Estimating primary and secondary acoustic velocities in rock

A method of generating a three-dimensional acoustic velocity model for a subsurface region of the Earth, the method comprising:

• obtaining well logging data for a multiplicity of wellbores to collect, for each wellbore,
• a plurality of training input data sets including at least:
• a Nuclear Magnetic Resonance (NMR) logging data set, and
• an element composition scanning data set, and
• at least one training output data set including a primary and secondary velocity data set,
• training or establishing at least one regression model using said training input data sets and output training data sets, wherein the plurality of training input data set and the at least one training output data set are correlated;
• obtaining seismic survey data for said subsurface region;
• estimating, for a first wellbore, first wellbore primary and secondary acoustic velocities, Vp and Vs, of formation surrounding the first wellbore by:
• performing well logging operations in the first wellbore to obtain a corresponding plurality of first wellbore input data sets comprising NMR logging data set and element composition scanning data set for the first wellbore;
• and
• applying the obtained corresponding plurality of first wellbore input data sets to the trained or established regression model to generate as an output of the regression model, a first wellbore output data set for the first wellbore including a primary and secondary velocity data set for the first wellbore;
• creating an initial acoustic velocity model for the formation surrounding the first wellbore using the first wellbore output data set;
• and
• applying a seismic inversion method to the seismic survey data and the initial acoustic velocity model to generate said three-dimensional acoustic velocity model.