Obviously, in last years complexity of oil and gas fields has increased dramatically and the era of simple and easy retrievable resources has almost gone. This situation leads to necessity of careful and comprehensive uncertainty quantification and risk analysis during field evaluation and planning development strategy. Conventional and widely used geological modelling algorithms based on kriging and stochastic simulation process produce biased results due to not accurate variogram ranges induced by the lack of knowledge about geological setting of target formation. It is necessary to develop a tool that could explore available geological data and retrieve spatial environmental dependencies of a particular field and then exploit them for the following geological modelling. Modern statistical methods such as machine learning algorithms can be used for these tasks.
In this research applicability of machine learning algorithms for the task of interpolation and reservoir properties prediction within interwell space was analyzed. Robustness and quality of forecast produced by different machine learning models also were considered. Influence of information amount and sparsity of geological data on prognosis accuracy were estimated in order to determine range of used method applicability.

Carbonate reservoirs are well known for high uncertainty in reservoir properties estimation. The article presents integrated analysis of well data (such as core data, log data, well testing data and well performance data) for reservoir characterization and classification in order to revise geological structure and re-estimate mobile oil volume.

The aim of bottomhole sampling is to obtain a small volume of fluid, which is identical to the reservoir oil at initial reservoir conditions. The results of study of reservoir oil PVT (abbreviation from Pressure, Volume, Temperature) properties made in the laboratory can then reasonably be applied to identify phase behavior and properties of reservoir fluids under reservoir conditions. Knowledge of PVT properties of reservoir oil is necessary to estimate of oil capacity, designing of reservoir development and its economic viability. PVT properties of reservoir oil are estimated from: the study of subsurface oil samples; the study of recombined samples from the test separator; mathematical simulation using equation-of-state and empirical correlations. Representative samples of the reservoir oil can be collected mainly by subsurface sampling. In cases of extremely tight (low permeable) reservoirs it may be virtually impossible to get sufficient flow rate to lift the liquids without excessive pressure draw-down and corresponding degassing of reservoir oil at bottomhole conditions. This article deals with on technical and technological solution of subsurface oil sampling when an oil not flow to surface. The use of such a method will help to solve the problem of reliable identification of the reservoir oil properties at reservoir conditions.

Under the conditions where several source rocks can be responsible for oil and gas presence in blocks it’s necessary to determine each contribution and find correlation with oil fluids. Similarity of different oils by geochemical criteria outlines reservoir unity and similarity of oils and source rocks proves probability of its genetic connection. In the terms of huge stratigrafic uncertainties especially at faulted areas where break amplitude may reach up to 1000 meters, Cand O- isotopic systems of carbonate matter can help in correlation between different blocks. Complex methodology including unique ancient rocks age estimation and geochemistry investigation combined with detailed geological and seismic study allowed to justify petroleum play conception and potential sweet spots.

The paper describe of experience to protect gas lift infrastructure at the Orenburg oil and gas condensate field from hydrate. Describe of effect obtained after installation automatic control systems of gas stream injected to wells.

This article is aimed at the technological research in the field of non-seismic methods in oil and gas development. Proper hydraulic fracturing monitoring is one of the main unsolved issue: fracture geometry and propped reservoir volume determination. In this study forward electromagnetic modelling before and after fracking were done to assess its potential applicability in determining the geometry of a cracks.

Developing of oil rims is related of many problems and the main one is the early gas breakthrough. In the current work the solution of the problem is considered by application of new approaches of completion of wells. The combine completion of the wells can increase the effectiveness of development oil rims.

The fields of application of machine learning in the oil industry are actively expanding. Despite this, there are currently no convenient and simple tools that allow you to use machine learning methods to solve applied problems without special programming skills. The purpose of this work is to create a program that will allow to carry out data mining using machine learning algorithms and solve common problems associated with the analysis and construction of predictive models. Created an algorithm to implementation typical stages of the data analysis process (detection of abnormal values, filling the skipped values, smoothing the time series, reducing the dimension of the original feature space) and build a predictive models. Test examples showed that the developed program allows to construct a predictive models, as well as the search for significant features, which is applicable both for the construction of surrogate models for the optimization of oilfield development and for an analysis of hydrodynamic connectivity of wells.

