Predicting Diffusion Coefficients of Binary and Ternary Supercritical Water Mixtures via Machine and Transfer Learning with Deep Neural Network

Interfacial Tension-Temperature-Pressure-Salinity Relationship for the Hydrogen-Brine System under Reservoir Conditions: Integration of Molecular Dynamics and Machine Learning

Hydrogen (H2) underground storage has attracted considerable attention as a potentially efficient strategy for the large-scale storage of H2. Nevertheless, successful execution and long-term storage and withdrawal of H2 necessitate a thorough understanding of the physical and chemical properties of H2 in contact with the resident fluids. As capillary forces control H2 migration and trapping in a subsurface environment, quantifying the interfacial tension (IFT) between H2 and the resident fluids in the subsurface is important. In this study, molecular dynamics (MD) simulation was employed to develop a data set for the IFT of H2-brine systems under a wide range of thermodynamic conditions (298-373 K temperatures and 1-30 MPa pressures) and NaCl salinities (0-5.02 mol·kg-1). For the first time to our knowledge, a comprehensive assessment was carried out to introduce the most accurate force field combination for H2-brine systems in predicting interfacial properties with an absolute relative deviation (ARD) of less than 3% compared with the experimental data. In addition, the effect of the cation type was investigated for brines containing NaCl, KCl, CaCl2, and MgCl2. Our results show that H2-brine IFT decreases with increasing temperature under any pressure condition, while higher NaCl salinity increases the IFT. A slight decrease in IFT occurs when the pressure increases. Under the impact of cation type, Ca2+ can increase IFT values more than others, i.e., up to 12% with respect to KCl. In the last step, the predicted IFT data set was used to provide a reliable correlation using machine learning (ML). Three white-box ML approaches of the group method of data handling (GMDH), gene expression programming (GEP), and genetic programming (GP) were applied. GP demonstrates the most accurate correlation with a coefficient of determination (R2) and absolute average relative deviation (AARD) of 0.9783 and 0.9767%, respectively.

Adversarial Transferred Data-Assisted Soft Sensor for Enhanced Multigrade Quality Prediction

Although recent transfer learning soft sensors show promising applications in multigrade chemical processes, good prediction performance mainly relies on available target domain data, which is difficult to achieve for a start-up grade. Additionally, only employing a single global model is inadequate to characterize the inner relationship of process variables. A just-in-time adversarial transfer learning (JATL) soft sensing method is developed to enhance multigrade process prediction performance. The distribution discrepancies of process variables between two different operating grades are first reduced by the ATL strategy. Subsequently, by applying the just-in-time learning approach, a similar data set is selected from the transferred source data for reliable model construction. Consequently, with the JATL-based soft sensor, quality prediction of a new target grade is implemented without its own labeled data. Experimental results on two multigrade chemical processes validate that the JATL method can give rise to the improvement of model performance.

Machine Learning Predictions of Simulated Self-Diffusion Coefficients for Bulk and Confined Pure Liquids

Diffusion properties of bulk fluids have been predicted using empirical expressions and machine learning (ML) models, suggesting that predictions of diffusion also should be possible for fluids in confined environments. The ability to quickly and accurately predict diffusion in porous materials would enable new discoveries and spur development in relevant technologies such as separations, catalysis, batteries, and subsurface applications. In this work, we apply artificial neural network (ANN) models to predict the simulated self-diffusion coefficients of real liquids in both bulk and pore environments. The training data sets were generated from molecular dynamics (MD) simulations of Lennard-Jones particles representing a diverse set of 14 molecules ranging from ammonia to dodecane over a range of liquid pressures and temperatures. Planar, cylindrical, and hexagonal pore models consisted of walls composed of carbon atoms. Our simple model for these liquids was primarily used to generate ANN training data, but the simulated self-diffusion coefficients of bulk liquids show excellent agreement with experimental diffusion coefficients. ANN models based on simple descriptors accurately reproduced the MD diffusion data for both bulk and confined liquids, including the trend of increased mobility in large pores relative to the corresponding bulk liquid.

Prediction of Self-Diffusion in Binary Fluid Mixtures Using Artificial Neural Networks

Artificial neural networks (ANNs) were developed to accurately predict the self-diffusion constants for individual components in binary fluid mixtures. The ANNs were tested on an experimental database of 4328 self-diffusion constants from 131 mixtures containing 75 unique compounds. The presence of strong hydrogen bonding molecules may lead to clustering or dimerization resulting in non-linear diffusive behavior. To address this, self- and binary association energies were calculated for each molecule and mixture to provide information on intermolecular interaction strength and were used as input features to the ANN. An accurate, generalized ANN model was developed with an overall average absolute deviation of 4.1%. Forward input feature selection reveals the importance of critical properties and self-association energies along with other fluid properties. Additional ANNs were developed with subsets of the full input feature set to further investigate the impact of various properties on model performance. The results from two specific mixtures are discussed in additional detail: one providing an example of strong hydrogen bonding and the other an example of extreme pressure changes, with the ANN models predicting self-diffusion well in both cases.