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.

The evolving membrane technology integrated with machine learning (ML) algorithms can significantly advance the novel membrane material design and fabrication. Although several studies have reported ML-based assistance in membrane development, none of them have offered a complete analysis of existing ML-assisted membrane fabrication methods from material design perspective. A two-way information gateway is therefore necessary to achieve the desired objective, whereby experienced researchers and data scientists from both sides need to provide valuable insights into novel membrane development process. In this work, we offer a midway platform by providing an overall view and scopes of ML uses in membrane science. This is accomplished by analyzing reported ML-assisted membrane fabrications via lensing through the overall ML development. This work culminates in identifying four crucial factors affecting ML-assisted membrane development: data mining, material functional description, selection of ML models and model interpretation. A future direction is proposed by making specific ML models and descriptors suggestions, in addition to molecular similarity analysis technique and ML-based image processing. We believe the proposed approaches and analyses through our identified lens will prove crucial for the future of ML-assisted membrane material design and development.