Timur Ildarovich Yunusov

Various organic additives can induce structural rearrangement of surfactant micelles in aqueous solutions, leading to enhanced rheological properties, namely an increase in viscosity, appearance of viscoelasticity, and non-Newtonian behavior. This phenomenon can be exploited in several industries to obtain strong gels. The selection of proper additives and their concentrations remains largely empirical owing to the high number of factors influencing structural rearrangement. This paper aims to employ machine learning (ML) methods to predict whether an enhancement of rheological behavior will occur in cetyltrimethylammonium bromide solutions (CTAB) upon addition of an organic compound. Five different shallow ML algorithms were tested along with graph neural networks (GNNs), using a dataset of 605 data points collected from the literature. Two types of descriptors (RDKit and PaDEL) were applied. Shallow ML algorithms achieved a maximum precision of 0.85 under cross-validation with a random fold split, and this performance did not deteriorate significantly when a structure-based split was applied (0.82). The random forest algorithm was selected based on its comparatively stable performance. GNN achieved a precision of 0.85 (random split) and 0.80 (structure-based split). Analysis of relative contribution of system properties and molecular features to the predictions of shallow and GNN models is consistent with the known physicochemical basis. Experimental validation of ML methods on four prospective compounds unseen during training was carried out. Comparison with ML predictions demonstrated that both models can correctly identify compounds that promote rheological enhancement, but tend to overpredict positive outcomes. However, this drawback may be partially mitigated by applying a pessimistic consensus, and then the accuracy of 0.84 and the precision of 0.73 are achieved for evaluation on the experimental dataset. The present work demonstrates that ML methods can be applied to address the problem of surfactant self-aggregation in solution upon addition of organic additives with room remaining for performance improvement.

This paper reviews recent advances in the application of machine learning (ML) methods to quantitative structure-property relationship (QSPR) modelling and molecular generation in surfactant science. As the variety of surfactant species and annual production volumes continue to grow, their proper characterization becomes increasingly important. Artificial intelligence (AI) technologies in chemistry represent a promising set of tools for addressing such tasks, in which ML plays a key role. The scope of the paper encompasses QSPR studies of two categories of surfactant properties: intrinsic properties, among which critical micelle concentration and surface tension are considered separately, and practically relevant industrial properties. Modeling approaches for each property type are compared, and their respective advantages, disadvantages, and challenges are discussed. Generative approaches represent the next stage of ML modelling, and this rapidly evolving field is reviewed. De novo generation of molecular structures and surfactant-based formulations is covered, with the relevant approaches described and compared. Finally, the current state of the field and future prospects of ML and AI applications in surfactant science and industry are outlined. Overall, this paper provides a structured evaluation of ML and AI applications across a range of tasks and demonstrates the broad scope of their utility in surfactant studies.

Chelating agents’ application for well stimulation is gaining more and more interest, as they can perform under harsh conditions. However, the mutual influence of surfactants and chelating agents on the wettability alteration of hydrophobic carbonate rock under conditions of high-temperature well stimulation is relatively unexplored. This paper aims to study interfacial processes on the surface of hydrophobic rock in the presence of the EDTA-based chelating agent and surfactants of different classes. Cationic (cetyltrimethylammonium bromide, CTAB, and cetylpyridinium bromide, CPB), anionic (sodium dodecyl sulfate, SDS), and amhoteric (alkyldimethyl aminooxide, AO) surfactants were studied. Wettability alteration of model hydrophobic rock was studied under conditions specific to well stimulation. It was shown that chelating agent (CA) alone and its mixture with SDS could not lead to sufficient wettability alteration. CTAB, CPB, and AO were able to change the wettability effectively. A synergistic effect between CA and these surfactants was observed and a possible mechanism was proposed. AO was selected as the most promising surfactant. The influence of surfactant on the CA’s dissolution capacity towards carbonate rock was investigated; dissolution capacity strongly depends on wettability alteration. Finally, the effect of CA, AO, and their mixture on the wettability of aged reservoir rock was studied and the absence of negative effects was proven.

Chelating agents’ application for EOR and well stimulation is fast growing nowadays. However, reagents of this class have some drawbacks, with high values of interfacial tension (IFT) being among them. IFT may be lowered with the addition of surfactants; however, the simultaneous application of chelating agents and surfactants has not yet been widely studied. This paper focuses on the experimental and theoretical investigation of the interaction between chelating agent (ethylenediaminetetraacetic acid, EDTA) and surfactants of anionic and cationic types (sodium dodecyl sulfate, SDS, and dodecyl trimethynlammonium bromide, DTAB). IFT measurement was performed at ambient conditions, with normal octane being as the reference hydrocarbon to eliminate the temperature and salinity effects and compare surfactant-containing systems. The experimental results show that chelating agents’ addition to the solutions of surfactants leads to a decrease in IFT value. Moreover, surfactants’ critical micelle concentration is lowered, whereas their effectiveness and efficiency are increased, which points to the salting-out nature of chelating agents. Molecular dynamics reveal that chelating agent addition causes closer packing of surfactant layer, the decrease in head groups’ hydration, and, at least in the case of SDS, specific surfactant–chelating agent attractive interaction. These molecular-level insights, experimental dependencies, and the combined methodology may be useful for the proper selection of fluids for real-field operations.

Rock swelling and rock disintegration in the presence of drilling, stimulation and completion fluids are considered to be the main reasons for operational and production problems for wells in clay-rich formations. The impact of these fluids on rock properties shall be established for the effective treatment design. This paper describes the development of the experimental setup for studying rock swelling in reservoir conditions and the application of this setup for the evaluation of swelling mechanisms of shale rock samples. Swelling quantification was performed using measuring piston displacement that was caused by rock swelling in a piston accumulator during pressure maintenance. We studied the interaction of the disintegrated rock samples with water-based and hydrocarbon-based fluids and supercritical CO₂. It was found that alkaline water solution in reservoir conditions causes swelling of the used rock samples in the amount of 1–3% vol. with a direct correlation between the rock swelling magnitude and the total clay content. The change in the rock volume in the presence of the used hydrocarbon-based fluid depends on the content of organic matter, its distribution in the rock, and the clay content. The observed swelling degree in the hydrocarbon fluid and CO₂ was significantly lower (0–0.5% vol.) than in water. The proposed methodology and obtained results can further be used for the optimization of various operations in clay-rich formations.

Different problems may occur during acid treatment of oil reservoirs because of the incompatibility of acid with rocks and fluids. One of the issues is the formation of acid-in-oil emulsions, which block pore throats and hinder acid removal. The standard “bottle-test” method does not fully characterize such emulsions and allows only quick reagent selection. This article presents a new methodology that enables the evaluation of emulsion formation and the possible risk for acid treatment. This methodology includes visual control and measurement of viscosity, interfacial tension, and voltage stability. We found that HCl-based emulsions are generally more viscous, finer, and stable, but the high strength of the acid may lead to emulsion breakdown. We also established that emulsions that are stable under static conditions may break down after applying mechanical stress, which is a characteristic of sulfamic acid-based emulsions. Although it may not be possible to separate emulsions visually, a water content gradient may be observed in an emulsion column. Our results demonstrate that the acid and oil parameters are interconnected in emulsion formation issues. This methodology and the obtained results may be applied for quick and proper reagent selection for better acid treatment results. Graphical Abstract