Hybrid optimization of fault detection and interpretation

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.

Fault detection based on seismic data interpretation

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.

USING DISTRIBUTED SENSOR DATA TO CONTROL CLUSTER EFFICIENCY DOWNHOLE

A system for determining real time cluster efficiency for a pumping operation in a wellbore includes a pump, a surface sensor, a downhole sensor system, and a computing device. The pump can pump slurry or diverter material in the wellbore. The surface sensor can be positioned at a surface of the wellbore to detect surface data about the pump. The downhole sensor system can be positioned in the wellbore to detect downhole data about an environment of the wellbore. The computing device can receive the surface data from the surface sensor, receive the downhole data from the downhole sensor system, apply the surface data and the downhole data to a long short-term memory (LSTM) neural network to produce a predicted cluster efficiency associated with operational settings of the pump, and control the pump using the operational settings to achieve the predicted cluster efficiency.

FAULT DETECTION BASED ON SEISMIC DATA INTERPRETATION

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.

CORRECTING BIASES IN MICROSEISMIC-EVENT DATA

Microseismic-event data can be corrected (e.g., to reduce or eliminate bias). For example, a first distribution of microseismic events that occurred in a first area of a subterranean formation can be determined. The first distribution can be used as a reference distribution. A second distribution of microseismic events that occurred in a second area of the subterranean formation can also be determined. The second area of the subterranean formation can be farther from an observation well than the first area. The second distribution can be corrected by including, in the second distribution, microseismic events that have characteristics tailored for reducing a difference between the second distribution and the first distribution.

WORKFLOW OPTIMIZATION

Managing execution of a workflow has a set of subworkflows. Optimizing the set of subworkflows using a deep neural network, each subworkflow of the set has a set of tasks. Each task of the sets has a requirement of resources of a set of resources; each task of the sets is enabled to be dependent on another task of the sets of tasks. Training the deep neural network by: executing the set of subworkflows, collecting provenance data from the execution, and collecting monitoring data that represents the state of said set of resources. Training causes the neural network to learn relationships between the states of the set of resources, the sets of tasks, their parameters and the obtained performance. Optimizing an allocation of resources to each task to ensure compliance with a user-defined quality metric based on the deep neural network output.

HYBRID OPTIMIZATION OF FAULT DETECTION AND INTERPRETATION

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.

GEOSTATISTICAL ANALYSIS OF MICROSEISMIC DATA IN FRACTURE MODELING

A method may comprise: modeling a complex fracture network within the subterranean formation with a mathematical model based on a natural fracture network map and measured data of the subterranean formation collected in association with a fracturing treatment of the subterranean formation to produce a complex fracture network map; importing microseismic data collected in association with the fracturing treatment of the subterranean formation into the mathematical model; identifying directions of continuity in the microseismic data via a geostatistical analysis that is part of the mathematical model; and correlating the directions of continuity in the microseismic data to the complex fracture network with the mathematical model to produce a microseismic-weighted (MSW) complex fracture network map.

MULTIVARIATE ANALYSIS OF SEISMIC DATA, MICROSEISMIC DATA, AND PETROPHYSICAL PROPERTIES IN FRACTURE MODELING

A multivariate analysis may be used to correlate seismic attributes for a subterranean formation with petrophysical properties of the subterranean formation and/or microseismic data associated with treating, creating, and/or extending a fracture network of the subterranean formation. For example, a method may involve modeling petrophysical properties of a subterranean formation, microseismic data associated with treating a complex fracture network in the subterranean formation, or a combination thereof with a mathematical model based on measured data, microseismic data, completion and treatment data, or a combination thereof to produce a petrophysical property map, a microseismic data map, or a combination thereof; and correlating a seismic attribute map with the petrophysical property map, the microseismic data map, or the combination thereof using the mathematical model to produce at least one quantified correlation, wherein the seismic attribute map is a seismic attributed modeled for the complex fracture network.

VISUALIZING ATTRIBUTES OF MULTIPLE FAULT SURFACES IN REAL TIME

Systems and method for visualizing attributes of multiple fault surfaces in real time by: picking a fault surface; generating a grid and a mesh for the fault surface in a three-dimensional space, wherein the mesh includes one or more units and a plurality of mesh points; calculating a local normal vector for each unit of the mesh; and calculating one or more dip-angle attributes and one or more dip-azimuth attributes for the fault surface using a respective local normal vector and a computer processor.

Correcting biases in microseismic-event data

Microseismic-event data can be corrected (e.g., to reduce or eliminate bias). For example, a first distribution of microseismic events that occurred in a first area of a subterranean formation can be determined. The first distribution can be used as a reference distribution. A second distribution of microseismic events that occurred in a second area of the subterranean formation can also be determined. The second area of the subterranean formation can be farther from an observation well than the first area. The second distribution can be corrected by including, in the second distribution, microseismic events that have characteristics tailored for reducing a difference between the second distribution and the first distribution.

