Hybrid seismic inversion methods and apparatuses perform wave equation inversion and stochastic inversion to generate one or more final models for the reservoir characterization of the survey region. A method may include retrieving seismic data using seismic data recording sensors; storing the seismic data in the database; retrieving well data using the well born sensor in the wellbore; storing the seismic data in the database; storing geology integration information and one or more background models in the database; retrieving the seismic data and processing the seismic data to mitigate the seismic data for a seismic hybrid inversion; and performing the seismic hybrid inversion including performing wave equation inversion and stochastic inversion to generate the one or more final models for the reservoir characterization of the survey region.

A method may include obtaining various seismic traces for a geological region of interest. The method may further include determining an offset attribute and an azimuthal attribute. The method may further include determining, using the offset attribute and the azimuthal attribute, a virtual trace bin for the geological region of interest. The method may further include generating a virtual trace using a subset of the seismic traces and corresponding to the virtual trace bin. The method may further include generating a velocity model for the geological region of interest using a virtual shot gather including the virtual trace and various virtual traces. A respective virtual trace among the virtual traces may correspond to a respective virtual trace bin among various virtual trace bins. The method may further include generating a seismic image of the geological region of interest using the velocity model.

A global objective function is initialized to an initial value. A particular model simulation process is executed using prepared input data. A mismatch value is computed by using a local function to compare an output of the particular model simulation process to corresponding input data for the particular model simulation process. Model objects associated with the particular model simulation process are sent to another model simulation process. An optimization process is executed to predict new values for input data to reduce the computed mismatch value.

A method, including: generating a velocity model for a subsurface region of the Earth by using a full wavefield inversion process; generating an impedance model for the subsurface region of the Earth by using a full wavefield inversion process; and estimating pore pressure at a prediction site in the subsurface region by integrating the velocity model and the impedance model with a velocity-based pore pressure estimation process.

A method is provided for automatically classifying grains, pores, or both of a formation sample. The method includes receiving a digital image representation of the formation sample, and identifying a plurality of pores, grains, or both in the digital image representation. The method also includes computing a plurality of geometric features associated with the pores, grains, or both in the digital image representation, and inputting the geometric features into an unsupervised machine learning model. The unsupervised machine learning model determines a label for each identified pore and grain, the label being a pore-type or a grain-type, and the plurality of geometric features and the labels determined for each pore, grain, or both, are input into a supervised machine learning model. The supervised machine learning model determines a final classification of a pore-type for each pore and a grain-type for each grain in the digital image representation of the formation sample.

Method for decomposing a complexly shaped object in a data set, such as a geobody (31) in a seismic data volume, into component objects more representative of the true connectivity state of the system represented by the data set. The geobody is decomposed using a basis set of eigenvectors (33) of a connectivity matrix (32) describing the state of connectivity between voxels in the geobody. Lineal subspaces of the geobody in eigenvector space are associated with likely component objects (34), either by a human interpreter (342) cross plotting (341) two or more eigenvectors, or in an automated manner in which a computer algorithm (344) detects the lineal sub-spaces and the clusters within them.

A method and system for modeling a subsurface region include applying a trained machine learning network to an initial petrophysical parameter estimate to predict a geologic prior model; and performing a petrophysical inversion with the geologic prior model, geophysical data, and geophysical parameters to generate a rock type probability model and an updated petrophysical parameter estimate. Embodiments include managing hydrocarbons with the rock type probability model. Embodiments include checking for convergence of the updated petrophysical parameter estimate; and iteratively: applying the trained machine learning network to the updated petrophysical parameter estimate of a preceding iteration to predict an updated rock type probability model and another geologic prior model; performing a petrophysical inversion with the updated geologic prior model, geophysical seismic data, and geophysical elastic parameters to generate another rock type probability model and another updated petrophysical parameter estimate; and checking for convergence of the updated petrophysical parameter estimate.

In an example method, one or more processors receive a plurality of rock fragment images. Each of the rock fragment images represents respective rock fragments obtained from a subsurface formation during well bore drilling. The one or more processors select one or more portions of the rock fragment images, and generate a geological formation image based on the one or more selected portions of the rock fragment images. The geological formation image is indicative of one or more geological characteristics of the subsurface formation along the well bore.

An acoustic logging method includes obtaining first horizontal transverse isotropy (“HTI”) angles resulting from a time domain HTI algorithm. The method further includes obtaining one or more second HTI angles resulting from a frequency domain HTI algorithm. The method further includes generating a first HTI anisotropy log including a relative angle log based on the first and second HTI angles. The method further includes generating a first color map of the first HTI anisotropy log and displaying the first color map.

A rock burst hazard prediction method based on vibration wave energy attenuation characteristics of a mine earthquake cluster is provided. The rock burst hazard prediction method comprehensively considers the static load and dynamic load effects of the vibration waves of the mine earthquake cluster based on vibration wave energy attenuation characteristics of the mine earthquake cluster. The static load strength index and the dynamic load strength index involved in the method have clear physical meanings. A comprehensive prediction index calculation model proposed based on the dynamic and static load superposition principle of rock burst occurrence is clear, and the method has a firm theoretical support as well as strong universality and operability. Meanwhile, the updating and adjustment of weights are rapid and the objective judgment and prediction of the final comprehensive prediction results are efficient, and the high-energy mine earthquake and impact behavior area can be effectively predicted.