Abstract: This disclosure describes systems and methods for determining spatial distributions of petrophysical properties in a subsurface formation. A method includes obtaining input data including petrophysical data, geophysical data and geological data of the subsurface formation; selecting input features from the input data; forming a training dataset including the input features and corresponding labeled data representing a target petrophysical property of the subsurface formation; training, using the training dataset, an ensemble machine learning model; and determining a spatial distribution of the target petrophysical property based on the trained ensemble machine learning model.

Abstract: Methods for seismic imaging of a subterranean geological formation include receiving first acoustic impedance data, having a first resolution, associated with wells in a subsurface region. A system receives seismic data including second acoustic impedance data having a second resolution. The system performs a quality control process configured to identify a mismatch between the first acoustic impedance data and the second acoustic impedance data. The system resamples the second acoustic impedance data into a three-dimensional (3D) grid model. The system scales up the first acoustic impedance data into the 3D grid model. The system downscales the second acoustic impedance data controlled by the first acoustic impedance data in the 3D grid model. The system generates third acoustic impedance data representing fine-scale impedance data. The system extrapolates the fine-scale impedance into areas or regions having no seismic data coverage or poor seismic data coverage.

Abstract: A 3D facies model generator system and methods thereof include a processor and repository comprising (i) facies data, (ii) sequence stratigraphy, and (iii) a depositional model for a subject reservoir. The processor is operable to generate a 3D stratigraphic sequence framework comprising a plurality of facies based on received facies data and sequence stratigraphy, generate a facies volume fraction for each facies, compare each facies volume fraction with the depositional model for the subject reservoir, reassign the facies volume fraction for the facies of the plurality of facies to another facies of the plurality of facies when the comparison determines that the facies of the 3D stratigraphic sequence framework is incorrectly assigned, generate a plurality of 3D probability trends for the plurality of facies based on the facies volume fraction for the respective facies, and generate the 3D facies model based on the 3D probability trends.

Abstract: Systems and methods for updating a reservoir model are disclosed. In one embodiment, a method of updating a reservoir computer model includes receiving actual well data from a plurality of wells, and accessing model well data from the reservoir computer model for a plurality of modeled wells, wherein the plurality of modeled wells correspond to the plurality of wells. The method further includes comparing the actual well data to the model well data according to a grid model vertical mismatch metric. When the grid model vertical mismatch metric is satisfied, the method includes globally updating the reservoir computer model. When the grid model vertical mismatch metric is not satisfied, the method includes comparing the plurality of wells of the actual well data to a cluster metric, when the cluster metric is satisfied, locally updating the reservoir computer model, and when the cluster metric is not satisfied, globally updating the reservoir computer model.

Abstract: A 3D facies model generator system and methods thereof include a processor and repository comprising (i) facies data, (ii) sequence stratigraphy, and (iii) a depositional model for a subject reservoir. The processor is operable to generate a 3D stratigraphic sequence framework comprising a plurality of facies based on received facies data and sequence stratigraphy, generate a facies volume fraction for each facies, compare each facies volume fraction with the depositional model for the subject reservoir, reassign the facies volume fraction for the facies of the plurality of facies to another facies of the plurality of facies when the comparison determines that the facies of the 3D stratigraphic sequence framework is incorrectly assigned, generate a plurality of 3D probability trends for the plurality of facies based on the facies volume fraction for the respective facies, and generate the 3D facies model based on the 3D probability trends.

Abstract: Systems and methods include a computer-implemented method for optimizing variogram ranges uncertainties. Variogram modeling is performed using variogram models on wells in parallel (major), normal (minor), and vertical directions for continuous log porosity to select a best-fit variogram model using large uncertainty ranges and a preferred-normal distribution. A distribution of geological properties is determined onto the best-fit variogram model. Multiple realizations are executed to determine predicted porosities over the best-fit variogram model. Correlation coefficients of actual porosity versus predicted porosity are generated using the multiple realizations. The process is repeated until a correlation meets a predetermined acceptance criteria. A variogram range for the best-fit variogram model is optimized using a high correlation realization. Correlations are determined for the subset of wells by executing multiple realizations using a same seed number.

Abstract: Systems and methods for updating a reservoir model are disclosed. In one embodiment, a method of updating a computer model includes receiving actual well data from a plurality of wells, and accessing model well data from the computer model for a plurality of modeled wells, wherein the plurality of modeled wells correspond to the plurality of wells. The method further includes comparing, by a computing device, the actual well data to the model well data according to a grid model vertical mismatch metric. When the grid model vertical mismatch metric is satisfied, the method includes globally updating the computer model. When the grid model vertical mismatch metric is not satisfied, the method includes comparing the plurality of wells of the actual well data to a cluster metric, when the cluster metric is satisfied, locally updating the computer model, and when the cluster metric is not satisfied, globally updating the computer model.