MULTIVARIATE ANALYSIS OF SEISMIC DATA, MICROSEISMIC DATA, AND PETROPHYSICAL PROPERTIES IN FRACTURE MODELING

A multivariate analysis may be used to correlate seismic attributes for a subterranean formation with petrophysical properties of the subterranean formation and/or microseismic data associated with treating, creating, and/or extending a fracture network of the subterranean formation. For example, a method may involve modeling petrophysical properties of a subterranean formation, microseismic data associated with treating a complex fracture network in the subterranean formation, or a combination thereof with a mathematical model based on measured data, microseismic data, completion and treatment data, or a combination thereof to produce a petrophysical property map, a microseismic data map, or a combination thereof; and correlating a seismic attribute map with the petrophysical property map, the microseismic data map, or the combination thereof using the mathematical model to produce at least one quantified correlation, wherein the seismic attribute map is a seismic attributed modeled for ...

VISUALIZING ATTRIBUTES OF MULTIPLE FAULT SURFACES IN REAL TIME

Systems and methods for visualizing attributes of multiple fault surfaces in real time by calculating the attributes as each respective fault surface is picked. 1. A method for visualizing attributes of a fault surface in real-time , which comprises:a) picking a fault surface;b) generating a grid and a mesh for the fault surface in a three-dimensional space, wherein the mesh includes one or more units and a plurality of mesh points;c) calculating a local normal vector for each unit of the mesh; andd) calculating one or more dip-angle attributes and one or more dip-azimuth attributes for the fault surface using a respective local normal vector and a computer processor.2. The method of claim 1 , further comprising calculating one or more curvature attributes for the fault surface using at least six of the plurality of mesh points.3. The method of claim 1 , further comprising calculating one or more curvature attributes for the fault surface using at least ten of the plurality of mesh points.4. The method of claim 1 , further comprising displaying the one or more dip-angle attributes claim 1 , the one or more dip-azimuth attributes and the one or more curvature attributes as the fault surface is picked.5. The method of claim 4 , further comprising positioning a well based on at least one of the one or more dip-angle attributes displayed claim 4 , the one or more dip-azimuth attributes displayed and the one or more curvature attributes displayed.6. The method of claim 2 , further comprising:rotating the fault surface from an original position to a new position before the one or more curvature attributes are calculated; androtating the fault surface to the original position after the one or more curvature attributes are calculated.7. The method of claim 1 , wherein the mesh generated for the fault surface is a quadratic mesh.8. The method of claim 1 , further comprising repeating steps a)-d) for another fault surface.9. The method of claim 1 , wherein each dip-angle ...

GEOSTATISTICAL ANALYSIS OF MICROSEISMIC DATA IN FRACTURE MODELING

A method may comprise: modeling a complex fracture network within the subterranean formation with a mathematical model based on a natural fracture network map and measured data of the subterranean formation collected in association with a fracturing treatment of the subterranean formation to produce a complex fracture network map; importing microseismic data collected in association with the fracturing treatment of the subterranean formation into the mathematical model; identifying directions of continuity in the microseismic data via a geostatistical analysis that is part of the mathematical model; and correlating the directions of continuity in the microseismic data to the complex fracture network with the mathematical model to produce a microseismic-weighted (MSW) complex fracture network map.

Geostatistical analysis of microseismic data in fracture modeling

A method may comprise: modeling a complex fracture network within the subterranean formation with a mathematical model based on a natural fracture network map and measured data of the subterranean formation collected in association with a fracturing treatment of the subterranean formation to produce a complex fracture network map; importing microseismic data collected in association with the fracturing treatment of the subterranean formation into the mathematical model; identifying directions of continuity in the microseismic data via a geostatistical analysis that is part of the mathematical model; and correlating the directions of continuity in the microseismic data to the complex fracture network with the mathematical model to produce a microseismic-weighted (MSW) complex fracture network map.

Multivariate analysis of seismic data, microseismic data, and petrophysical properties in fracture modeling

A multivariate analysis may be used to correlate seismic attributes for a subterranean formation with petrophysical properties of the subterranean formation and/or microseismic data associated with treating, creating, and/or extending a fracture network of the subterranean formation. For example, a method may involve modeling petrophysical properties of a subterranean formation, microseismic data associated with treating a complex fracture network in the subterranean formation, or a combination thereof with a mathematical model based on measured data, microseismic data, completion and treatment data, or a combination thereof to produce a petrophysical property map, a microseismic data map, or a combination thereof; and correlating a seismic attribute map with the petrophysical property map, the microseismic data map, or the combination thereof using the mathematical model to produce at least one quantified correlation, wherein the seismic attribute map is a seismic attributed modeled for ...

