Landmark Graphics Corporation

Halliburton Energy Services, Inc.

Landmark Graphics Corporation, a Halliburton Company

Jeffrey Marc Yarus

Genbao Shi

Richard L Chambers

Rae Mohan Srivastava

Marko Maucec

Zitao Xu

Yogendra Narayan Pandey

Jin Fei

Maurice Christopher Gehin

ChiKang David Chien

Veronica Liceras

Ronald Glen Dusterhoft

Harold Grayson Walters

Zhaoyang Wang

Lu Ming Liang

Robello Samuel

Keshava Prasad Rangarajan

Ashwani Dev

Dale E Jamison

Srinath Madasu

Travis St George Ramsay

Robert Lynn Williams

Gustavo Carvajal

Dwight David Fulton

Andres Cesar Callegari

Zhengchun Liu

Jesse Clay Hampton

Shashi Dande

Yevgeniy Zagayevskiy

Amir Bar

Ajay Pratap Singh

Randy Guetter

Gaetan Bardy

Chikang David Chien

Raja Vikram R Pandya

Kalyan Saikia

Trace Boone Smith

Sridharan Vallabhaneni

Jim Ching-Rong Lin

Shohreh Amini

Nagaraj Srinivasan

Yashas Malur Saidutta

Steven James Drinovsky

Jordan Michael Yarus

Larry Gregg Chorn

Daniel James Carruthers

Chi-Kang David Chien

Raquel Morag Velasco

Naresh Chaudhary

James Etienne

Kevin B Hall

Shaolong Wu

Meftun Erdogan

Douglas E Wyatt, Jr

Richard Chambers

Srimoyee Bhattacharya

Travis St Ramsay

Mayrice Gehin

Zhenchun Liu

Maurice Gehin

Systems and methods for modeling petroleum reservoir properties using a gridless reservoir simulation model are provided. Data relating to geological properties of a reservoir formation is analyzed. A tiered hierarchy of geological elements within the reservoir formation is generated at different geological scales, based on the analysis. The geological elements at each of the different geological scales in the tiered hierarchy are categorized. Spatial boundaries between the categorized geological elements are defined for each of the geological scales in the tiered hierarchy. A scalable and updateable gridless model of the reservoir formation is generated, based on the spatial boundaries defined for at least one of the geological scales in the tiered hierarchy.

Point-vector based modeling of petroleum reservoir properties for a gridless reservoir simulation model

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 drilling device may use a concurrent path planning process to create a path from a starting location to a destination location within a subterranean environment. The drilling device can receive sensor data. A probability distribution can be generated from the sensor data indicating one or more likely materials compositions that make up each portion of the subterranean environment. The probability distribution can be sampled, and for each sample, a drill path trajectory and drill parameters for the trajectory can be generated. A trained neural network may evaluate each trajectory and drill parameters to identify the most ideal trajectory based on the sensor data. The drilling device may then initiate drilling operations for a predetermined distance along the ideal trajectory.

Automated concurrent path planning and drilling parameter optimization using robotics

A method for creating a seamless scalable geological model may comprise identifying one or more geological scales, establishing a geological tied system, identifying one or more graphical resolution levels for each of the one or more geological scales, constructing the seamless scalable geological model, and producing a post-process model. A system for creating a seamless scalable geological model may comprise an information handling system, which may comprise a random access memory, a graphics module, a main memory, a secondary memory, and one or more processors configured to run a seamless scalable geological model software.

Seamless scaling geomodeling

Geomechanical parameters can be used to optimize a well configuration that includes one or more projected wells having locations and geometries. Formation data and regional stress information of a formation can be used to determine a local stress variation of the formation. A quality index can be generated by combining petrophysical properties with the local stress variation. Hydrocarbon recovery flow simulations can be generated by generating well configuration models based on the quality index, generating reservoir geomechanical model that includes hydraulic fracture propagation characteristics, determining new hydraulic fractures by simulating propagation through the reservoir geomechanical model and using geomechanical rules, and determining a projected hydrocarbon recovery rate by simulating flow with the new hydraulic fractures. A well placement plan can be selected using the projected hydrocarbon recovery rates. The well placement plan can be output to be used to plan one or more wellbores.

Planning a well configuration using geomechanical parameters

Embodiments of the subject technology for deep learning based reservoir modelling provides for receiving input data comprising information associated with one or more well logs in a region of interest. The subject technology determines, based at least in part on the input data, an input feature associated with a first deep neural network (DNN) for predicting a value of a property at a location within the region of interest. Further, the subject technology trains, using the input data and based at least in part on the input feature, the first DNN. The subject technology predicts, using the first DNN, the value of the property at the location in the region of interest. The subject technology utilizes a second DNN that classifies facies based on the predicted property in the region of interest.

