Numerical models can be used for many purposes in oil and gas engineering, such as production optimization and forecasting, uncertainty analysis, history matching, and risk assessment. However, subsurface problems are complex and non-linear, and making reliable decisions in reservoir management requires substantial computational effort. Proxy models have gained much attention in recent years. They are advanced non-linear interpolation tables that can approximate complex models and alleviate computational effort. Proxy models are constructed by running high-fidelity models to gather the necessary data to create the proxy model. Once constructed, they can be a great choice for different tasks such as uncertainty analysis, optimization, forecasting, etc. The application of proxy modeling in oil and gas has had an increasing trend in recent years, and there is no consensus rule on the correct choice of proxy model. As a result, it is crucial to better understand the advantages and disadvantages of various proxy models. The existing work in the literature does not comprehensively cover all proxy model types, and there is a considerable requirement for fulfilling the existing gaps in summarizing the classification techniques with their applications. We propose a novel categorization method covering all proxy model types. This review paper provides a more comprehensive guideline on comparing and developing a proxy model compared to the existing literature. Furthermore, we point out the advantages of smart proxy models (SPM) compared to traditional proxy models (TPM) and suggest how we may further improve SPM accuracy where the literature is limited. This review paper first introduces proxy models and shows how they are classified in the literature. Then, it explains that the current classifications cannot cover all types of proxy models and proposes a novel categorization based on various development strategies. This new categorization includes four groups multi-fidelity models (MFM), reduced-order models (ROM), TPM, and SPM. MFMs are constructed based on simplifying physics assumptions (e.g., coarser discretization), and ROMs are based on dimensional reduction (i.e., neglecting irrelevant parameters). Developing these two models requires an in-depth knowledge of the problem. In contrast, TPMs and novel SPMs require less effort. In other words, they do not solve the complex underlying mathematical equations of the problem; instead, they decouple the mathematical equations into a numeric dataset and train statistical/AI-driven models on the dataset. Nevertheless, SPMs implement feature engineering techniques (i.e., generating new parameters) for its development and can capture the complexities within the reservoir, such as the constraints and characteristics of the grids. The newly introduced parameters can help find the hidden patterns within the parameters, which eventually increase the accuracy of SPMs compared to the TPMs. This review highlights the superiority of SPM over traditional statistical/AI-based proxy models. Finally, the application of various proxy models in the oil and gas industry, especially in subsurface modeling with a set of real examples, is presented. The introduced guideline in this review aids the researchers in obtaining valuable information on the current state of PM problems in the oil and gas industry.

Asphaltene instability may occur when pressure, temperature and compositional variations affect the reservoir oil. Permeability reduction, wettability alteration, and plugging of wells and flow lines are the consequences of this phenomenon. Therefore, it is crucial to investigate the asphaltene behavior in different thermodynamic conditions by knowing the Asphaltene Precipitation Envelope (APE) in a preventive way rather than the costly clean-up procedures. The selected reservoir oil has faced a remarkable decline in production due to several years of extraction, and Enhanced Oil Recovery (EOR) has been considered as a solution. Therefore, in this paper, a comprehensive study was carried out to predict the effects of different injected gases on asphaltene onset and to prevent future asphaltene precipitation based on the laboratory data. The Advanced Redlich-Kwong-Soave (RKSA) equation of state was considered to develop APE using Multiflash (Infochem Co.). For the selected reservoir oil, with temperature reduction at low temperatures, asphaltene precipitation weakened and made the onset pressure decrease, so this behavior is different from the results obtained in other published reports. On the basis of this model, several sensitivity analyses were performed with different gases (i.e., methane, CO2, N2 and associated gases) to compare the risk of each gas for future EOR strategies. APE tend to expand as the amount of injected gases increases, except for CO2 gas injection, that showed another unconventional behavior for this crude oil. It was observed that for CO2 gas injection below a certain temperature, asphaltene stability increased, which can be considered as a good inhibitor of asphaltene precipitation. L’instabilité des asphaltènes peut se produire lorsque des variations de pression, de température et de composition affectent les réservoirs d’huile conduisant à une réduction de la perméabilité, à l’altération de la mouillabilité et au blocage de l’écoulement dans les puits et les conduites. Par conséquent, il est crucial d’étudier le comportement des asphaltènes pour différentes conditions thermodynamiques en connaissant leur domaine de précipitation (APE, Asphaltene Precipitation Envelope) de manière préventive pour limiter les opérations couteuses de nettoyage. Le réservoir d’huile choisi pour cette étude a subi un déclin remarquable de sa production du fait de plusieurs années d’extraction et la récupération assistée (EOR, Enhanced Oil Recovery) a été considérée comme une solution prometteuse. Par conséquent, dans ce document, une étude détaillée basée sur des données de laboratoire est réalisée afin de prévoir les effets de d’injection de différents gaz lors du début de la précipitation des asphaltènes et pour empêcher toute précipitation ultérieure. L’équation d’état avancée Redlich-Kwong-Soave (RKSA) a été considérée pour établir l’enveloppe APE en utilisant le logiciel Multiflash (Infochem Co.). Pour le réservoir de pétrole sélectionné, une réduction de la température diminua la précipitation d’asphaltènes et fit chuter la pression de départ. Ce comportement diffère des résultats précédemment publiés. De nombreuses analyses de sensibilité ont été réalisées pour différents gaz (méthane, CO2, N2 et gaz associé) dans le but de comparer le taux de risque de chaque gaz pour différentes stratégies de récupération EOR. Les enveloppes APE ont tendance à croître lorsque la quantité de gaz injecté augmente, sauf pour de l’injection de CO2 qui a révélé un comportement non conventionnel avec ce pétrole brut. Il a été constaté qu’avec l’injection de CO2, en-dessous d’une certaine température, la stabilité des asphaltènes augmentait, ce qui peut être considéré comme un bon système d’inhibition de la précipitation des asphaltènes.