Visualizing attributes of multiple fault surfaces in real time

Systems and method for visualizing attributes of multiple fault surfaces in real time by: picking a fault surface; generating a grid and a mesh for the fault surface in a three-dimensional space, wherein the mesh includes one or more units and a plurality of mesh points; calculating a local normal vector for each unit of the mesh; and calculating one or more dip-angle attributes and one or more dip-azimuth attributes for the fault surface using a respective local normal vector and a computer processor.

DRILL BIT REPAIR TYPE PREDICTION USING MACHINE LEARNING

The subject disclosure provides for a mechanism implemented with neural networks through machine learning to predict wear and relative performance metrics for performing repairs on drill bits in a next repair cycle, which can improve decision making by drill bit repair model engines, drill bit design, and help reduce the cost of drill bit repairs. The machine learning mechanism includes obtaining drill bit data from different data sources and integrating the drill bit data from each of the data sources into an integrated dataset. The integrated dataset is pre-processed to filter out outliers. The filtered dataset is applied to a neural network to build a machine learning based model and extract features that indicate significant parameters affecting wear. A repair type prediction is determined with the applied machine learning based model and is provided as a signal for facilitating a drill bit operation on a cutter of the drill bit. 1. A method , comprising:obtaining drill bit data from a plurality of data sources through one or more application programming interfaces communicably coupled to a processor circuit;integrating, in a data integration engine executed on the processor circuit, the drill bit data from each of the plurality of data sources into an integrated dataset;pre-processing, in a data pre-process engine executed on the processor circuit, the integrated dataset to filter out one or more outlier data points from the integrated dataset;processing, in the processor circuit, the filtered dataset with a neural network to build a machine learning based model;processing, in the processor circuit, the machine learning based model to extract one or more features that indicate significant parameters affecting wear on a drill bit;determining a repair type prediction with the applied machine learning based model based on the extracted one or more features, the repair type prediction indicating a repair action for a cutter on a drill bit; andproviding a signal ...

Multivariate Analysis Of Seismic Data, Microseismic Data, And Petrophysical Properties In Fracture Modeling

A multivariate analysis may be used to correlate seismic attributes for a subterranean formation with petrophysical properties of the subterranean formation and/or microseismic data associated with treating, creating, and/or extending a fracture network of the subterranean formation. For example, a method may involve modeling petrophysical properties of a subterranean formation, microseismic data associated with treating a complex fracture network in the subterranean formation, or a combination thereof with a mathematical model based on measured data, microseismic data, completion and treatment data, or a combination thereof to produce a petrophysical property map, a microseismic data map, or a combination thereof; and correlating a seismic attribute map with the petrophysical property map, the microseismic data map, or the combination thereof using the mathematical model to produce at least one quantified correlation, wherein the seismic attribute map is a seismic attributed modeled for the complex fracture network. 1. A method comprising:modeling one selected from the group consisting of petrophysical properties of a subterranean formation, microseismic data associated with treating a complex fracture network in the subterranean formation, and a combination thereof with a mathematical model based on one selected from the group consisting of measured data, microseismic data, completion and treatment data, and a combination thereof to produce one selected from the group consisting of a petrophysical property map, a microseismic data map, and a combination thereof; andcorrelating a seismic attribute map with one selected from the group consisting of the petrophysical property map, the microseismic data map, and the combination thereof using the mathematical model to produce at least one quantified correlation, wherein the seismic attribute map is a seismic attributed modeled for the complex fracture network.2. The method of further comprising:modeling the seismic ...

Workflow optimization

A computer implemented method, computer program product, and system for managing execution of a workflow comprising a set of subworkflows, comprising optimizing the set of subworkflows using a deep neural network, wherein each subworkflow of the set of subworkflows has a set of tasks, wherein each task of the sets of tasks has a requirement of resources of a set of resources; wherein each task of the sets of tasks is enabled to be dependent on another task of the sets of tasks, training the deep neural network by: executing the set of subworkflows, collecting provenance data from the execution, and collecting monitoring data that represents the state of said set of resources, wherein the training causes the neural network to learn relationships between the states of said set of resources, the said sets of tasks, their parameters and the obtained performance, optimizing an allocation of resources of the set of resources to each task of the sets of tasks to ensure compliance with a user-defined quality metric based on the deep neural network output. 1. A computer implemented method for managing execution of a workflow comprising a set of subworkflows , the method comprising:optimizing the set of subworkflows using a deep neural network; wherein each subworkflow of the set of subworkflows has a set of tasks; wherein each task of the sets of tasks has a requirement of resources of a set of resources; wherein each task of the sets of tasks is enabled to be dependent on another task of the sets of tasks;training the deep neural network by: executing the set of subworkflows, collecting provenance data from the execution, and collecting monitoring data that represents the state of the set of resources; wherein the training causes the neural network to learn relationships between the states of the set of resources, the sets of tasks, their parameters and the obtained performance;optimizing an allocation of resources of the set of resources to each task of the sets of tasks ...

