RESUMEN
A reliable and practical determination of a chemical species' solubility in water continues to be examined using empirical observations and exhaustive experimental studies alone. Predictions of chemical solubility in water using data-driven algorithms can allow us to create a rationally designed, efficient, and cost-effective tool for next-generation materials and chemical formulations. We present results from two machine learning (ML) modeling studies to adequately predict various species' solubility using data for over 8400 compounds. Molecular-descriptors, the most used method in previous studies, and Morgan fingerprint, a circular-based hash of the molecules' structures, were applied to produce water solubility estimates. We trained all models on 80% of the total datasets using the Random Forest (RFs) technique as the regressor and tested the prediction performance using the remaining 20%, resulting in coefficient of determination (R2) test values of 0.88 and 0.81 and root-mean-square deviation (RMSE) test values 0.64 and 0.80 for the descriptors and circular fingerprint methods, respectively. We interpreted the produced ML models and reported the most effective features for aqueous solubility measures using the Shapley Additive exPlanations (SHAP) and thermodynamic analysis. Low error, ability to investigate the molecular-level interactions, and compatibility with thermodynamic quantities made the fingerprint method a distinct model compared to other available computational tools. However, it is worth emphasizing that physicochemical descriptor model outperformed the fingerprint model in achieving better predictive accuracy for the given test set.
RESUMEN
The calcium carbonate (CaCO3) scale is one of the most common oilfield scales and oil and gas production bane. CaCO3 scale can lead to a sudden halt in production or, worst-case scenario, accidents; therefore, CaCO3 scale formation prevention is essential for the oil and gas industry. Scale inhibitors are chemicals that can mitigate this problem. We used two popular theoretical techniques in this study: Density Functional Theory (DFT) and Ab Initio Molecular Dynamics (AIMD). The objective was to investigate the inhibitory abilities of mixed oligomers, specifically acrylamide functionalized silica (AM-Silica). DFT studies indicate that Ca2+ does not bind readily to acryl acid and acrylamide; however, it has a good binding affinity with PAM and Silica functionalized PAM. The highest binding affinity occurs in the silica region and not the -CONH functional groups. AIMD calculations corroborate the DFT studies, as observed from the MD trajectory that Ca2+ binds to PAM-Silica by forming bonds with silicon; however, Ca2+ initially forms a bond with silicon in the presence of water molecules. This bonding does not last long, and it subsequently bonds with the oxygen atoms present in the water molecule. PAM-Silica is a suitable calcium scale inhibitor because of its high binding affinity with Ca2+. Theoretical studies (DFT and AIMD) have provided atomic insights on how AM-Silica could be used as an efficient scale inhibitor.