Abstract: An embodiment includes a method for use in importing geomechanical data from one or more references into a knowledge base. The method includes selecting at least one chart within at least a given one of the one or more references; extracting at least a subset of the geomechanical data in the selected chart; preparing one or more learnable models at least in part from the geomechanical data; and loading the learnable models into the knowledge base for use at least in part by at least one machine learning classifier.

Abstract: An embodiment includes a method for use in importing geomechanical data from one or more references into a knowledge base. The method includes selecting at least one chart within at least a given one of the one or more references; extracting at least a subset of the geomechanical data in the selected chart; preparing one or more learnable models at least in part from the geomechanical data; and loading the learnable models into the knowledge base for use at least in part by at least one machine learning classifier.

Abstract: A method for identifying seismic horizons in digitized seismic images includes deploying a swarm of agents at an initial position in a seismic image to be analyzed, where the swarm of agents includes picking agents that define a direction for the swarm and averaging agents that smooth the direction of the swarm, identifying a direction to follow in the seismic image for each picking agent, and advancing each picking agent in the identified direction, and averaging, by the averaging agents, the directions identified by the picking agents, wherein if an information concentration measured by a picking agent at a current time step is greater than a previous time step, the picking agent keeps a previous direction, otherwise the picking agent changes direction according to the average current state of the set of averaging agents within its neighborhood.

Abstract: One aspect includes a method for use with a steam assisted gravity drainage well. The method includes generating an analytical framework for the well at least in part by modeling one or more observable variables as a function at least of one or more control variables; and modeling one or more output variables as a function at least of at least one of the one or more control variables; and at least one of the one or more observable variables. The method further includes utilizing the analytical framework to determine an optimal configuration for the well, the optimal configuration including a set of one or more values for the one or more control variables which produce one or more desired values for the one or more output variables; and configuring the well to operate with the determined optimal configuration.

Abstract: A method for increasing efficiency in emulsion production for a steam-assisted gravity drainage (SAGD) oil well system includes generating a causal model of the SAGD oil well system and training the causal model of the SAGD oil well system utilizing historical time series data relating to one or more SAGD oil wells at one or more SAGD production sites of the SAGD oil well system. The historical time series data is obtained from a plurality of sensors in the SAGD oil well system. The method also includes utilizing the causal model to determine a forecast emulsion production and a forecast set of control parameters associated with one or more of the SAGD production sites of the SAGD oil well system. The method further includes adjusting a set of controls of the SAGD oil well system based on the forecast emulsion production and the forecast set of control parameters and subject to one or more constraints associated with the SAGD oil well system.

Abstract: A method for increasing efficiency in emulsion production for a steam-assisted gravity drainage (SAGD) oil well system includes generating a model of the SAGD oil well system and training the model of the SAGD oil well system utilizing historical time series data relating to one or more SAGD oil wells at one or more SAGD production sites of the SAGD oil well system. The historical time series data is obtained from a plurality of sensors in the SAGD oil well system. The method also includes determining an uncertainty of the model as a function of a control space of the model and utilizing the model to determine values for control variables associated with one or more of the SAGD production sites of the SAGD oil well system which reduce the model uncertainty while meeting one or more objectives subject to one or more constraints. The method further includes adjusting a set of controls of the SAGD oil well system based on the determined values for the control variables.

Abstract: A method for increasing efficiency in emulsion production for a steam-assisted gravity drainage (SAGD) oil well system includes generating a multiple time step model of the SAGD oil well system and training the multiple time step model of the SAGD oil well system utilizing historical time series data relating to one or more SAGD oil wells at one or more SAGD production sites of the SAGD oil well system. The historical time series data is obtained from a plurality of sensors in the SAGD oil well system. The method also includes utilizing the multiple time step model to determine, based on a set of objectives and subject to one or more constraints, two or more sets of values for control parameters associated with one or more of the SAGD production sites of the SAGD oil well system for respective ones of two or more time steps.

Abstract: A fracture pattern characterization method, system, and computer program product, include classifying fracture patterns of reservoir layers using a correlation of reservoir information associated with target images and the target images extracted from a database and determining a fracture pattern characterization of a new reservoir layer input based on the classified fracture patterns.