HYBRID OPTIMIZATION OF FAULT DETECTION AND INTERPRETATION

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. 1. A method comprising: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;determining a difference between the first set of faults and the second set of faults;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; anddetermining a feature of the subsurface geologic formation based on fault interpretation operations using the second set of interpretation parameters.2. The method of claim 1 , wherein the second set of interpretation parameters is determined based on a stochastic optimization.3. The method of claim 2 , wherein the stochastic optimization is a Bayesian optimization claim 2 , and wherein the difference between the first set of faults and the second set of faults is based on an Euclidean norm.4. The method of claim 1 , wherein the seismic dataset is a three-dimensional seismic dataset.5. The method of claim 1 , further comprising modifying a drilling operation based ...

Multivariate analysis of seismic data, microseismic data, and petrophysical properties in fracture modeling

A multivariate analysis may be used to correlate seismic attributes for a subterranean formation with petrophysical properties of the subterranean formation and/or microseismic data associated with treating, creating, and/or extending a fracture network of the subterranean formation. For example, a method may involve modeling petrophysical properties of a subterranean formation, microseismic data associated with treating a complex fracture network in the subterranean formation, or a combination thereof with a mathematical model based on measured data, microseismic data, completion and treatment data, or a combination thereof to produce a petrophysical property map, a microseismic data map, or a combination thereof; and correlating a seismic attribute map with the petrophysical property map, the microseismic data map, or the combination thereof using the mathematical model to produce at least one quantified correlation, wherein the seismic attribute map is a seismic attributed modeled for ...

Geostatistical Analysis Of Microseismic Data In Fracture Modeling

A method may comprise: modeling a complex fracture network within the subterranean formation with a mathematical model based on a natural fracture network map and measured data of the subterranean formation collected in association with a fracturing treatment of the subterranean formation to produce a complex fracture network map; importing microseismic data collected in association with the fracturing treatment of the subterranean formation into the mathematical model; identifying directions of continuity in the microseismic data via a geostatistical analysis that is part of the mathematical model; and correlating the directions of continuity in the microseismic data to the complex fracture network with the mathematical model to produce a microseismic-weighted (MSW) complex fracture network map. 1. A method comprising:modeling a complex fracture network within the subterranean formation with a mathematical model based on a natural fracture network map and measured data of the subterranean formation collected in association with a fracturing treatment of the subterranean formation to produce a complex fracture network map;importing microseismic data collected in association with the fracturing treatment of the subterranean formation into the mathematical model;identifying directions of continuity in the microseismic data via a geostatistical analysis that is part of the mathematical model; andcorrelating the directions of continuity in the microseismic data to the complex fracture network with the mathematical model to produce a microseismic-weighted (MSW) complex fracture network map.2. The method of further comprising:producing the natural fracture network map by modeling a natural fracture network within the subterranean formation with the mathematical model based on a well log of the subterranean formation.3. The method of further comprising:developing a parameter of a subsequent wellbore operation based on the MSW complex fracture network map.4. The method of ...

FAULT DETECTION BASED ON SEISMIC DATA INTERPRETATION

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. 1. A method for determining a position of a geological feature in a formation comprising:acquiring a seismic dataset, wherein the seismic dataset is based on signals of one or more seismic sensors to receive waves from within the formation;determining a set of indicators of candidate discontinuities in the formation based on the seismic dataset;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; anddetermining 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.2. The method of claim 1 , wherein the determining the set of indicators of candidate discontinuities based on the seismic dataset ...

Correcting Biases In Microseismic-Event Data

Microseismic-event data can be corrected (e.g., to reduce or eliminate bias). For example, a first distribution of microseismic events that occurred in a first area of a subterranean formation can be determined. The first distribution can be used as a reference distribution. A second distribution of microseismic events that occurred in a second area of the subterranean formation can also be determined. The second area of the subterranean formation can be farther from an observation well than the first area. The second distribution can be corrected by including, in the second distribution, microseismic events that have characteristics tailored for reducing a difference between the second distribution and the first distribution. 1. A method comprising:generating, by a processing device, a first distribution that is representative of a distribution of microseismic events that occurred in a first area of a subterranean formation;generating, by the processing device, a second distribution that is representative of another distribution of microseismic events that occurred in a second area of the subterranean formation that is farther from an observation well than the first area; andcorrecting, by the processing device, the second distribution by including in the second distribution microseismic events that have characteristics for reducing a difference between the first distribution and the second distribution.2. The method of claim 1 , further comprising generating the first distribution by:determining a plurality of distances between primary events and secondary events that occurred within the first area of the subterranean formation, a primary event being a microseismic event for which a characteristic satisfies a condition and a secondary event being another microseismic event for which the characteristic does not satisfy the condition; anddetermining how many times each distance is present in the plurality of distances.3. The method of claim 2 , wherein the ...

