One of the key aspects of successful field exploration and monitoring of reservoir development is the spatial prediction of hydrocarbon saturation of geological structures. Traditional prediction methods based on various types of elastic inversion of seismic data may be limited in conditions of a complex geological structure and insufficient coverage of the studied space with well data. In such situations, machine learning algorithms can become an effective tool for the nonlinear, multidimensional generalization of knowledge obtained by geophysical methods in the well space to the entire territory covered by 3D seismic surveys. The study proposes a new approach to knowledge transfer, which consists in predicting the probability of gas saturation of the territory using ensembles of classifiers trained on data from logging studies of hydrocarbon saturation along the well trajectory. Attributes of the seismic field are used as predictors.

The aim of this work is to create and apply a methodological approach for predicting gas traps from 3D seismic data and gas well testing. The proposed approach is based on binary classification algorithms with training on well data. The study includes the following sequence of operations: interpretation of gas well test results to determine the radius of radial gas filtration (IARF); correlation of the top and bottom of productive horizons based on seismic data in the near-wellbore space; creating volumes of space for positive and negative class; dividing the sample into training and validation; creation of a separate test sample for the metamodel; creation of a feature space - extraction of seismic wavefield attributes; creation of data sampling - assignment of a vector of seismic attributes to each point of space within the volumes of classes; selection of features; basic model training; generalized assessment of trait contribution; creation of an ensemble of classification models using a metamodel - logistic regression; prediction of the probability of space belonging to gas reservoirs; evaluation of forecast quality on a test sample. The paper formalizes an approach to creating a training dataset by selecting volumes with established gas saturation and filtration properties within a seismic wavefield. The volumes divide the studied space into positive and negative classes. Positive class is a volume of gas-saturated sands, identified by the results of detailed correlation of the gas sandstone top and bottom, within which there is a region with a boundary along the radius of continuous radial gas filtration.

The aim of this study is to develop and apply an autonomous approach for predicting the probability of hydrocarbon reservoirs spreading in the studied area. The methodology uses machine learning algorithms in the problem of binary classification, which restore the probability function of the space element belonging to the classes identified by the results of interpretation of well logging. Attributes of seismic wavefield are used as predictors. The study includes the following sequence of actions: creation of data sets for training, selection of features, reverse-calibration of data, creation of a population of classification models, evaluation of classification quality, evaluation of the contribution of features in the prediction, ensembling the population of models by stacking method. As a result, a prediction was made - a three-dimensional cube of calibrated probabilities of belonging of the studied space to the class of reservoir and its derivative in the form of the map of reservoir thicknesses of the Achimov complex of deposits was obtained. Assessment of changes in the quality of the forecast depending on the use of different data sets was carried out. Conclusion. The reverse-calibration method proposed in this work uses the uncertainty of geophysical data as a hyperparameter of the global tuning of the technological stack, within the given limits of the a priori error of these data. It is shown that the method improves the quality of the forecast. The technological stack of machine learning algorithms used in this work allows expert-independent generalization of geological and geophysical data, and use this generalization to test hypotheses and create geological models based on a probabilistic view of the reservoir.

The aim of this work was to predict the probability of the spread of rock formations with hydrocarbon-collecting properties in the studied coastal area using a stack of machine learning algorithms and data augmentation and modification methods. This research develops the direction of machine learning where training is conducted on well data and spatial attributes. Methods for overcoming the limitations of this direction are shown, two methods - augmentation and modification of the well data sample: Spindle and Revers-Calibration. Considering the difficulties for seismic data interpretation in coastal area conditions, the proposed approach is a tool which is able to work with the whole totality of geological and geophysical data, extract the knowledge from 159-dimensional space spatial attributes and make facies spreading prediction with acceptable quality - F1 measure for reservoir class 0.798 on average for evaluation of "drilling" results of different geological conditions. It was shown that consistent application of the proposed augmentation methods in the implemented technology stack improves the quality of reservoir prediction by a factor of 1.56 relative to the original dataset.

This paper presents a successful attempt to overcome the uncertainties in seismicstratigraphic interpretation of the complex rock section with good accuracy for the early stage of field maturity. The deliverable included the model of restored regression relationship between the values of natural radioactivity of rocks and seismic wave field attributes with an acceptable prediction quality. Acceptable quality of the forecast is confirmed both by model validation with complete removal of some data from the learning process, and by the data obtained following the results of a new well drilled 150 meters away from the well from the learning sample. The regression relationship between the natural radioactivity of rocks and effective porosity of reservoirs was restored based on well tops data and log interpretation data - transition to reservoir properties of the target was carried out. The result was achieved with help of process stack consisting of machine learning methods, methods of enriching the source data with synthetic data, algorithms of creating new features using the function for regression model reconstruction as the target one, measurements of natural radioactivity of rocks, including for horizontal segments of wells. Two approaches were developed to enriching the source sample (geophysical data augmentations): spindle method and with help of Conditional Generative Adversarial Nets architecture (CGAN).

This paper described a method for reconstruction of detailed-resolution depth structure maps, usually obtained after the 3D seismic surveys, using the data from 2D seismic depth maps. The method uses two algorithms based on the generative-adversarial neural network architecture. The first algorithm StyleGAN2-ADA accumulates in the hidden space of the neural network the semantic images of mountainous terrain forms first, and then with help of transfer learning, in the ideal case - the structure geometry of stratigraphic horizons. The second algorithm, the Pixel2Style2Pixel encoder, using the semantic level of generalization of the first algorithm, learns to reconstruct the original high-resolution images from their degraded copies (super-resolution technology). There was demonstrated a methodological approach to transferring knowledge on the structural forms of stratigraphic horizon boundaries from the well-studied areas to the underexplored ones. Using the multimodal synthesis of Pixel2Style2Pixel encoder, it is proposed to create a probabilistic depth space, where each point of the project area is represented by the density of probabilistic depth distribution of equally probable reconstructed geological forms of structural images. Assessment of the reconstruction quality was carried out for two blocks. Using this method, credible detailed depth reconstructions comparable with the quality of 3D seismic maps have been obtained from 2D seismic maps.