Specific software is developed for qualitative and quantitative ranking of unconventional hydrocarbon reserves location and risk assessment of stimulation technology application in relatively new areas. The product allows to conduct a probabilistic calculation of oil production in the region by the license areas discretization, taking into account the geological and technological parameters, and to conduct a sensitivity analysis of researched area by the cost parameters and oil prices. The final assessment of the region by basic economic parameters allows to rank of the license areas and to conduct a portfolio analysis
of the current resource base of unconventional reserves.

The paper presents an approach to the multi-purpose application of the results of three-dimensional geomechanical modeling: in the field of accident-free well construction, optimization of multi-stage hydraulic fracturing ports on the example of the development of Achimov formations of the Severo-Samburgskoye oilfield.

Deeper exploration of the decisions on the logistical support in the early stages of the life cycle of the field will provide the opportunity to carry out projects in an ambitiously short time, ensuring timely delivery of logistical resources in full. In the current situation, the tasks of conceptual and logistical engineering are considered separately. In this, in the concept only the unit costs for logistical support are taken into account, logistic calculations are not performed. This approach leads not only to the error in estimating costs, but also does not allow to determine the need for logistics facilities at the early stages of the project, which entails additional risks of project implementation. On the other hand, at the input of logistic engineering not always can be a complete and relevant view of the planned complex of construction, which also affects the accuracy of planning. Assessing the risks and uncertainties of logistical schemes and finding the optimal sustainable solution in the early stages of the life cycle of the field should become an integral part of the conceptual design projects. This article focuses on the development of unique algorithms that allow to take into account during the conceptual design the transportation, storage and other operations being conducted under logistical delivery. Development of the tool will allow to work logistics already at the stage of the concept, what is necessary for choosing the optimal solution for integrated conceptual design together with the logistical solutions, taking into account assessment of the cost and risk of different alternatives.

In the cases of absence acoustic logging, alternative methods of calculating the necessary rock properties are required. This article describes the results of applying machine learning technologies to predict the velocities of elastic waves propagation.

The article discusses the use of different approaches to the calculation of technical and economic parameters of oil and gas treatment and pumping facilities in the evaluation of projects and reengineering. The usual practice of assessing the cost of training facilities at an early stage involves the use of analogous facilities designed for a certain composition and properties of the produced fluid. At the same time, the estimated project according to these indicators may differ significantly, both in quantitative and qualitative indicators. To bring the existing analogue to a comparable form, heuristic approaches are often used, such as correcting scale coefficients, the Lenz (Nelson) formula, etc. As calculations show, these approaches often make significant errors in the evaluation of the project, especially when they are applied to such complex objects as oil and gas treatment facilities. Taking into account the fact that the cost of such objects is often a significant part of the total capital costs of the project, the estimation error can be hundreds of millions and billions of rubles. The paper proposes an alternative approach, as well as a software solution that allows you to get the optimized characteristics of the object and more accurate, the cost of the object, taking into account all the main influencing factors and processes, and thereby improve the accuracy of the project evaluation.

Design, adaptation and adoption of new technologies is one of the highest priorities for oil companies. In Gazprom Neft PJSC technological projects aimed on improvement of oil and gas fields development were consolidated into a single document called “Technological Strategy”. The implementation of new technologies allows to reduce the capital and operating costs, increase production, develop new reserves and will have a significant impact on the field development. Long-term investment planning considering technological improvement allows to identify key technological projects, find the way to develop currently unprofitable reserves and set new goals for technological improvement. Calculation of the technological improvement effect requires to consider the interference and synergy of different technological projects. This article considers a complex approach to calculate the influence of technological improvement in a long-term planning of field development.