USING DISTRIBUTED SENSOR DATA TO CONTROL CLUSTER EFFICIENCY DOWNHOLE

A system for determining real time cluster efficiency for a pumping operation in a wellbore includes a pump, a surface sensor, a downhole sensor system, and a computing device. The pump can pump slurry or diverter material in the wellbore. The surface sensor can be positioned at a surface of the wellbore to detect surface data about the pump. The downhole sensor system can be positioned in the wellbore to detect downhole data about an environment of the wellbore. The computing device can receive the surface data from the surface sensor, receive the downhole data from the downhole sensor system, apply the surface data and the downhole data to a long short-term memory (LSTM) neural network to produce a predicted cluster efficiency associated with operational settings of the pump, and control the pump using the operational settings to achieve the predicted cluster efficiency. 1. A system comprising:a pump in operable communication with a wellbore having multiple stages, to pump slurry or diverter material into the wellbore;a surface sensor positionable at a surface of the wellbore to detect surface data about the pump;a downhole sensor system positionable in the wellbore to detect downhole data about an environment of the wellbore; anda computing device to communicate with the pump, the surface sensor, and the downhole sensor system, the computing device being operable to: receive the downhole data from the downhole sensor system;', 'apply the surface data and the downhole data to a long short-term memory (LSTM) neural network to produce a predicted cluster efficiency associated with operational settings of the pump; and', 'control the pump using the operational settings to achieve the predicted cluster efficiency., 'receive the surface data from the surface sensor;'}2. The system of claim 1 , wherein the LSTM neural network is a deep recurrent neural network (DRNN) that is trained using a subset of the surface data and of the downhole data.3. The system of claim 1 , ...

COLLAPSIBLE SHIPPING CONTAINER

A collapsible container that includes a base, a first side panel hingedly attached to the base, a second side panel hingedly attached to the base, a first end panel hingedly attached to the base, with the first end panel including a door, and a second end panel hingedly attached to the base. The collapsible container can further include a top cover. The collapsible container is configured to be positioned in a collapsed position and an assembled position. In an assembled position, the collapsible container is configured to hold items during a domestic or international move. 1. A collapsible container comprising:a base;b) a first side panel hingedly attached to the base;c) a second side panel hingedly attached to the base;d) a first end panel hingedly attached to the base, the first end panel including a door; ande) a second end panel hingedly attached to the base,wherein the collapsible container is configured to be positioned in a collapsed position and an assembled position, andwherein, in the collapsed position, the second end panel is positioned on top of the second side panel, the second side panel is positioned on top of the first side panel, the first side panel is positioned on top of the first end panel, and the first and panel is positioned on top of the base.2. The collapsible container according to claim 1 , wherein claim 1 , in the assembled position claim 1 , (a) the first end panel attaches to (i) the first side panel along a first side of the first end panel and (ii) the second side panel along a second side of the first end panel claim 1 , and (b) the second end panel attaches to (i) the first side panel along a first side of the second end panel and (ii) the second side panel along a second side of the second end panel claim 1 , such that the first end panel is disposed opposite to the second end panel and the first side panel is disposed opposite to the second side panel.3. The collapsible container according to claim 2 , wherein claim 2 , in the ...

Workflow optimization

A computer implemented method, computer program product, and system for managing execution of a workflow comprising a set of subworkflows, comprising optimizing the set of subworkflows using a deep neural network, wherein each subworkflow of the set of subworkflows has a set of tasks, wherein each task of the sets of tasks has a requirement of resources of a set of resources; wherein each task of the sets of tasks is enabled to be dependent on another task of the sets of tasks, training the deep neural network by: executing the set of subworkflows, collecting provenance data from the execution, and collecting monitoring data that represents the state of said set of resources, wherein the training causes the neural network to learn relationships between the states of said set of resources, the said sets of tasks, their parameters and the obtained performance, optimizing an allocation of resources of the set of resources to each task of the sets of tasks to ensure compliance with a user-defined quality metric based on the deep neural network output.

RESERVOIR FLUID PROPERTY MODELING USING MACHINE LEARNING

System and methods for tuning equation of state (EOS) characterizations are presented. Pressure-volume-temperature (PVT) data is obtained for downhole fluids within a reservoir formation. A component grouping for an EOS model of the downhole fluids is determined, based on the obtained PVT data. The component grouping is used to estimate properties of the downhole fluids for a current stage of a downhole operation within the formation. A machine learning model is trained to minimize an error between the estimated properties and actual fluid properties measured during the current stage of the operation, where the component grouping for the EOS model is iteratively adjusted by the machine learning model until the error is minimized. The EOS model is tuned using the adjusted component grouping. Fluid properties are estimated for one or more subsequent stages of the downhole operation to be performed along the wellbore, based on the tuned EOS model. 1. A computer-implemented method for tuning equation of state (EOS) characterizations , the method comprising:obtaining pressure-volume-temperature (PVT) data for downhole fluids within a reservoir formation;determining a component grouping for an EOS model of the downhole fluids, based on the obtained PVT data, the component grouping including a selected number of fluid components;estimating properties of the downhole fluids for a current stage of a downhole operation along a wellbore within the reservoir formation, based on the component grouping determined for the EOS model;training a machine learning model to minimize an error between the estimated properties of the downhole fluids and actual properties of the downhole fluids as measured along the wellbore during the current stage of the downhole operation, wherein the component grouping for the EOS model is iteratively adjusted by the machine learning model until the error is minimized during the current stage of the downhole operation;tuning the EOS model using the ...

