Breaking barriers in surface tension prediction of aqueous organics: A Hansen parameter-based machine learning model optimized with a genetic algorithm

• The ML model predicts surface tension accurately with minimal, accessible inputs. • The genetic algorithm-optimized model boosts accuracy and expands coverage. • The studied aqueous organics cover one of the most diverse sets to date. • The model outperforms SRK, PR, and CPA in predicting entirely unseen systems. • This simple yet accurate ML model is extendable to ternary and complex systems. A practical and generalizable machine learning model was developed to predict the surface tension of aqueous organic solutions, relevant to a wide range of applications, including CO 2 capture, pharmaceuticals, membranes, and energy. Aqueous solutions of various organic compounds—such as alcohols, acids, amines, surfactants, and sophorolipids—were used to train a multilayer perceptron artificial neural network (MLPANN), a powerful machine learning tool. To balance simplicity and accuracy, the network’s architecture was optimized using a genetic algorithm, rather than relying on traditional or non-traditional calculation methods. Furthermore, to enhance practicality, in addition to essential variables such as temperature, composition, and molecular weight, only the Hansen solubility parameters (HSPs) of water and the organic component were used as inputs. The proposed approach successfully correlated 319 training data points, yielding an average absolute relative deviation (AARD) of 2.61 %. In prediction mode, it achieved an AARD of 3.53 % for 66 testing data points, demonstrating robust predictive accuracy. Its extrapolation capability was further validated on the unseen monoethanolamine (MEA) + water system, where it achieved an AARD of 2.41 % across a broad range of temperatures and compositions. This approach presents a practical and novel solution for predicting the surface tension of any aqueous organic solution, striking an optimal balance between simplicity, accuracy, and generality. Its capacity to handle both pure and binary mixtures with minimal input makes it easily extendable to ternary and multicomponent systems. Furthermore, it offers valuable insights for the modeling of other thermophysical properties.