The present disclosure relates to a method for determination of a real subsoil geological formation. In at least one embodiment, the method includes receiving a model representing the real subsoil, determining a first fluvial geological formation in said model using parametric surfaces, determining a subsequent fluvial geological formation as a deformation of the first fluvial geological formation using parametric surfaces, and subtracting the first fluvial geological formation from the subsequent fluvial geological formation to create a new geological formation named point bar formation.

A methodology for providing set-point recommendations in an automated manner to optimize the operation of a well-producing fluid, by establishing a live synergy between physics-based simulation and real-time field data, through the employment of machine learning models. The machine learning models serve two distinct purposes in this approach: 1. Accelerate emulation of the numerical physics-based simulation to enable real-time solutions 2. Provide a probabilistic estimate of the unknown operating conditions of a well and updating the estimate based on the response to the set-point changes made, thus improving with each iteration.

Systems and methods for simulating subterranean regions having multi-scale, complex fracture geometries. Non-intrusive embedded discrete fracture modeling formulations are applied in conjunction with commercial or in-house simulators to efficiently and accurately model subsurface characteristics including temperature profiles in regions having complex hydraulic fractures, complex natural fractures, or a combination of both.

Techniques including methods, apparatus and computer program products are disclosed for determining an amount of hydrocarbon recoverable from porous reservoir rock by a miscible gas flood. The techniques include retrieve a representation of a physical porous reservoir rock sample (porous reservoir rock), the representation including pore space and grain space data corresponding to the porous reservoir rock, subsequent to an execution of a multiphase flow simulation to obtain predictions of flow behavior of oil in the presence of a waterflood of the porous reservoir rock, locate substantially immobile oil blobs or patches in the retrieved representation of the porous reservoir rock; and for N number of substantially immobile oil blobs or patches (blobs), evaluate changes in mobility of the blobs for two or more iterations an effort level for of a given EOR technique, with a first one of the two or more iterations expending a first level of effort and a second one of the two or more iterations expending a second, higher level of effort, to estimate an amount of change in mobilization of the blob between the first and the second iterations for the given EOR technique.

Disclosed is a method of quantitatively evaluating structural disturbance characteristics of present in-situ geo-stress in deep shale gas reservoirs, including: measuring geomechanics key parameters of key wells in different tectonic zones within a study area; performing interpretations of single-well profile rock mechanics and continuity of the in-situ geo-stress in magnitude and direction; establishing a geological model; performing anisotropic sequential Gaussian stochastic simulation to obtain three-dimensional (3D) heterogeneous rock mechanics parameter field distribution; performing prediction of distribution of geo-stress states in the study area, and calculating a stress structural index and stress disturbance factor of the target layer and a rotation degree of a maximum horizontal principal stress; and performing quantitative evaluation on an in-situ geo-stress structural disturbance and mapping.

A computer-implemented method for augmented inversion and uncertainty quantification for characterizing geophysical bodies is disclosed. The method includes machine-learning-augmented inversion that also facilitates the characterization of uncertainties in geophysical bodies. The method may further estimate wavelets without a well-log calibration, thereby enabling a pre-discovery exploration phase when well log data is unavailable. The machine learning component incorporates a priori knowledge about the subsurface and physics, such as distributions of expected rock types and rock properties, geological structures, and wavelets, through learning from examples. The methodology also allows for conditioning the characterization with the information extracted a priori about the geobodies, such as probabilities of rock types, using other analysis tools. Thus, the conditioning strategy may make the inversion more robust even when a priori distributions are not well balanced. Using the method, a scenario testing workflow may evaluate different candidate subsurface models, facilitating the management of uncertainty in decision-making processes.

A method and system for outputting a state of a physical system using a calibrated model of the physical system, where the calibrated model is used to generate a model prediction. The system includes a plurality of sensors connected to a routing node are used to monitor measured data of the physical system. A first sensor of the plurality of sensors includes a logic module configured to determine an uncertainty quantification, and to combine the uncertainty quantification with the model prediction to output the state of the physical system.

A glass clamping model based on microscopic displacement experiment, including a frame, a transparent silicone sleeve having a horizontal through hole, a piston, a piston cap arranged on the frame, a connecting plate, a screw compression bracket, a clamp support, a glass sheet entirety placed in the transparent silicone sleeve, a boss, a light source and a microscope. The transparent silicone sleeve is sheathed on the piston cap, the piston penetrates through the horizontal penetration hole; the connecting plate and the clamp support are respectively connected to both ends of the frame, the end of the screw compression bracket is clamped between the frame and the connecting plate, and the piston and the frame are connected with the clamp support; an emptying channel and an inlet passage are respectively arranged at both ends of the piston, and an outlet passage is arranged at an end of the piston.

A method includes receiving a model representing a real subsoil geological formation. The model includes a stratigraphic layer, which includes a shore line dividing the stratigraphic layer into a continental zone and a marine zone. First and second flow speed fields are received, with the first flow speed field representative of a continental domain for the stratigraphic layer, and the second flow speed field representative of a marine domain for the stratigraphic layer. A global flow speed field is determined and includes a weighted combination of the first and second flow speed fields for each position in the stratigraphic layer. Weights of the combination are based on a distance of the position to the shore line and whether the position is within the continental zone or the marine zone. The real subsoil geological formation for the stratigraphic layer is determined based on the determined global flow speed field.

A computer-implemented method is provided for interpreting geophysical data utilising an Artificial Neural Network (ANN), performed by electronic operations executed by a computing device, comprising: performing a training processing step on at least one training-data set, comprising the steps of: (a) generating a first label-data by segmenting said at least one training-data set into at least a first region, representing a known first region having at least one identified geological feature, and/or a second region, representing a known second region having at least one unidentified geological feature, and a third region, representing an unknown region; (b) generating a first ANN model output for a dynamically adaptable Region of Interest (ROI) of said first label-data, said dynamically adaptable ROI including said first and/or second region; (c) generating an updated label-data by selecting at least a first portion of any one of said first, second and third region, and labelingly append at least said first portion to any one of said first, second and third region; (d) generating an updated ANN model output for an updated dynamically adaptable ROI of said updated label-data; (e) repeating steps (c) and (d) until a predetermined condition is met, providing a final ANN model output; and then applying said final ANN model output to a target-data set utilising said ANN, generating a desired output data.