DETECTION OF UNDERGROUND FAILURES BASED ON THE INTERPRETATION OF SEISMIC DATA

Procédé d'identification des caractéristiques géologiques, telles que les failles, consistant à effectuer une détection de bord pour localiser un ensemble de discontinuités dans un jeu de données sismiques. Le procédé consiste à classer, à l'aide d'un réseau neuronal, chacune de l'ensemble de discontinuités comme faille sismique ou faille non sismique. Le procédé consiste également à déterminer les positions des discontinuités classées comme failles sismiques. A method of identifying geological features, such as faults, of performing edge detection to locate a set of discontinuities in a seismic data set. The method involves classifying, using a neural network, each of the set of discontinuities as a seismic fault or non-seismic fault. The method also includes determining the positions of discontinuities classified as seismic faults.

VISUALIZATION OF ATTRIBUTES OF MULTIPLE SURFACES OF FAILURE IN REAL TIME

Systèmes et procédés pour visualiser des attributs de multiples surfaces de faille en temps réel par calcul des attributs lorsque chaque surface de faille respective est choisie. Systems and methods for visualizing attributes of multiple fault surfaces in real time by calculating attributes as each respective fault area is selected.

DETECTION OF UNDERGROUND GEOLOGICAL STRUCTURES BASED ON THE INTERPRETATION OF SEISMIC DATA

La présente invention concerne un procédé comprenant la réception d'une sélection d'entraînement d'un premier ensemble de failles situées dans un premier sous-ensemble d'un ensemble de données sismiques pour une formation géologique souterraine, la détection d'un second ensemble de failles dans l'ensemble de données sismiques sur la base d'opérations d'interprétation de failles en utilisant un premier ensemble de paramètres d'interprétation, et la détermination d'une différence entre le premier ensemble de failles et le second ensemble de failles. Le procédé comprend également la génération d'un second ensemble de paramètres d'interprétation pour les opérations d'interprétation de failles sur la base de la différence entre le premier ensemble de failles et le second ensemble de failles, et la détermination d'une caractéristique de la formation géologique souterraine sur la base d'opérations d'interprétation de failles en utilisant le second ensemble de paramètres opérationnels. The present invention relates to a method comprising receiving a driving selection of a first set of faults located in a first subset of a set of seismic data for an underground geological formation, detecting a second set of faults in the seismic data set 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 characteristic underground geological formation on the basis of fault interpretation operations using the second set of operational parameters.

BRITISH CORRECTION IN MICROSISMIC EVENT DATA

Les données d'événements microsismiques peuvent être corrigées (par exemple, pour réduire ou éliminer des biais). Par exemple, une première distribution d'événements microsismiques qui se sont produits dans une première zone d'une formation souterraine peut être déterminée. La première distribution peut être utilisée comme distribution de référence. Une seconde distribution des événements microsismiques qui se sont produits dans une seconde zone de la formation souterraine peut également être déterminée. La seconde zone de la formation souterraine peut être plus éloignée d'un puits d'observation que de la première zone. La seconde distribution peut être corrigée en incluant, dans la seconde distribution, des événements microsismiques ayant des caractéristiques adaptées pour réduire une différence entre la seconde distribution et la première distribution. The microseismic event data can be corrected (for example, to reduce or eliminate bias). For example, a first distribution of microseismic events that occurred in a first zone of a subterranean formation can be determined. The first distribution can be used as a reference distribution. A second distribution of microseismic events that occurred in a second zone of the subterranean formation can also be determined. The second zone of the subterranean formation may be farther from an observation well than from the first zone. The second distribution can be corrected by including, in the second distribution, microseismic events having characteristics adapted to reduce a difference between the second distribution and the first distribution.

Using distributed sensor data to control cluster efficiency downhole

A system for determining real time cluster efficiency for a pumping operation in a wellbore includes a pump, a surface sensor, a downhole sensor system, and a computing device. The pump can pump slurry or diverter material in the wellbore. The surface sensor can be positioned at a surface of the wellbore to detect surface data about the pump. The downhole sensor system can be positioned in the wellbore to detect downhole data about an environment of the wellbore. The computing device can receive the surface data from the surface sensor, receive the downhole data from the downhole sensor system, apply the surface data and the downhole data to a long short-term memory (LSTM) neural network to produce a predicted cluster efficiency associated with operational settings of the pump, and control the pump using the operational settings to achieve the predicted cluster efficiency.

Hybrid optimization of fault detection and interpretation

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.

