Smart Optimization of Proactive Control of Petroleum Reservoir

Artificial Intelligence plays an increasingly important role in many industrial applications as it has great potential for solving complex engineering problems. One of such applications is the optimization of petroleum reservoirs production. It is crucial to produce hydrocarbons efficiently as their geological resources are limited. From an economic point of view, optimization of hydrocarbon well control is an important factor as it affects the whole market. The solution proposed in this paper is based on state-of-the-art artificial intelligence methods, optimal control, and decision tree theory. The proposed idea is to apply a novel temporal clustering algorithm utilizing an autoencoder for temporal dimensionality reduction and a temporal clustering layer for cluster assignment, to cluster wells into groups depending on the production situation that occurs in the vicinity of the well, which allows reacting proactively. Then the optimal control of wells belonging to specific groups is determined using an auto-adaptive decision tree whose parameters are optimized using a novel sequential model-based algorithm configuration method. Optimization of petroleum reservoirs production translates directly into several economic benefits: reduction in operation costs, increase in the production effectiveness and increase in overall income without any extra expenditure as only control is changed. This work is licensed under a Creative Commons Attribution-NonCommercial 4.0 International License.

Source Indication and Geochemical Significance of Sedimentary Organic Matters from the Xisha Area, the South China Sea

Although various geochemical and geophysical investigations have already indicated a great resource potential in the Xisha area of the South China Sea, the origin of organic matter and molecular evidence for tracing the migration of hydrocarbons from deep petroleum reservoirs are still lacking. In this study, systematic organic geochemical analyses, including bulk organic matter parameters and lipid biomarkers were performed for deep sediments from two cores. The C/N ratios and δ13C and δ15N values of organic matter in most of the samples, together with the maxima of short-chain n-alkanoic acids and mid-chain n-alkanols, high abundances of monounsaturated fatty acids C18:1ω9 and C22:1ω13, jointly indicate the dominance of marine organic matter. n-Alkanes in sediments from core GMGS4-XH-W06B are characterized by small unresolved complex mixture (UCMs) humps, high odd/even predominance (OEP) and carbon preference index (CPI) values, clearly exhibiting characteristics of modern sediments. However, the sediments for core GMGS4-XH-W03B are featured with big UCMs, associated with OEP and CPI values around 1.0, showing signatures of petroleum hydrocarbons from high maturity sources. Considering the geologic background, the biomarker signatures are solid evidence for indicating the existence of underlying petroleum reservoirs, and may provide the valuable information for assessing the hydrocarbon resources in the Xisha area.

Technologies Involved in the Demulsification of Crude Oil

Due to the use of enhanced recovery processes that necessitate the use of a considerable amount of water, mature petroleum reservoirs generate crude oil with huge amounts of water. The majority of this water gets emulsified into crude oil during production, increasing viscosity and making flow more difficult, resulting in production, transportation, and refining operational challenges that have an influence on corporate productivity. Natural surfactants with a strong potential to create stable emulsions are naturally mixed with crude oils. Because crudes with a high amount of stable emulsion have a lower value, the stable emulsion must be adequately processed to meet industrial requirements. As a result, basic research on natural surfactants that contribute to emulsion stability is examined in order to effectively separate emulsions into oil and water. This would need a review of various emulsification methods as well as the proper formulation for effective demulsification. The petroleum industry recognizes the importance of an efficient demulsification procedure for treating emulsions. Numerous studies on the mechanisms of emulsification and demulsification have been undertaken for decades. To guarantee optimal hydrocarbon output, effective treatment is required. The present paper is to review reported works on the formation of petroleum emulsions, demulsification treatments, and characteristics of fit-for-purpose demulsifiers as well as research trends in emulsion treatment.

Adjoint Numerical Method for a Multiphysical Inverse Problem of Two-Phase Well Testing in Petroleum Reservoirs

Inverse problem solution is an integral part of data interpretation for well testing in petroleum reservoirs. In case of two-phase well tests with water injection, forward problem is based on the multiphase flow model in porous media and solved numerically. The inverse problem is based on a misfit or likelihood objective function. Adjoint methods have proved robust and efficient for gradient calculation of the objective function in this type of problems. However, if time-lapse electrical resistivity measurements during the well test are included in the objective function, both the forward and inverse problems become multiphysical, and straightforward application of the adjoint method is problematic. In this paper we present a novel adjoint algorithm for the inverse problems considered. It takes into account the structure of cross dependencies between flow and electrical equations and variables, as well as specifics of the equations (mixed parabolic-hyperbolic for flow and elliptic for electricity), numerical discretizations and grids, and measurements in the inverse problem. Decomposition is proposed for the adjoint problem which makes possible step-wise solution of the electric adjoint equations, like in the forward problem, after which a cross-term is computed and added to the right-hand side of the flow adjoint equations at this timestep. The overall procedure provides accurate gradient calculation for the multiphysical objective function while preserving robustness and efficiency of the adjoint methods. Example cases of the adjoint gradient calculation are presented and compared to straightforward difference-based gradient calculation in terms of accuracy and efficiency.

Facies Analysis and Sedimentary Architecture of Hybrid Event Beds in Submarine Lobes: Insights from the Crocker Fan, NW Borneo, Malaysia

Hybrid event beds represent the combined effect of multiple geological processes, which result in complex depositional geometries and distinct facies distribution in marine environments. Previous work on hybrid event beds highlights the classification, origin, and types of hybrid facies. However, in the present study, we discuss the development of hybrid event beds in submarine lobes with an emphasis on the analysis of proximal to distal, frontal to lateral relationships and evolution during lobe progradation. Detailed geological fieldwork was carried out in the classical deep-marine Late Paleogene Crocker Fan to understand the relationship between the character of hybrid bed facies and lobe architecture. The results indicate that hybrid facies of massive or structureless sandstone with mud clasts, clean to muddy sand, and chaotic muddy sand with oversized sand patch alternations (H1–H3) are well developed in proximal to medial lobes, while distal lobes mainly contain parallel to cross-laminated clean to muddy hybrid facies (H3–H5). Furthermore, lateral lobes have less vertical thickness of hybrid beds than frontal lobes. The development of hybrid beds takes place in the lower part of the thickening upward sequence of lobe progradation, while lobe retrogradation contains hybrid facies intervals in the upper part of stratigraphy. Hence, the development of hybrid beds in submarine lobe systems has a significant impact on the characterization of heterogeneities in deep-marine petroleum reservoirs at sub-seismic levels.