Abstract: One aspect includes a method for use with a plurality of steam assisted gravity drainage wells. The method includes designing a first modeling framework which provides a model of total output for the plurality of wells from one or more input variables for respective ones of the plurality of wells. The method also includes designing a second modeling framework which provides a model of output for a given one of the plurality of wells based at least in part on one or more input variables for the given one of the plurality of wells and one or more input variables for at least another one of the plurality of wells. The method further includes utilizing the first and second modeling frameworks to determine an optimal configuration for the wells and configuring the well to operate with the determined optimal configuration.

Abstract: An embodiment includes a method for use by at least one machine learning classifier. The method comprises the machine learning classifier obtaining one or more recent results from at least one geomechanical simulation; the machine learning classifier comparing the recent results to stored historical data; and, based on the comparing, the machine learning classifier deciding at least one reservoir model for use by at least one reservoir simulation.

Abstract: An agricultural material application management system includes an automated agricultural data collection vehicle including a location sensor. The automated agricultural data collection vehicle includes a receiver that receives sensor data including crop information, a memory that stores the plurality of locations and the sensor data, and a processor that generates a mapping correlating the crop information with the plurality of locations in the agricultural area, and generates an agricultural material application recommendation for each of the plurality of locations based on the mapping. The agricultural material application management system includes an agricultural vehicle including an interface unit that interfaces with the automated agricultural data collection vehicle and receives the agricultural material application recommendations from the agricultural data collection vehicle.

Abstract: An agricultural material application management system includes an automated agricultural data collection vehicle including a location sensor. The automated agricultural data collection vehicle includes a receiver that receives sensor data including crop information, a memory that stores the plurality of locations and the sensor data, and a processor that generates a mapping correlating the crop information with the plurality of locations in the agricultural area, and generates an agricultural material application recommendation for each of the plurality of locations based on the mapping. The agricultural material application management system includes an agricultural vehicle including an interface unit that interfaces with the automated agricultural data collection vehicle and receives the agricultural material application recommendations from the agricultural data collection vehicle.

Abstract: Determining semantically equivalent text or questions using hybrid representations based on neural network learning. Weighted bag-of-words and convolutional neural networks (CNN) based distributed vector representations of questions or text may be generated to compute the semantic similarity between questions or text. Weighted bag-of-words and CNN based distributed vector representations may be jointly used to compute the semantic similarity. A pair-wise ranking loss function trains neural network. In one embodiment, the parameters of the system are trained by minimizing a pair-wise ranking loss function over a training set using stochastic gradient descent (SGD).

Abstract: Visualizations of a serial process are provided. A process model of a serial process is constructed using an underlying statististical model. The process model represents each instance of the serial process as a series of interconnected nodes, wherein (i) the serial process includes a plurality of events; (ii) each node is associated with an event and a time at which the associated event occurred in an instance of the serial process; and (iii) connectors link nodes together to form the series of interconnected nodes, the connectors representing stages of serial process. The stages are scored and categorized into various categories based, at least in part, on the process model. One or more of the categories is associated with outlier stages. A visualization of the process model is presented such that the visualization associates the stages of the instances of serial process with respective categories.

Abstract: A method for identifying a resource in a field using historic well data including vertical well logs for the resource and historic horizontal well production data for the resource, the method including extracting a plurality of features from the vertical well logs, performing a spatial interpolation of the plurality of features extracted from the vertical well logs onto coordinates of the horizontal well production data to determine a plurality of interpolated features, and building a model predicting production of the resource in the field by regressing the horizontal well production data onto the interpolated features, wherein the model is displayed as a visualization of the resource production predicted in the field.

Abstract: A method for identifying a resource in a field using historic well data including vertical well logs for the resource and historic horizontal well production data for the resource, the method including extracting a plurality of features from the vertical well logs, performing a spatial interpolation of the plurality of features extracted from the vertical well logs onto coordinates of the horizontal well production data to determine a plurality of interpolated features, and building a model predicting production of the resource in the field by regressing the horizontal well production data onto the interpolated features, wherein the model is displayed as a visualization of the resource production predicted in the field.