Using distributed sensor data to control cluster efficiency downhole

USE OF DISTRIBUTED SENSOR DATA TO MONITOR THE EFFICIENCY OF DOWNHOLE CLUSTERS

Un système permettant de déterminer une efficacité de grappe en temps réel pour une opération de pompage dans un puits de forage comprend une pompe, un capteur de surface, un système de capteur de fond de puits et un dispositif informatique. La pompe peut pomper de la boue ou du matériau de déviation dans le puits de forage. Le capteur de surface peut être positionné à une surface du puits de forage pour détecter des données de surface concernant la pompe. Le système de capteur de fond de puits peut être positionné dans le puits de forage pour détecter des données de fond de puits concernant un environnement du puits de forage. Le dispositif informatique peut recevoir les données de surface depuis le capteur de surface, recevoir les données de fond de puits depuis le système de capteur de fond de puits, appliquer les données de surface et les données de fond de puits à un réseau neuronal à mémoire à court et long terme (LSTM) pour produire une efficacité de grappe prédite associée aux paramètres opérationnels de la pompe, et contrôler la pompe à l’aide des paramètres opérationnels pour atteindre l’efficacité de grappe prédite. A system for determining a cluster efficiency in real time for a wellbore pumping operation includes a pump, a surface sensor, a downhole sensor system and a computing device. The pump can pump mud or deflection material into the wellbore. The surface sensor can be positioned on a surface of the wellbore to detect surface data regarding the pump. The downhole sensor system can be positioned in the wellbore to detect downhole data relating to a wellbore environment. The computing device can receive surface data from the surface sensor, receive downhole data from the downhole sensor system, apply surface data and downhole data to a memory neural network. short and long term (LSTM) to produce predicted cluster efficiency associated with operational parameters of the pump, and control the pump using operational parameters to achieve predicted ...

Fault detection based on seismic data interpretation

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.

MULTIVARIABLE ANALYSIS OF SEISMIC DATA, MICROSISMIC DATA, AND PETROPHYSICAL PROPERTIES IN FRACTURE MODELING

Une analyse multivariable peut être utilisée pour mettre en corrélation des attributs sismiques pour une formation souterraine avec des propriétés pétrophysiques de la formation souterraine et/ou des données microsismiques associées au traitement, à la création, et/ou à l'extension d'un réseau de fractures de ladite formation souterraine. Par exemple, un procédé peut impliquer la modélisation de propriétés pétrophysiques d'une formation souterraine, des données microsismiques associées au traitement d'un réseau de fractures complexes dans la formation souterraine, ou une combinaison correspondante avec un modèle mathématique basé sur des données mesurées, des données microsismiques, des données de conditionnement et de traitement ou une combinaison correspondante, pour produire une carte des propriétés pétrophysiques, une carte des données microsismiques, ou une combinaison correspondante ; et la mise en corrélation entre une carte des attributs sismiques avec la carte des propriétés pétrophysiques, la carte des données microsismiques ou la combinaison correspondante en utilisant le modèle mathématique pour produire au moins une corrélation quantifiée, dans lequel la carte des attributs sismiques est une carte des attributs sismiques modélisée pour le réseau de fractures complexes. Multivariate analysis can be used to correlate seismic attributes for underground formation with petrophysical properties of the subterranean formation and / or microseismic data associated with the treatment, creation, and / or extension of a network. fractures of said subterranean formation. For example, a process may involve modeling petrophysical properties of a subterranean formation, microseismic data associated with the processing of a complex fracture network in the subterranean formation, or a corresponding combination with a mathematical model based on measured data, microseismic data, conditioning and processing data, or a combination thereof, for producing a ...

Workflow optimization

Collapsible shipping container

A collapsible container that includes a base, a first side panel hingedly attached to the base, a second side panel hingedly attached to the base, a first end panel hingedly attached to the base, with the first end panel including a door, and a second end panel hingedly attached to the base. The collapsible container can further include a top cover. The collapsible container is configured to be positioned in a collapsed position and an assembled position. In an assembled position, the collapsible container is configured to hold items during a domestic or international move.

Workflow optimization

A computer implemented method, computer program product, and system for managing execution of a workflow comprising a set of subworkflows, comprising optimizing the set of subworkflows using a deep neural network, wherein each subworkflow of the set of subworkflows has a set of tasks, wherein each task of the sets of tasks has a requirement of resources of a set of resources; wherein each task of the sets of tasks is enabled to be dependent on another task of the sets of tasks, training the deep neural network by: executing the set of subworkflows, collecting provenance data from the execution, and collecting monitoring data that represents the state of said set of resources, wherein the training causes the neural network to learn relationships between the states of said set of resources, the said sets of tasks, their parameters and the obtained performance, optimizing an allocation of resources of the set of resources to each task of the sets of tasks to ensure compliance with a user-defined quality metric based on the deep neural network output.

System and method for machine learning using multiple models

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.

