Abstract: Systems, methods, and computer-readable storage media for combining machine learning models which respectfully use public and private data using a third machine learning model. Upon training a public data machine learning model and a private data machine learning model, the system trains a public and private data machine learning model using a combination of: (1) historical public data machine learning predictions output by the public data machine learning model, and (2) historical private data machine learning predictions output by the private data machine learning model. The system then executes the public and private data machine learning models, resulting in a public data machine learning prediction and a private data machine learning prediction, then executes the public and private data machine learning model using the public data machine learning prediction and the private data machine learning prediction as inputs, resulting in a final prediction.

Abstract: Processes can be employed to select cartographic reference system (CRS) recommendations from a CRS model where the CRS recommendations are matched to received seismic data. A learning mode can be used to build the CRS model where seismic data is matched to CRS. The learning mode can be automated using natural language processing system to parse the meta data for the seismic data, such as the name, area, or code, or label. The CRS model can be updated using an output from a user system, such as when a user manually matches a CRS to seismic data. The matched seismic data to CRS can be used as input to a user system or a computing system, such as a borehole operation system.

Abstract: Systems, methods, and computer-readable storage media for database migration, and more specifically to systems and methods for enabling transfer of data between databases with different schema. A system can receive a request to transfer data from a first database to a second database, where the first database and the second database have distinct schema. The system can generate, via an entity relationship mapping algorithm text descriptions of how data is stored in the first database and how data is stored in the second database. Then, using a natural language processing (NLP) based large language model (LLM), the system can process the text descriptions to generate a database mapping, the database mapping identifying how information in the first database corresponds to the second database. The system can then transfer the data from the first database to the second database using the database mapping.

Abstract: Systems, methods, and computer-readable storage media for combining machine learning models which respectfully use public and private data using a third machine learning model. Upon training a public data machine learning model and a private data machine learning model, the system trains a public and private data machine learning model using a combination of: (1) historical public data machine learning predictions output by the public data machine learning model, and (2) historical private data machine learning predictions output by the private data machine learning model. The system then executes the public and private data machine learning models, resulting in a public data machine learning prediction and a private data machine learning prediction, then executes the public and private data machine learning model using the public data machine learning prediction and the private data machine learning prediction as inputs, resulting in a final prediction.

Abstract: Systems, methods, and computer-readable storage media for aggregating the outputs of multiple machine learning models, then using the output of yet another machine learning model as a multiplier to obtain a final prediction. A system can receiving a plurality of data sets, each data set being associated with at least one data type, and train machine learning models, each model associated with one or more of the different data types. Upon execution, the multiple machine learning models can each produce a prediction which is aggregated together to form an aggregated prediction. The multiplier from the additional machine learning model can then be applied to the aggregated prediction, resulting in a final prediction.

Abstract: Systems, methods, and computer-readable storage media for recommending loads for transport. A system can receive location coordinates for a transport vehicle, and further receive data regarding available loads which can be transported by the transport vehicle. The system can then filter the available loads based at least in part on the location coordinates. The system can also receive at least one carrier profile and at least one shipper profile. Finally, the system can execute a load recommendation algorithm using the preference filtered loads, the at least one carrier profile, and the at least one shipper profile as inputs, resulting in at least one load recommendation score for a load within the preference filtered loads.

Abstract: The disclosure presents processes to select cartographic reference system (CRS) recommendations from a CRS model where the CRS recommendations are matched to received seismic data. A learning mode can be used to build the CRS model where seismic data is matched to CRS. The learning mode can be automated using natural language processing system to parse the meta data for the seismic data, such as the name, area, or code, or label. The CRS model can be updated using an output from a user system, such as when a user manually matches a CRS to seismic data. The matched seismic data to CRS, e.g., seismic data-CRS match, can be used as input to a user system or a computing system, such as a borehole operation system.

Abstract: A method for determining a position of a geological feature in a formation includes acquiring a seismic dataset, wherein the seismic dataset is based on signals of one or more seismic sensors and determining a set of indicators of candidate discontinuities in the formation based on the seismic dataset. The method also includes labeling a subset of the set of indicators of candidate discontinuities using a neural network with a label based on the set of indicators of candidate discontinuities, wherein the label distinguishes an indicator of a candidate discontinuity between being an indicator of a target discontinuity or being an indicator of a non-target discontinuity and determining the position of the geological feature in the formation, wherein the geological feature in the formation is associated with at least one target discontinuity based on the subset of the set of indicators of candidate discontinuities.

Abstract: A method includes receiving a training selection of a first set of faults located in a first subset of a seismic dataset for a subsurface geologic formation, detecting a second set of faults in the seismic dataset based on fault interpretation operations using a first set of interpretation parameters, and determining a difference between the first set of faults and the second set of faults. The method also includes generating a second set of interpretation parameters for the fault interpretation operations based on the difference between the first set of faults and the second set of faults, and determining a feature of the subsurface geologic formation based on fault interpretation operations using the second set of interpretation parameters.

Abstract: A method includes receiving a training selection of a first set of faults located in a first subset of a seismic dataset for a subsurface geologic formation, detecting a second set of faults in the seismic dataset based on fault interpretation operations using a first set of interpretation parameters, and determining a difference between the first set of faults and the second set of faults. The method also includes generating a second set of interpretation parameters for the fault interpretation operations based on the difference between the first set of faults and the second set of faults, and determining a feature of the subsurface geologic formation based on fault interpretation operations using the second set of interpretation parameters.

Abstract: A method for determining a position of a geological feature in a formation includes acquiring a seismic dataset, wherein the seismic dataset is based on signals of one or more seismic sensors and determining a set of indicators of candidate discontinuities in the formation based on the seismic dataset. The method also includes labeling a subset of the set of indicators of candidate discontinuities using a neural network with a label based on the set of indicators of candidate discontinuities, wherein the label distinguishes an indicator of a candidate discontinuity between being an indicator of a target discontinuity or being an indicator of a non-target discontinuity and determining the position of the geological feature in the formation, wherein the geological feature in the formation is associated with at least one target discontinuity based on the subset of the set of indicators of candidate discontinuities.