Abstract: A method can include receiving neutron data and density data for a borehole in a geologic formation; determining a migration length value for a layer of the geologic formation based at least in part on the neutron data; forward modeling at least the layer based at least in part on the migration length value and the density data; and outputting, based at least in part on the forward modeling, modeled neutron data for the layer.

Abstract: A method can include receiving neutron data and density data for a borehole in a geologic formation; determining a migration length value for a layer of the geologic formation based at least in part on the neutron data; forward modeling at least the layer based at least in part on the migration length value and the density data; and outputting, based at least in part on the forward modeling, modeled neutron data for the layer.

Abstract: A method can include receiving data for a geologic region; based at least in part on the data, selecting a model from a plurality of models using a trained machine learning model, and inverting the data using the selected model to determine parameters of the selected model.

Abstract: A method includes receiving information for a subsurface region; based at least in part on the information, identifying sub-regions within the subsurface region; assigning individual identified sub-regions a dimensionality of a plurality of different dimensionalities that correspond to a plurality of different models; via a model-based computational framework, generating at least one result for at least one of the individual identified sub-regions based at least in part on at least one assigned dimensionality; and consolidating the at least one result for multiple sub-regions.

Abstract: Properties of a geological formation, such as vertical resistivity values, horizontal resistivity values, dip, and azimuth may be determined by inverting electromagnetic (EM) well log data based at least in part on an anisotropic formation model and a cost function. The cost function may include a data misfit term, a smoothness term, and an entropy term. In some embodiments, one or more of the data misfit term, the smoothness term, and the entropy term may be represented as functions of vertical conductivity and horizontal conductivity. The cost function may include one or more regularization parameters that are based at least in part on the data misfit term. Further, the cost function may include one or more relaxation factors that are based at least in part on a ratio of the Hessians of the smoothness term and the data misfit term.

Abstract: Properties of a geological formation, such as vertical resistivity values, horizontal resistivity values, dip, and azimuth may be determined by inverting electromagnetic (EM) well log data based at least in part on an anisotropic formation model and a cost function. The cost function may include a data misfit term, a smoothness term, and an entropy term. In some embodiments, one or more of the data misfit term, the smoothness term, and the entropy term may be represented as functions of vertical conductivity and horizontal conductivity. The cost function may include one or more regularization parameters that are based at least in part on the data misfit term. Further, the cost function may include one or more relaxation factors that are based at least in part on a ratio of the Hessians of the smoothness term and the data misfit term.

Abstract: A method includes receiving information for a subsurface region; based at least in part on the information, identifying sub-regions within the subsurface region; assigning individual identified sub-regions a dimensionality of a plurality of different dimensionalities that correspond to a plurality of different models; via a model-based computational framework, generating at least one result for at least one of the individual identified sub-regions based at least in part on at least one assigned dimensionality; and consolidating the at least one result for multiple sub-regions.