Geostatistical analysis of microseismic data in fracture modeling

A method may comprise: modeling a complex fracture network within the subterranean formation with a mathematical model based on a natural fracture network map and measured data of the subterranean formation collected in association with a fracturing treatment of the subterranean formation to produce a complex fracture network map; importing microseismic data collected in association with the fracturing treatment of the subterranean formation into the mathematical model; identifying directions of continuity in the microseismic data via a geostatistical analysis that is part of the mathematical model; and correlating the directions of continuity in the microseismic data to the complex fracture network with the mathematical model to produce a microseismic-weighted (MSW) complex fracture network map.

System of and method for load recommendations

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.

Workflow optimization

Managing execution of a workflow has a set of subworkflows. Optimizing the set of subworkflows using a deep neural network, each subworkflow of the set has a set of tasks. Each task of the sets has a requirement of resources of a set of resources; each task of the sets is enabled to be dependent on another task of the sets of tasks. Training the deep neural network by: executing the set of subworkflows, collecting provenance data from the execution, and collecting monitoring data that represents the state of said set of resources. Training causes the neural network to learn relationships between the states of the set of resources, the sets of tasks, their parameters and the obtained performance. Optimizing an allocation of resources to each task to ensure compliance with a user-defined quality metric based on the deep neural network output.

Workflow optimization

Managing execution of a workflow has a set of subworkflows. Optimizing the set of subworkflows using a deep neural network, each subworkflow of the set has a set of tasks. Each task of the sets has a requirement of resources of a set of resources; each task of the sets is enabled to be dependent on another task of the sets of tasks. Training the deep neural network by: executing the set of subworkflows, collecting provenance data from the execution, and collecting monitoring data that represents the state of said set of resources. Training causes the neural network to learn relationships between the states of the set of resources, the sets of tasks, their parameters and the obtained performance. Optimizing an allocation of resources to each task to ensure compliance with a user-defined quality metric based on the deep neural network output.

Workflow optimization

Managing execution of a workflow has a set of subworkflows. Optimizing the set of subworkflows using a deep neural network, each subworkflow of the set has a set of tasks. Each task of the sets has a requirement of resources of a set of resources; each task of the sets is enabled to be dependent on another task of the sets of tasks. Training the deep neural network by: executing the set of subworkflows, collecting provenance data from the execution, and collecting monitoring data that represents the state of said set of resources. Training causes the neural network to learn relationships between the states of the set of resources, the sets of tasks, their parameters and the obtained performance. Optimizing an allocation of resources to each task to ensure compliance with a user-defined quality metric based on the deep neural network output.

System for and method of multiple machine learning model aggregation

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.

Reservoir fluid property modeling using machine learning

System and methods for tuning equation of state (EOS) characterizations are presented. Pressure-volume-temperature (PVT) data is obtained for downhole fluids within a reservoir formation. A component grouping for an EOS model of the downhole fluids is determined, based on the obtained PVT data. The component grouping is used to estimate properties of the downhole fluids for a current stage of a downhole operation within the formation. A machine learning model is trained to minimize an error between the estimated properties and actual fluid properties measured during the current stage of the operation, where the component grouping for the EOS model is iteratively adjusted by the machine learning model until the error is minimized. The EOS model is tuned using the adjusted component grouping. Fluid properties are estimated for one or more subsequent stages of the downhole operation to be performed along the wellbore, based on the tuned EOS model.

Contenedor de envio plegable.

Un contenedor plegable que incluye una base, un primer panel lateral unido de forma articulada a la base, un segundo panel lateral unido de forma articulada a la base, un primer panel de extremo unido de forma articulada a la base, incluyendo el primer panel de extremo una puerta, y un segundo panel de extremo unido de forma articulada a la base. El contenedor plegable puede incluir además una cubierta superior. El contenedor plegable está configurado para colocarse en una posición plegada y en una posición ensamblada. En una posición ensamblada, el contenedor plegable está configurado para contener artículos durante una mudanza nacional o internacional.

System of and method for load recommendations

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.

System for and method of multiple machine learning model aggregation

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.

Workflow optimization

Sistema y metodo para las recomendaciones de carga.

Sistemas, métodos y medios de almacenamiento legibles por ordenador para recomendar cargas para el transporte. Un sistema puede recibir coordenadas de ubicación para un vehículo de transporte y recibir además datos sobre las cargas disponibles que pueden ser transportadas por el vehículo de transporte. Después, el sistema puede filtrar las cargas disponibles basándose, al menos en parte, en las coordenadas de ubicación. El sistema puede recibir también al menos un perfil del transportista y al menos un perfil del remitente. Finalmente, el sistema puede ejecutar un algoritmo de recomendación de carga usando las cargas filtradas de preferencia, el al menos un perfil del transportista y el al menos un perfil del remitente como entradas, lo que da como resultado al menos un puntaje de recomendación de carga para una carga dentro de las cargas filtradas preferidas.