Abstract: A method for modeling a subsurface property for a subterranean volume of interest includes receiving input measurement data representing a subterranean volume of interest, predicting a subsurface property based at least in part on the input measurement data using a first machine learning model, predicting a subsurface property model based at least in part on the subsurface property, the input measurement data, or both, using a second machine learning model, predicting synthetic measurement data based at least in part on the subsurface property model using a third machine learning model, a physics-based model, or both, comparing the synthetic measurement data and the input measurement data, and training the first machine learning model, the second machine learning model, or both based at least in part on the comparing.

Abstract: Techniques and technologies for mapping user identifiers between different device ecosystems are described. In at least some embodiments, a system includes a processing component, a memory, and a mapping engine configured to map a first identifier associated with a user with a second identifier, at least one of the first or second identifiers being associated with a first device ecosystem; and map a third identifier associated with a second device ecosystem with at least one of the first identifier or the second identifier, the second device ecosystem different from the first device ecosystem, based at least partially on (i) a plurality of first co-location occurrences of the third identifier with the first identifier, and (ii) a plurality of second co-location occurrences of the third identifier with the second identifier. The mapping engine may provide an indication of an association of the third identifier with the user.

Abstract: Techniques and technologies for mapping user identifiers between different device ecosystems are described. In at least some embodiments, a system includes a processing component, a memory, and a mapping engine configured to map a first identifier associated with a user with a second identifier, at least one of the first or second identifiers being associated with a first device ecosystem; and map a third identifier associated with a second device ecosystem with at least one of the first identifier or the second identifier, the second device ecosystem different from the first device ecosystem, based at least partially on (i) a plurality of first co-location occurrences of the third identifier with the first identifier, and (ii) a plurality of second co-location occurrences of the third identifier with the second identifier. The mapping engine may provide an indication of an association of the third identifier with the user.

Abstract: In a method for testing a system, the technology initially accesses a database having a plurality of stand-alone pieces-of-code. Each piece-of-code includes a sequence of operations to be performed on a system. One or more of a plurality of stand-alone pieces-of-code within a database are selected to generate a set of at least two stand-alone pieces-of-code, based on a testing scenario. A variable test sequence from a set of at least two stand-alone pieces-of-code is then generated. The variable test sequence is then utilized to test a system based on a testing scenario.