Abstract: In some aspects, the techniques described herein relate to a method including: receiving, as input to a machine learning engine, a processing operation identifier, and an initial data object reference, wherein the processing operation identifier identifies a processing operation; generating, as output from the machine learning engine, a set of data object references, wherein the set of data object references are predicted as required input to the processing operation by the machine learning engine; executing a batch retrieval process, wherein the batch retrieval process retrieves a set of data objects that corresponds to the set of data object references from a datastore; loading the set of data objects in a cache; and executing the processing operation using the predicted set of data objects loaded in the cache.

Abstract: Reservoir fracture simulation relates to a method of evaluating a reservoir. Data associated with properties of the reservoir as well as properties of a fracture in the reservoir, is collected. This data is then used in conjunction with a correlation matrix to determine modification parameters of a reservoir model of the reservoir. The correlation matrix corresponds to an empirical functional relationship between the modification parameters and the data, and is obtained based on a plurality of experimental fractures defined in the reservoir. Effects of the fracture are then emulated by selectively modifying the reservoir model using the modification parameters to generate a modified reservoir model. The reservoir is then modeled with the fracture by using the modified reservoir model to generate a result.

Abstract: Implementations of well placement in a volume are described. Some techniques described herein involve ascertaining a skeleton of a volume within a reservoir, and using the skeleton to map out a well topology to retrieve resources, such as hydrocarbons, from the volume. In one possible implementation, the skeleton can be found by generating a repulsive field throughout an interior of the volume, with the field decreasing with distance from the boundary of the volume. Interior points where a magnitude of the force drops to within a preset value are called critical points. The skeleton can be found by following outward flow from the volume from critical point to critical point.

Abstract: Reservoir fracture simulation relates to a method of evaluating a reservoir. Data associated with properties of the reservoir as well as properties of a fracture in the reservoir, is collected. This data is then used in conjunction with a correlation matrix to determine modification parameters of a reservoir model of the reservoir. The correlation matrix corresponds to an empirical functional relationship between the modification parameters and the data, and is obtained based on a plurality of experimental fractures defined in the reservoir. Effects of the fracture are then emulated by selectively modifying the reservoir model using the modification parameters to generate a modified reservoir model. The reservoir is then modeled with the fracture by using the modified reservoir model to generate a result.