Provided is a method and apparatus for predicting oil and gas yields in in-situ oil shale exploitation, the method includes: acquiring an original TOC value, a Ro value and an original HI value of a shale to be measured; and obtaining oil and gas yields in in-situ exploitation of the shale based on the original TOC value, Ro value, original HI value thereof and pre-established models for predicting oil and gas yields in in-situ oil shale exploitation, the models are pre-established based on oil and gas yield data obtained by performing a thermal simulation experiment on a plurality of different shale samples, and the original TOC value, Ro value and original HI value thereof. The above technical solution achieves a quantitative prediction of oil and gas yields in in-situ oil shale exploitation, and improves the accuracy and efficiency of prediction of oil and gas yields in in-situ oil shale exploitation.

A method for predicting an occurrence of a geological feature in a borehole image log using a backpropagation-enabled process trained by inputting a set of training images (12) of a borehole image log, iteratively computing a prediction of the probability of occurrence of the geological feature for the set of training images and adjusting the parameters in the backpropagation-enabled model until the model is trained. The trained backpropagation-enabled model is used to predict the occurrence of the geological features in non-training borehole image logs. The set of training images may include non- geological features and/or simulated data, including augmented images (22) and synthetic images (24).

Systems and methods include a computer-implemented method for predicting hydraulic fracture initiation. A fracking operations dataset is prepared using historical field information for fracking wells. A set of hyper-parameters is tuned for use in a machine learning algorithm configured to predict fracture initiation for new fracturing wells. The dataset is divided into training and test datasets. A regression algorithm is applied to train the training dataset and to validate with the test dataset. A target variable of a breakdown pressure for a new hydraulic fracturing treatment is determined. A prediction dataset is updated using at least the target variable. The training dataset is trained using a classifier of the machine learning algorithm. A prediction is made using the prediction dataset whether the new hydraulic fracturing treatment can be initiated or not. The breakdown pressure is incrementally adjusted, and the method is repeated until successful hydraulic fracture initiation is predicted.

A method of training a machine learning model to predict seafloor ripple geometry that includes receiving one or more input values, each input value based on an observation associated with ocean wave and seafloor conditions, and preprocessing the one or more input values. The method includes generating a training data set based on the preprocessed data set, splitting the training data set into a plurality of folds, and training via stacked generalization the machine learning model by performing a cross validation of each fold of training data based on at least one deterministic equilibrium ripple predictor model and on at least one machine learning algorithm. The method may include generating via the trained machine learning model, a set of one or more seafloor ripple geometry predictions, and performing Bayesian regression on the set of one or more seafloor ripple predictions to generate a probabilistic distribution of predicted seafloor ripple geometry.

The present invention relates to a method for determination of real subsoil composition or structure characterized in that the method comprises: —receiving a model representing the real subsoil, said model comprising at least one parametric volume describing a geological formation in said model, said volume having a plurality of cells; —for each cell in the plurality of cells, determining a quality index (QI.sub.cell) function of a respective position of the cell in the geological formation; —receiving a set of facies, each facies in said set being associated with a proportion and a quality index ordering in said formation; —associating a facies to each cell, said association comprising: /a/ selecting a cell with a lowest quality index within cells in the plurality of cells having no facies associated to; /b/ associating, to said cell, a facies with a lowest Quality index ordering within facies of the set of facies for which the respective proportion is not reached in the formation; /c/ reiterating steps /a/ to /c/ until all cells in the plurality of cells are associated with a facies.

A computer-implemented method for constrained multi-phase virtual flow metering and forecasting is described. The method includes predicting instantaneous flow rates and forecasting future target flow rates and well dynamics. The method includes constructing a virtual sensing model trained using forecasted target flow rates and well dynamics. The method includes building a constrained forecasting model by combining unconstrained flow forecasting models, well dynamics models, and virtual sensing models, wherein the constrained forecasting model forecasts multi-phase flow rates.

Systems and methods for generating a curtain plot that includes two inverted parameters based on the formation boundaries and the formation resistivity, the uncertainties of the formation boundaries, and the uncertainties of the drilled well-path, generating an updated curtain plot that includes two projected inverted parameters based on updated formation boundaries and updated formation resistivity, the projected uncertainties of the updated formation boundaries, and the projected uncertainties of the planned well-path, and avoiding, by the drilling operations, the uncertainties of the formation boundaries of the curtain plot and the updated curtain plot based on the two inverted parameters and the two projected inverted parameters to maintain or adjust the planned well-path within the projected uncertainties of the planned well-path.

Methods and systems are provided for inverted detection and positioning of a strip-like subterranean tunnel in a mountain mass, pertaining to the field combining theories of the discipline of geophysics and remote sensing technology. The method includes: using a model of thermal radiation between a mountain mass and an air layer in conjunction with DEM data to calculate solar radiation energy, and iteratively filtering out background heat flow field energy of the mountain mass; calculating mountain mass background heat propagation energy with reference to hyperspectral data; using a subterranean target inversion model to filter out each layer of background heat flow field energy of the mountain mass in an infrared remote sensing image, and acquiring an optimal elevation of the strip-like subterranean tunnel in the mountain mass and a disturbance signal distribution image constructed via strip-like subterranean tunnel heat flow field energy in each layer of the mountain mass; and using a Hough transform detection method to detect a straight line in the disturbance signal distribution image, performing fitting according to the principle of relevance of tunnel engineering design to acquire a detected location of the tunnel. In this way, inverted detection and positioning of a strip-like subterranean tunnel in a mountain environment is achieved.

The present disclosure is directed to numerically estimating the shear modulus of Kerogen by using a combination of mineralogy from digital image analysis and sonic log analysis, when measured data on only one elastic constant (Bulk, Young's or P-wave modulus) is available. In some instances, elastic properties predicted from the digital images are compared with sonic, shear, and density logs, to estimate the shear modulus of kerogen. As a one-to-one correspondence is not expected between the core sub-samples and the rock unit sampled by the well logs, cross-property relations can be used to identify the suitability of the effective medium models and to iteratively determine the shear modulus of kerogen.

A method for formation evaluation may comprise forming one or more model parameters from one or more priori geological information and one or more downhole measurements, identifying one or more inversion controls, and performing a forward model operation using a piecewise polynomial model (PPM). The method may further comprise performing an optimization using at least the forward model operation, the one or more model parameters, and the one or more inversion controls, determining if a misfit between the one or more downhole measurements and the one or more model parameters is greater than or less than a threshold, and updating the forward model operation or the one or more priori geological information based at least in part on the misfit.