume based on the second machine learning technique, the representation including an indication of a three-dimensional fault structure within the seismic volume.

Downhole display systems and methods. A display of one or more portions of a well log of a well during drilling may be displayed together with a display of one or more portions of one or more reference well logs, which may be presented as projected onto one or more planes, respectively. The logs may be segmented and correlated, with the segments or correlated portions displayed in different colors. A user may manipulate the display of the logs or log segments to assist in correlating them. The user may also manipulate the display so that the view provided of the wellbore and the projected logs changes in any one or all of three dimensions. In addition, the user may manipulate the display by navigating along the length of the borehole to view the projected logs at any point along the well path.

Methods of identifying a subterranean tunnel using digital imaging that may include: obtaining data of a propagating wavefield through a propagating volume that includes a portion of the earth's subsurface; obtaining a reference digital image of the propagating volume; selecting a holographic computational method of wavefield imaging; selecting a wavefield based on one or more parameters; calculating a sampling ratio by dividing a number of data samples in the data subset by a number of image samples in the data subset; decimating the data subset; generating a new digital image based on the selected holographic computational method of imaging, the decimated data subset, and parameters corresponding to the data subset; determining a quantitative difference measure between the reference digital image and the new digital image, and image quality; and identifying the subterranean tunnel.

A method, apparatus, and program product may model a subsurface formation by computing an iso-surface for an iso-value from a three-dimensional stratigraphic function (436) for a volume of interest in the subsurface formation, computing first and second strike traces (454, 456) following a topography of the computed iso-surface on respective first and second sides of a fault (452) in the volume of interest, extracting seismic data (458, 460) along the first and second strike traces, correlating the extracted seismic data along the first and second strike traces, and computing a fault displacement vector (C) for the fault from the correlated extracted seismic data along the first and second strike traces.

Systems and methods of placing wells in a hydrocarbon field based on seismic attributes and quality indicators associated with a subterranean formation of the hydrocarbon field can include receiving seismic attributes representing the subterranean formation and seismic data quality indicators. A cutoff is generated for each seismic attribute and seismic data quality indicator. A weight is assigned to each seismic attribute and seismic data quality indicator. The weighted seismic attributes and data quality indicators are aggregated for each location in the hydrocarbon field. A risk ranking is assigned based on the weighted seismic attributes and data quality indicators associated with each location in the hydrocarbon field based on the cutoffs. A map is generated with each location on the surface of the subterranean formation color-coded based on its assigned risk ranking.