This disclosure describes a system and method for generating images and location data of a subsurface object using existing infrastructure as a source. Many infrastructure objects (e.g., pipes, cables, conduits, wells, foundation structures) are constructed of rigid materials and have a known shape and location. Additionally these infrastructure objects can have exposed portions that are above or near the surface and readily accessible. A signal generator can be affixed to the exposed portion of the infrastructure object, which induces acoustic energy, or vibrations in the object. The object with affixed signal generator can then be used as a source in performing a subsurface imaging of subsurface objects, which are not exposed.

An actuation location for actuation of a first source coupled to a first marine survey vessel relative to a position of a second marine survey vessel towing a receiver to enhance illumination of a subsurface location can be determined based on a survey route of the second marine survey vessel and a priori data of the subsurface location. The first marine survey vessel can be navigated along a survey route of the first marine survey vessel to the actuation location during a marine survey by changing at least a cross-line position or an in-line position of the first marine survey vessel relative to the survey route of the second marine survey vessel.

An actuation location for actuation of a first source coupled to a first marine survey vessel relative to a position of a second marine survey vessel towing a receiver to enhance illumination of a subsurface location can be determined based on a survey route of the second marine survey vessel and a priori data of the subsurface location. The first marine survey vessel can be navigated along a survey route of the first marine survey vessel to the actuation location during a marine survey by changing at least a cross-line position or an in-line position of the first marine survey vessel relative to the survey route of the second marine survey vessel.

Property values inside an explored underground subsurface are determined using hybrid analytic and machine learning. A training dataset representing survey data acquired over the explored underground structure is used to obtain labels via an analytic inversion. A deep neural network model generated using the training dataset and the labels is used to predict property values corresponding to the survey data using the DNN model.

A method for training a backpropagation-enabled regression process is used for predicting values of an attribute of subsurface data. A multi-dimensional seismic data set with an input dimension of at least two is inputted into a backpropagation-enabled process. A predicted value of the attribute has a prediction dimension of at least 1 and is at least 1 dimension less than the input dimension.

Aspects of the technology described herein identify geologic features within seismic data using modern computer analysis. An initial step is the development of training data for the machine classifier. The training data comprises an image of seismic data paired with a label identifying points of interest that the classifier should identify within raw data. Once the training data is generated, a classifier can be trained to identify areas of interest in unlabeled seismic images. The classifier can take the form of a deep neural network, such as a U-net. Aspects of the technology described herein utilize a deep neural network architecture that is optimized to detect broad and flat features in seismic images that may go undetected by typical neural networks in use. The architecture can include a group of layers that perform aspect ratio compression and simultaneous comparison of images across multiple aspect ratio scales.

A method of operating a reservoir simulator can include performing a time step of a reservoir simulation using a spatial reservoir model that represents a subterranean environment that includes a reservoir to generate simulation results for a first time where the simulation results include a front defined by at least in part by a gradient at a position between portions of the spatial reservoir model; predicting a position of the front for a subsequent time step for a corresponding second time using a trained machine model; discretizing the spatial reservoir model locally at the predicted position of the front to generate a locally discretized version of the spatial reservoir model; and performing a time step of the reservoir simulation using the locally discretized version of the spatial reservoir model to generate simulation results for the second time.

A method of operating a reservoir simulator can include performing a time step of a reservoir simulation using a spatial reservoir model that represents a subterranean environment that includes a reservoir to generate simulation results for a first time where the simulation results include a front defined by at least in part by a gradient at a position between portions of the spatial reservoir model; predicting a position of the front for a subsequent time step for a corresponding second time using a trained machine model; discretizing the spatial reservoir model locally at the predicted position of the front to generate a locally discretized version of the spatial reservoir model; and performing a time step of the reservoir simulation using the locally discretized version of the spatial reservoir model to generate simulation results for the second time.

The present disclosure is directed to numerically estimating the shear modulus of Kerogen by using a combination of mineralogy from digital image analysis and sonic log analysis, when measured data on only one elastic constant (Bulk, Young's or P-wave modulus) is available. In some instances, elastic properties predicted from the digital images are compared with sonic, shear, and density logs, to estimate the shear modulus of kerogen. As a one-to-one correspondence is not expected between the core sub-samples and the rock unit sampled by the well logs, cross-property relations can be used to identify the suitability of the effective medium models and to iteratively determine the shear modulus of kerogen.

The present disclosure is directed to numerically estimating the shear modulus of Kerogen by using a combination of mineralogy from digital image analysis and sonic log analysis, when measured data on only one elastic constant (Bulk, Young's or P-wave modulus) is available. In some instances, elastic properties predicted from the digital images are compared with sonic, shear, and density logs, to estimate the shear modulus of kerogen. As a one-to-one correspondence is not expected between the core sub-samples and the rock unit sampled by the well logs, cross-property relations can be used to identify the suitability of the effective medium models and to iteratively determine the shear modulus of kerogen.