Deep learning based reservoir modeling

Target objects are simulated using different triangle mesh sizes to improve processing performance. To perform the simulation, a seed point for the target object within a constraint volume is determined, the seed point representing a vertex of a first triangle forming part of the target object. One or more hexagonal orbits of triangles adjacent the first triangle are propagated, whereby the hexagonal orbits of triangles form the target object. The size of each triangle is determined based upon dimensions of the target object, and the target object is generated.

Target object simulation using orbit propagation

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.

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

The selection of a candidate formation realization(s) from a plurality of formation realizations may be done with a classification and regression tree (CART) analysis taking into account petrophysical and geological properties. For example, a method may include applying a CART analysis to a plurality of formation realizations using a first formation property as a predictor in the CART analysis, wherein the plurality of formation realizations are for a second formation property and are based on at least one measured formation property, thereby yielding an association between the first and second properties for each of the plurality of formation realizations; analyzing a strength of the association for each of the plurality of formation realizations; and selecting a candidate formation realization from the plurality of formation realizations based on the strength of the association. The identified candidate formation realization(s) may then be used to develop the parameters of subsequent wellbore operations.

Classification and regression tree analysis of formation realizations

Systems and methods for mapping vertices from one coordinate system in an earth model to another coordinate system in a two-dimensional (2D) array without disrupting the topology of the vertices.

Mapping vertices from an earth model to a 2D array

A method may include drilling a deviated wellbore penetrating a subterranean formation according to bottom hole assembly parameters and surface parameters; collecting real-time formation data during drilling; updating a model of the subterranean formation based on the real-time formation data and deriving formation properties therefrom; collecting survey data corresponding to a location of a drill bit in the subterranean formation; deriving a target well path for the drilling based on the model of the subterranean formation; deriving a series of trajectory well paths based on the formation properties, the survey data, the bottom hole assembly parameters, and the surface parameters and uncertainties associated therewith; deriving an actual well path based on the series of trajectory well paths; deriving a deviation between the target well path and the actual well path; and adjusting the bottom hole assembly parameters and the surface parameters to maintain the deviation below a threshold.

Real-time trajectory control during drilling operations

Systems and methods for generating and storing measurements in point and vector format for a plurality of formations of reservoirs. In one embodiment, the methods comprise generating a set of measurements corresponding to a plurality of formations, reservoirs, or wellbores; determining physical locations for the set of measurements, wherein the physical locations are represented in a point and vector representation; associating the vector representations with the determined physical locations, wherein the vector representations comprise at least a magnitude and a direction derived from the measurement; wherein the magnitude and direction tracks the physical location in space and time; manipulating the set of measurements such that a change in physical location is updated in the vector representation; generating a repository of vector representations accessible to determine an optimal completion design for a set of parameters for a subterranean formation.

Big data point and vector model

A method includes generating a faulted point cloud representing a faulted geological formation including a first fault block having a first surface, a second fault block having a second surface, and a fault formed therebetween and having a fault surface, generating a first fault trace from an intersection of the first surface and the fault surface and a second fault trace from an intersection of the second surface and the fault surface, generating a first fault polygon using the first and second fault traces, generating a center polyline, generating third and fourth fault traces separated from the first and second fault traces, respectively, generating a second fault polygon using the third and fourth fault traces, expanding a first area including the first and third fault traces, expanding a second area including the second and fourth fault traces, and generating an unfaulted point cloud representing an unfaulted geological formation.

Systems and methods for unfaulting point clouds

Systems and methods for generating and storing completion design models in a central data repository of models for completion design, well bore (such as fracturing or drilling) or other operations is shown. In one embodiment, the methods comprise identifying parameters of a hydraulic fracturing operation within a subterranean formation; generating a completion design model based on the parameters of the hydraulic fracturing operation; storing the completion design model in a central data repository of models; generating the central data repository of models; wherein the data repository is based on previously generated models for one or more other subterranean formations having varying levels of uncertainty for expected output; reducing the level of uncertainty for the expected output based on completion parameters, wherein the completion parameters are used to update the central data repository of models; accessing the central data repository of models to predict results expected for a data set based at least in part on the central data repository of models, wherein the results comprise a prediction as to a level of output for the dataset, further wherein the prediction comparison results in an identification of the optimized completion design for the dataset.

Completion design optimization using machine learning and big data solutions

The disclosed embodiments include a method, apparatus, and computer program product for modifying a three-dimensional geocellular model. For example, one disclosed embodiment includes a system that includes at least one processor and at least one memory coupled to the at least one processor. The memory stores instructions that when executed by the at least one processor performs operations that includes loading into memory a three-dimensional geocellular model that corresponds to a two-dimensional geological model. The operations include determining a portion of the three-dimensional geocellular model affected by a change to the two-dimensional geological model and performing a local update to the portion of the three-dimensional geocellular model affected by the change.

Local updating of 3D geocellular model

Growing community of inventors

Houston, TX, United States of America

Jeffrey Marc Yarus